chore: release v2.90.1

Revert "fix(dataset_runs): ensure consistent ordering to fetch score data for…"

This reverts commit 2b2022ae85.

.codespellrc

@@ -1,4 +1,4 @@
 [codespell]
 skip = .git,*.pdf,*.svg,package-lock.json,*.prisma,pnpm-lock.yaml
-ignore-words-list = afterall,vertx
+ignore-words-list = afterall,vertx,notIn
 

.dockerignore

@@ -3,6 +3,6 @@ Dockerfile
 node_modules
 npm-debug.log
 README.md
-.next
+**/.next
 .git
 **/node_modules

.env.dev.example

@@ -6,6 +6,12 @@
 DIRECT_URL="postgresql://postgres:postgres@localhost:5432/postgres"
 DATABASE_URL="postgresql://postgres:postgres@localhost:5432/postgres"
 
+# Clickhouse
+CLICKHOUSE_MIGRATION_URL="clickhouse://localhost:9000"
+CLICKHOUSE_URL="http://localhost:8123"
+CLICKHOUSE_USER="clickhouse"
+CLICKHOUSE_PASSWORD="clickhouse"
+
 # Next Auth
 # You can generate a new secret on the command line with:
 # openssl rand -base64 32
@@ -28,15 +34,36 @@ EMAIL_FROM_ADDRESS=""  # Defines the email address to use as the from address.
 SMTP_CONNECTION_URL=""  # Defines the connection url for smtp server.
 
 # S3 storage
-S3_ENDPOINT=
-S3_ACCESS_KEY_ID=
-S3_SECRET_ACCESS_KEY=
-S3_BUCKET_NAME=
-S3_REGION=
+S3_ENDPOINT=http://localhost:9090
+S3_ACCESS_KEY_ID=minio
+S3_SECRET_ACCESS_KEY=miniosecret
+S3_BUCKET_NAME=langfuse
+S3_REGION=us-east-1
+## Necessary for minio compatibility
+S3_FORCE_PATH_STYLE=true
 
-# Prompt playground
-OPENAI_API_KEY=""
-ANTHROPIC_API_KEY=""
+# # S3 Media Upload LOCAL
+LANGFUSE_S3_MEDIA_UPLOAD_ENABLED=true
+LANGFUSE_S3_MEDIA_UPLOAD_BUCKET=langfuse
+LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID=minio
+LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY=miniosecret
+LANGFUSE_S3_MEDIA_UPLOAD_REGION=us-east-1
+LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT=http://localhost:9090
+## Necessary for minio compatibility
+LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE=true
+LANGFUSE_S3_MEDIA_UPLOAD_PREFIX=media/
+
+# S3 Event Bucket Upload
+## Set to true to test uploading all events to S3
+LANGFUSE_S3_EVENT_UPLOAD_ENABLED=true
+LANGFUSE_S3_EVENT_UPLOAD_BUCKET=langfuse
+LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID=minio
+LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY=miniosecret
+LANGFUSE_S3_EVENT_UPLOAD_REGION=us-east-1
+LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT=http://localhost:9090
+## Necessary for minio compatibility
+LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE=true
+LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
 
 # Set during docker build of application
 # Used to disable environment verification at build time
@@ -46,6 +73,8 @@ REDIS_HOST="127.0.0.1"
 REDIS_PORT=6379
 REDIS_AUTH="myredissecret"
 
-LANGFUSE_WORKER_PASSWORD=mybasicauthsecret
 # openssl rand -hex 32 used only here
-ENCRYPTION_KEY=6c16874e5c0f0cc74ddec00425fa99fbe9ffbe412b7d5d906a4b00005df91403 
+ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000 
+
+# speeds up local development by not executing init scripts on server startup
+NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT="false"

.env.local.example

@@ -13,14 +13,10 @@ NEXTAUTH_URL="http://localhost:3000"
 LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES="false"
 SALT="salt"
 
-
-# Prompt playground
-OPENAI_API_KEY=""
-ANTHROPIC_API_KEY=""
-
 # Redis
 REDIS_HOST="127.0.0.1"
 REDIS_PORT=6379
 REDIS_AUTH="myredissecret"
 
-LANGFUSE_WORKER_PASSWORD=myworkerpassword
+# openssl rand -hex 32 used only here
+ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000

.env.prod.example

@@ -9,28 +9,47 @@
 DATABASE_URL="postgresql://postgres:postgres@db:5432/postgres"
 # DIRECT_URL="postgresql://postgres:postgres@db:5432/postgres"
 # SHADOW_DATABASE_URL=
+# optional, set to true to disable automated database migrations on Docker start
+# LANGFUSE_AUTO_POSTGRES_MIGRATION_DISABLED=
 
 # Next Auth
 # NEXTAUTH_URL does not need to be set when deploying on Vercel
 NEXTAUTH_URL="http://localhost:3000"
 
-# You can generate a new secret on the command line with:
+# For each of these, you can generate a new secret on the command line with:
 # openssl rand -base64 32
-# https://next-auth.js.org/configuration/options#secret
-NEXTAUTH_SECRET="secret"
-SALT="salt"
+NEXTAUTH_SECRET="secret" # https://next-auth.js.org/configuration/options#secret
+SALT="salt" # salt used to hash api keys
+
+# API level encryption for sensitive data
+# Must be 256 bits, 64 string characters in hex format, generate via: openssl rand -hex 32
+ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000"
 
 # Use CSP headers to enforce HTTPS, optional
-LANGFUSE_CSP_ENFORCE_HTTPS="true"
+# LANGFUSE_CSP_ENFORCE_HTTPS="true"
+
+# Configure base path for self-hosting, optional
+# Note: You need to build the docker image with the base path set and cannot use the pre-built docker image if you set this.
+# NEXT_PUBLIC_BASE_PATH="/app"
 
 # Docker only, optional
 # PORT=3000
 # HOSTNAME=localhost
 
-# Default project, optional
+# Opentelemetry, optional
+OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4318"
+OTEL_SERVICE_NAME="langfuse"
+
+# Default role for users who sign up, optional, can be org or org+project
+# LANGFUSE_DEFAULT_ORG_ID=
+# LANGFUSE_DEFAULT_ORG_ROLE=
 # LANGFUSE_DEFAULT_PROJECT_ID=
 # LANGFUSE_DEFAULT_PROJECT_ROLE=
 
+# Logging, optional
+# LANGFUSE_LOG_LEVEL=info
+# LANGFUSE_LOG_FORMAT=text
+
 # Enable experimental features, optional
 # LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES=true
 
@@ -38,14 +57,20 @@ LANGFUSE_CSP_ENFORCE_HTTPS="true"
 # AUTH_DOMAINS_WITH_SSO_ENFORCEMENT=domain1.com,domain2.com
 # AUTH_DISABLE_USERNAME_PASSWORD=true
 # AUTH_DISABLE_SIGNUP=true
+# AUTH_SESSION_MAX_AGE=43200 # 30 days in minutes (default)
 
 # SSO, each group is optional
 # AUTH_GOOGLE_CLIENT_ID=
 # AUTH_GOOGLE_CLIENT_SECRET=
 # AUTH_GOOGLE_ALLOW_ACCOUNT_LINKING=false
+# AUTH_GOOGLE_ALLOWED_DOMAINS=langfuse.com,google.com # optional allowlist of workspace domains that can sign in via Google
 # AUTH_GITHUB_CLIENT_ID=
 # AUTH_GITHUB_CLIENT_SECRET=
 # AUTH_GITHUB_ALLOW_ACCOUNT_LINKING=false
+# AUTH_GITLAB_CLIENT_ID=
+# AUTH_GITLAB_CLIENT_SECRET=
+# AUTH_GITLAB_ALLOW_ACCOUNT_LINKING=false
+# AUTH_GITLAB_ISSUER=
 # AUTH_AZURE_AD_CLIENT_ID=
 # AUTH_AZURE_AD_CLIENT_SECRET=
 # AUTH_AZURE_AD_TENANT_ID=
@@ -62,7 +87,12 @@ LANGFUSE_CSP_ENFORCE_HTTPS="true"
 # AUTH_COGNITO_CLIENT_SECRET=
 # AUTH_COGNITO_ISSUER=
 # AUTH_COGNITO_ALLOW_ACCOUNT_LINKING=false
-
+# AUTH_CUSTOM_CLIENT_ID=
+# AUTH_CUSTOM_CLIENT_SECRET=
+# AUTH_CUSTOM_ISSUER=
+# AUTH_CUSTOM_NAME=
+# AUTH_CUSTOM_SCOPE="openid email profile" # optional
+# AUTH_CUSTOM_ALLOW_ACCOUNT_LINKING=false
 
 # Transactional email, optional
 # Defines the email address to use as the from address.
@@ -76,13 +106,55 @@ LANGFUSE_CSP_ENFORCE_HTTPS="true"
 # S3_SECRET_ACCESS_KEY=
 # S3_BUCKET_NAME=
 # S3_REGION=
+# BATCH_EXPORT_DOWNLOAD_LINK_EXPIRATION_HOURS=
+
+# S3 storage for events, optional, used to persist all incoming events
+# LANGFUSE_S3_EVENT_UPLOAD_ENABLED="true"
+# LANGFUSE_S3_EVENT_UPLOAD_BUCKET=
+# Optional prefix to be used within the bucket. Must end with `/` if set
+# LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
+# The following four options are optional and fallback to the normal SDK credential provider chain if omitted
+# See https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/setting-credentials-node.html
+# LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT=
+# LANGFUSE_S3_EVENT_UPLOAD_REGION=
+# LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID=
+# LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY=
 
 # Exports are streamed to S3 in pages to avoid memory issues
 # The page size can be adjusted if needed to optimize performance
 # DB_EXPORT_PAGE_SIZE=1000
 
-# Disable logging to `events` table in db
-# ENABLE_EVENT_LOG=false
+# Automated provisioning of default resources
+# LANGFUSE_INIT_ORG_ID=org-id
+# LANGFUSE_INIT_ORG_NAME=org-name
+# LANGFUSE_INIT_PROJECT_ID=project-id
+# LANGFUSE_INIT_PROJECT_NAME=project-name
+# LANGFUSE_INIT_PROJECT_PUBLIC_KEY=pk-1234567890
+# LANGFUSE_INIT_PROJECT_SECRET_KEY=sk-1234567890
+# LANGFUSE_INIT_USER_EMAIL=user@example.com
+# LANGFUSE_INIT_USER_NAME=User Name
+# LANGFUSE_INIT_USER_PASSWORD=password
+
+
+
+### START Enterprise Edition Configuration
+
+# Allowlisted users that can create new organizations, by default all users can create organizations
+# LANGFUSE_ALLOWED_ORGANIZATION_CREATORS=user1@langfuse.com,user2@langfuse.com
+
+# UI Customization Options
+# LANGFUSE_UI_API_HOST=https://api.example.com
+# LANGFUSE_UI_DOCUMENTATION_HREF=https://docs.example.com
+# LANGFUSE_UI_SUPPORT_HREF=https://support.example.com
+# LANGFUSE_UI_FEEDBACK_HREF=https://feedback.example.com
+# LANGFUSE_UI_LOGO_LIGHT_MODE_HREF=https://static.langfuse.com/langfuse-dev/example-logo-light-mode.png
+# LANGFUSE_UI_LOGO_DARK_MODE_HREF=https://static.langfuse.com/langfuse-dev/example-logo-dark-mode.png
+# LANGFUSE_UI_DEFAULT_MODEL_ADAPTER=Anthropic # OpenAI, Anthropic, Azure
+# LANGFUSE_UI_DEFAULT_BASE_URL_OPENAI=https://api.openai.com/v1
+# LANGFUSE_UI_DEFAULT_BASE_URL_ANTHROPIC=https://api.anthropic.com
+# LANGFUSE_UI_DEFAULT_BASE_URL_AZURE_OPENAI=https://{instanceName}.openai.azure.com/openai/deployments
+
+### END Enterprise Edition Configuration
 
 
 
@@ -91,9 +163,6 @@ LANGFUSE_CSP_ENFORCE_HTTPS="true"
 # Disable the expensive analytics queries and related features
 # LANGFUSE_DISABLE_EXPENSIVE_POSTGRES_QUERIES="true"
 
-# Customize the default datetime offset filter used in for the UI tables
-# LANGFUSE_DEFAULT_TABLE_DATETIME_OFFSET="7" # int (days)
-
 ### END Envs to be deprecated in Langfuse v3.0
 
 
@@ -114,32 +183,66 @@ LANGFUSE_CSP_ENFORCE_HTTPS="true"
 # NEXT_PUBLIC_POSTHOG_KEY=
 
 # Sentry
+# NEXT_PUBLIC_LANGFUSE_TRACING_SAMPLE_RATE
 # NEXT_PUBLIC_SENTRY_DSN=
 # NEXT_SENTRY_ORG=
 # NEXT_SENTRY_PROJECT=
 # SENTRY_AUTH_TOKEN=
+# SENTRY_CSP_REPORT_URI=
+
 
 # Cloudflare Turnstile
 # NEXT_PUBLIC_TURNSTILE_SITE_KEY=
 # TURNSTILE_SECRET_KEY=
 
-# Prompt playground
-# OPENAI_API_KEY=""
-# ANTHROPIC_API_KEY=""
-
-# Betterstack
-# LANGFUSE_TEAM_BETTERSTACK_TOKEN=
-
 # Demo project that users can use to try the platform
+# NEXT_PUBLIC_DEMO_ORG_ID=
 # NEXT_PUBLIC_DEMO_PROJECT_ID=
 
 # Crisp chat
 # NEXT_PUBLIC_CRISP_WEBSITE_ID=
 
-# Encryption
-# ENCRYPTION_KEY=
-
 # Admin API
 # ADMIN_API_KEY=
 
+# Redis
+# REDIS_HOST=
+# REDIS_PORT=
+# REDIS_AUTH=
+# REDIS_CONNECTION_STRING=
+# REDIS_ENABLE_AUTO_PIPELINING=
+
+# Cache configuration
+# LANGFUSE_CACHE_API_KEY_ENABLED=
+# LANGFUSE_CACHE_API_KEY_TTL_SECONDS=
+# LANGFUSE_CACHE_PROMPT_ENABLED=
+# LANGFUSE_CACHE_PROMPT_TTL_SECONDS=
+
+# Rate limiting
+# LANGFUSE_RATE_LIMITS_ENABLED=
+
+# Stripe
+# STRIPE_SECRET_KEY=
+# STRIPE_WEBHOOK_SIGNING_SECRET=
+
 ### END Langfuse Cloud Config
+
+
+## START Langfuse V3 Ingestion 
+
+# Clickhouse
+# CLICKHOUSE_MIGRATION_URL=
+# CLICKHOUSE_URL=
+# CLICKHOUSE_USER=
+# CLICKHOUSE_PASSWORD=
+
+# Ingestion
+# LANGFUSE_INGESTION_QUEUE_DELAY_MS=
+# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_BATCH_SIZE=
+# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS= 
+# LANGFUSE_INGESTION_CLICKHOUSE_MAX_ATTEMPTS=
+# LANGFUSE_LEGACY_INGESTION_WORKER_CONCURRENCY=
+# LANGFUSE_ASYNC_INGESTION_PROCESSING="true"
+# QUEUE_CONSUMER_LEGACY_INGESTION_QUEUE_IS_ENABLED="true"
+
+## END Langfuse V3 Ingestion

.github/dependabot.yml

@@ -8,6 +8,7 @@ updates:
   - package-ecosystem: npm
     directory: "/" # Location of package manifests
     rebase-strategy: "disabled" # use dependabot-rebase-stale
+    open-pull-requests-limit: 10
     schedule:
       interval: "daily"
     versioning-strategy: "increase"
@@ -19,17 +20,29 @@ updates:
       - dependency-name: "@types/node"
       - dependency-name: "@trpc/*"
     groups:
-      sentry:
-        patterns:
-          - "@sentry/*"
       prisma:
         patterns:
           - "prisma"
-          - "@prisma/*"
+          - "@prisma/client"
       next:
         patterns:
           - "eslint-config-next"
           - "next"
-      patches:
-        update-types:
-          - "patch"
+      lodash:
+        patterns:
+          - "lodash"
+          - "@types/lodash"
+      express:
+        patterns:
+          - "express"
+          - "@types/express"
+      observability:
+        patterns:
+          - "dd-trace"
+          - "@opentelemetry/*"
+          - "@appsignal/opentelemetry-instrumentation-bullmq"
+          - "@prisma/instrumentation"
+          - "@sentry/*"
+      radix-ui:
+        patterns:
+          - "@radix-ui/*"

.github/workflows/_deploy_ecs_service.yml

@@ -0,0 +1,75 @@
+name: WorkflowCall - Deploy to ECS Service
+on:
+  workflow_call:
+    inputs:
+      environment:
+        type: string
+        description: Deployment environment
+        required: true
+      service:
+        type: string
+        description: Name of the service to be deployed, e.g. web-ingestion, web, or worker.
+        required: true
+jobs:
+  ecs-deploy:
+    runs-on: ubuntu-latest
+    environment: ${{ inputs.environment }}
+    steps:
+      - name: Get app name
+        uses: winterjung/split@v2
+        id: split
+        with:
+          msg: ${{ inputs.service }}
+          separator: "-"
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Authenticate with AWS
+        # GitHub/AWS recommend to use OIDC here: https://github.com/aws-actions/configure-aws-credentials?tab=readme-ov-file#oidc
+        # Probably more painful to configure, but would remove all long-lived credentials.
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ vars.AWS_REGION }}
+      - name: Login to AWS ECR
+        id: login-ecr
+        uses: aws-actions/amazon-ecr-login@v2
+      - name: Build, tag, and push Docker image
+        env:
+          REGISTRY: ${{ steps.login-ecr.outputs.registry }}
+          REPOSITORY: ${{ steps.split.outputs._0 }}
+          IMAGE_TAG: ${{ github.sha }}
+        run: |
+          docker build \
+            -t $REGISTRY/$REPOSITORY:$IMAGE_TAG \
+            -f ./${{ steps.split.outputs._0 }}/Dockerfile \
+            --build-arg NEXT_PUBLIC_LANGFUSE_CLOUD_REGION=${{ vars.NEXT_PUBLIC_LANGFUSE_CLOUD_REGION }} \
+            --build-arg NEXT_LANGFUSE_TRACING_SAMPLE_RATE=${{ vars.NEXT_LANGFUSE_TRACING_SAMPLE_RATE }} \
+            --build-arg NEXT_PUBLIC_SENTRY_ENVIRONMENT=${{ vars.NEXT_PUBLIC_SENTRY_ENVIRONMENT }} \
+            --build-arg NEXT_PUBLIC_DEMO_ORG_ID=${{ vars.NEXT_PUBLIC_DEMO_ORG_ID }} \
+            --build-arg NEXT_PUBLIC_DEMO_PROJECT_ID=${{ vars.NEXT_PUBLIC_DEMO_PROJECT_ID }} \
+            --build-arg NEXT_PUBLIC_SENTRY_DSN=${{ vars.NEXT_PUBLIC_SENTRY_DSN }} \
+            --build-arg NEXT_PUBLIC_BUILD_ID=${{ github.sha }} \
+            --build-arg NEXT_PUBLIC_POSTHOG_KEY=${{ vars.NEXT_PUBLIC_POSTHOG_KEY }} \
+            --build-arg NEXT_PUBLIC_POSTHOG_HOST=${{ vars.NEXT_PUBLIC_POSTHOG_HOST }} \
+            --build-arg NEXT_PUBLIC_CRISP_WEBSITE_ID=${{ vars.NEXT_PUBLIC_CRISP_WEBSITE_ID }} \
+            --build-arg SENTRY_AUTH_TOKEN=${{ secrets.SENTRY_AUTH_TOKEN }} \
+            --build-arg SENTRY_ORG=${{ vars.SENTRY_ORG }} \
+            --build-arg SENTRY_PROJECT=${{ vars.SENTRY_PROJECT }} \
+            .
+          docker push $REGISTRY/$REPOSITORY:$IMAGE_TAG
+
+      - name: Render AWS ECS Task Definition
+        id: render-task-definition
+        uses: aws-actions/amazon-ecs-render-task-definition@v1
+        with:
+          container-name: ${{ inputs.service }}
+          image: ${{ steps.login-ecr.outputs.registry }}/${{ steps.split.outputs._0 }}:${{ github.sha }}
+          task-definition-family: ${{ inputs.environment }}-${{ inputs.service }}
+      - name: Update AWS ECS Service
+        uses: aws-actions/amazon-ecs-deploy-task-definition@v2
+        with:
+          task-definition: ${{ steps.render-task-definition.outputs.task-definition }}
+          service: ${{ inputs.environment }}-${{ inputs.service }}
+          cluster: ${{ inputs.environment }}-cluster
+          wait-for-service-stability: true

.github/workflows/ci.yml.template

@@ -22,7 +22,7 @@ jobs:
 
     steps:
       - name: Checkout repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Start containers
         run: docker compose -f "docker-compose.yml" up -d --build
@@ -31,7 +31,7 @@ jobs:
         uses: pnpm/action-setup@v2.2.4
 
       - name: Setup Node 18
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18
 

.github/workflows/codeql.yml

@@ -0,0 +1,92 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: ["main", "production", "v*"]
+  pull_request:
+    branches: ["main", "production", "v*"]
+  schedule:
+    - cron: "31 13 * * 0"
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - language: javascript-typescript
+            build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v3
+        with:
+          languages: ${{ matrix.language }}
+          build-mode: ${{ matrix.build-mode }}
+          # If you wish to specify custom queries, you can do so here or in a config file.
+          # By default, queries listed here will override any specified in a config file.
+          # Prefix the list here with "+" to use these queries and those in the config file.
+
+          # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+          # queries: security-extended,security-and-quality
+
+      # If the analyze step fails for one of the languages you are analyzing with
+      # "We were unable to automatically build your code", modify the matrix above
+      # to set the build mode to "manual" for that language. Then modify this step
+      # to build your code.
+      # ℹ️ Command-line programs to run using the OS shell.
+      # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+      - if: matrix.build-mode == 'manual'
+        shell: bash
+        run: |
+          echo 'If you are using a "manual" build mode for one or more of the' \
+            'languages you are analyzing, replace this with the commands to build' \
+            'your code, for example:'
+          echo '  make bootstrap'
+          echo '  make release'
+          exit 1
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v3
+        with:
+          category: "/language:${{matrix.language}}"

.github/workflows/deploy.yml

@@ -0,0 +1,105 @@
+on:
+  push:
+    branches:
+      - main
+      - production
+  workflow_dispatch:
+    inputs:
+      service:
+        description: 'Service to be deployed'
+        type: choice
+        options:
+          - all
+          - web
+          - web-ingestion
+          - worker
+        required: true
+      environment:
+        description: 'Environment to deploy to'
+        type: choice
+        options:
+          - staging
+          - prod-eu
+          - prod-us
+        required: true
+
+concurrency:
+  # Support concurrent `push` and `workflow_dispatch`` actions
+  group: deploy-${{ github.event_name }}-${{ github.ref }}
+  cancel-in-progress: true
+
+name: Deploy to ECS
+jobs:
+  affected-services:
+    runs-on: ubuntu-latest
+    outputs:
+      services: ${{ steps.affected-services.outputs.result }}
+    steps:
+      - name: Get affected services
+        id: affected-services
+        uses: actions/github-script@v7
+        with:
+          script: |
+            if (context.eventName === "workflow_dispatch") {
+              if (context.payload.inputs.service === "all") {
+                return `["web", "web-ingestion", "worker"]`
+              }
+              return `["${context.payload.inputs.service}"]`
+            }
+            if (context.eventName === "push") {
+              return `["web", "web-ingestion", "worker"]`
+            }
+            return "[]"
+          result-encoding: string
+      - name: Print services to build
+        uses: actions/github-script@v7
+        env:
+          services: ${{ steps.affected-services.outputs.result }}
+        with:
+          result-encoding: string
+          script: |
+            console.log('Services', `${process.env.services}` ?? 'n/a');
+
+  affected-environments:
+    runs-on: ubuntu-latest
+    outputs:
+      environments: ${{ steps.affected-environments.outputs.result }}
+    steps:
+      - name: Get affected environments
+        id: affected-environments
+        uses: actions/github-script@v7
+        with:
+          script: |
+            if (context.eventName === "workflow_dispatch") {
+              return `["${context.payload.inputs.environment}"]`
+            }
+            if (context.eventName === "push") {
+              if (context.ref === "refs/heads/main") {
+                return `["staging"]`
+              }
+              if (context.ref === "refs/heads/production") {
+                return `["prod-eu", "prod-us"]`
+              }
+            }
+            return "[]"
+          result-encoding: string
+      - name: Print environments to build
+        uses: actions/github-script@v7
+        env:
+          environments: ${{ steps.affected-environments.outputs.result }}
+        with:
+          result-encoding: string
+          script: |
+            console.log('Environments', `${process.env.environments}` ?? 'n/a');
+
+  ecs-deploy:
+    uses: ./.github/workflows/_deploy_ecs_service.yml
+    needs: [affected-services, affected-environments]
+    secrets: inherit
+    strategy:
+      matrix:
+        service: ${{ fromJson(needs.affected-services.outputs.services) }}
+        environment: ${{ fromJson(needs.affected-environments.outputs.environments) }}
+    with:
+      service: ${{ matrix.service }}
+      environment: ${{ matrix.environment }}

.github/workflows/licencecheck.yml

@@ -14,10 +14,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Setup node
-        uses: actions/setup-node@v2
+        uses: actions/setup-node@v4
         with:
           node-version: 18
 

.github/workflows/pipeline.yml

@@ -16,11 +16,11 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
-          version: 8.15.5
-      - uses: actions/setup-node@v3
+          version: 9.5.0
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: "pnpm"
@@ -35,24 +35,22 @@ jobs:
         run: pnpm run lint
 
   test-docker-build:
+    timeout-minutes: 20
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
-
+        uses: actions/checkout@v4
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
+      - name: Set NEXT_PUBLIC_BUILD_ID
+        run: echo "NEXT_PUBLIC_BUILD_ID=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
       - name: Build and run both images from compose
         run: |
           docker compose -f docker-compose.build.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
-
-      - name: Check server health
-        run: |
-          timeout 10 bash -c 'until curl -f http://localhost:3000/api/public/health; do sleep 2; done'
-
-      - name: Check worker health
-        run: |
-          timeout 10 bash -c 'until curl -f http://localhost:3030/api/health; do sleep 2; done'
-
       - name: Ensure no unhealthy status
         run: |
           if docker-compose ps | grep "(unhealthy)"; then
@@ -61,149 +59,239 @@ jobs:
           else
             echo "All services are healthy"
           fi
+      - name: Check worker health
+        run: |
+          timeout 10 bash -c 'until curl -f http://localhost:3030/api/health; do sleep 2; done'
+      - name: Check server health
+        run: |
+          timeout 10 bash -c 'until curl -f http://localhost:3000/api/public/health; do sleep 2; done'
 
   tests-web:
+    timeout-minutes: 20
     runs-on: ubuntu-latest
+    name: tests-web (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }})
     strategy:
       matrix:
         node-version: [20]
+        postgres-version: [12, 15]
     steps:
       - name: Set Swap Space
         uses: pierotofy/set-swap-space@master
         with:
           swap-size-gb: 10
-
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+      - name: Install golang-migrate for Clickhouse migrations
+        run: |
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.16.2/migrate.linux-amd64.tar.gz | tar xvz
+          sudo mv migrate /usr/bin/migrate
+          which migrate
       - uses: pnpm/action-setup@v3
         with:
-          version: 8.15.5
+          version: 9.5.0
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
       - name: Use Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node-version }}
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: install dependencies
         run: |
           pnpm install
-
       - name: Load default env
         run: |
           cp .env.dev.example .env
-          cp .env.dev.example web/.env
-
+          grep -v -e '^S3_BUCKET_NAME=' -e '^REDIS_HOST=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev.example > .env
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
-
+          docker compose ps
+        env:
+          POSTGRES_VERSION: ${{ matrix.postgres-version }}
       - name: Seed DB
         run: |
           pnpm run db:migrate
-          pnpm run db:seed
-
+          pnpm --filter=shared ch:up
       - name: Build
         run: pnpm run build
-
       - name: Start Langfuse
         run: (pnpm run start&)
-
+        env:
+          LANGFUSE_INIT_ORG_ID: "seed-org-id"
+          LANGFUSE_INIT_ORG_NAME: "Seed Org"
+          LANGFUSE_INIT_PROJECT_ID: "7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"
+          LANGFUSE_INIT_PROJECT_NAME: "Seed Project"
+          LANGFUSE_INIT_PROJECT_PUBLIC_KEY: "pk-lf-1234567890"
+          LANGFUSE_INIT_PROJECT_SECRET_KEY: "sk-lf-1234567890"
+          LANGFUSE_INIT_USER_EMAIL: "demo@langfuse.com"
+          LANGFUSE_INIT_USER_NAME: "Demo User"
+          LANGFUSE_INIT_USER_PASSWORD: "password"
       - name: run tests
         run: pnpm --filter=web run test
 
   tests-worker:
+    timeout-minutes: 20
     runs-on: ubuntu-latest
+    name: tests-worker (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }})
     strategy:
       matrix:
         node-version: [20]
+        postgres-version: [12, 15]
     steps:
       - name: Set Swap Space
         uses: pierotofy/set-swap-space@master
         with:
           swap-size-gb: 10
-
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
-          version: 8.15.5
+          version: 9.5.0
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
       - name: Use Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node-version }}
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: install dependencies
         run: |
           pnpm install
-
+      - name: Install golang-migrate for Clickhouse migrations
+        run: |
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.16.2/migrate.linux-amd64.tar.gz | tar xvz
+          sudo mv migrate /usr/bin/migrate
+          which migrate
       - name: Load default env
         run: |
           cp .env.dev.example .env
           cp .env.dev.example web/.env
-
+          cp .env.dev.example worker/.env
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
           sleep 5 # Wait for PostgreSQL to accept connections
-
+          docker compose ps
+      - name: Ensure no unhealthy status
+        run: |
+          if docker compose ps | grep "(unhealthy)"; then
+            echo "One or more services are unhealthy"
+            exit 1
+          else
+            echo "All services are healthy"
+          fi
       - name: Seed DB
         run: |
           pnpm run db:migrate
           pnpm run db:seed
-
+          pnpm run --filter=shared ch:up
       - name: Build
         run: pnpm --filter=worker... run build
-
       - name: run tests
         run: pnpm --filter=worker run test
 
   e2e-tests:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: pnpm/action-setup@v3
         with:
-          version: 8.15.5
-      - uses: actions/setup-node@v3
+          version: 9.5.0
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
       - name: install dependencies
         run: |
           pnpm install
-
       - name: Load default env
         run: |
           cp .env.dev.example .env
           cp .env.dev.example web/.env
-
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
+          docker compose ps
           sleep 5 # Wait for PostgreSQL to accept connections
-
       - name: Seed DB
         run: |
           pnpm run db:migrate
           pnpm run db:seed
-
       - name: Build
         run: pnpm run build
-
       - name: Install playwright
         run: pnpm --filter=web exec playwright install --with-deps
-
       - name: Run e2e tests
         run: pnpm --filter=web run test:e2e
 
+  e2e-server-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME_READ }}
+          password: ${{ secrets.DOCKERHUB_TOKEN_READ }}
+      - uses: pnpm/action-setup@v3
+        with:
+          version: 9.5.0
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: "pnpm"
+          cache-dependency-path: "pnpm-lock.yaml"
+      - name: install dependencies
+        run: |
+          pnpm install
+      - name: Load default env
+        run: |
+          cp .env.dev.example .env
+          echo "LANGFUSE_ASYNC_INGESTION_PROCESSING=true" >> .env
+          echo "LANGFUSE_CACHE_API_KEY_ENABLED=true" >> .env
+          echo "LANGFUSE_CACHE_PROMPT_ENABLED=true" >> .env
+      - name: Run + migrate
+        run: |
+          docker compose -f docker-compose.dev.yml up -d
+          docker compose ps
+          sleep 5 # Wait for PostgreSQL to accept connections
+      - name: Seed DB
+        run: |
+          pnpm run db:migrate
+          pnpm run db:seed:examples
+      - name: Build
+        run: pnpm run build
+      - name: Run server
+        run: (pnpm run start&)
+      - name: Run e2e tests
+        run: pnpm --filter=web run test:e2e:server
+
   all-ci-passed:
     # This allows us to have a branch protection rule for tests and deploys with matrix
     runs-on: ubuntu-latest
-    needs: [lint, tests-web, tests-worker, e2e-tests, test-docker-build]
+    needs:
+      [
+        lint,
+        tests-web,
+        tests-worker,
+        e2e-tests,
+        test-docker-build,
+        e2e-server-tests,
+      ]
     if: always()
     steps:
       - name: Successful deploy
@@ -227,29 +315,33 @@ jobs:
     steps:
       - uses: pnpm/action-setup@v3
         with:
-          version: 8.15.5
+          version: 9.5.0
       - name: Setup node
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 20
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: Checkout
-        uses: actions/checkout@v3
-
+        uses: actions/checkout@v4
+      - name: Set NEXT_PUBLIC_BUILD_ID
+        run: echo "NEXT_PUBLIC_BUILD_ID=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
       - name: Log in to the GitHub Container registry
         uses: docker/login-action@v2
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Log in to Docker Hub
         uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
-
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: network=host
       - name: Extract metadata (tags, labels) for Docker
         id: meta-web
         uses: docker/metadata-action@v4
@@ -264,7 +356,6 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
-
       - name: Build and push Docker image (web)
         uses: docker/build-push-action@v4
         with:
@@ -273,7 +364,9 @@ jobs:
           push: true
           tags: ${{ steps.meta-web.outputs.tags }}
           labels: ${{ steps.meta-web.outputs.labels }}
-
+          platforms: |
+            linux/amd64
+            ${{ startsWith(github.ref, 'refs/tags/') && 'linux/arm64' || '' }}
       - name: Extract metadata (tags, labels) for Docker
         id: meta-worker
         uses: docker/metadata-action@v4
@@ -288,7 +381,6 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
-
       - name: Build and push Docker image (worker)
         uses: docker/build-push-action@v4
         with:
@@ -297,3 +389,6 @@ jobs:
           push: true
           tags: ${{ steps.meta-worker.outputs.tags }}
           labels: ${{ steps.meta-worker.outputs.labels }}
+          platforms: |
+            linux/amd64
+            ${{ startsWith(github.ref, 'refs/tags/') && 'linux/arm64' || '' }}

.github/workflows/porter_stack_worker.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-    - main
-name: Deploy to worker
-jobs:
-  porter-deploy:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v3
-    - name: Set Github tag
-      id: vars
-      run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
-    - name: Setup porter
-      uses: porter-dev/setup-porter@v0.1.0
-    - name: Deploy stack
-      timeout-minutes: 30
-      run: exec porter apply
-      env:
-        PORTER_CLUSTER: "3959"
-        PORTER_DEPLOYMENT_TARGET_ID: d2bb23e4-1d77-48f2-a113-383d076959b3
-        PORTER_HOST: https://dashboard.getporter.dev
-        PORTER_PR_NUMBER: ${{ github.event.number }}
-        PORTER_PROJECT: "12565"
-        PORTER_REPO_NAME: ${{ github.event.repository.name }}
-        PORTER_STACK_NAME: worker
-        PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-        PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_3959 }}

.github/workflows/snyk.yml

@@ -0,0 +1,46 @@
+name: Snyk Container
+on:
+  pull_request:
+    branches:
+      - "**"
+  push:
+    branches:
+      - main
+
+jobs:
+  snyk:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Build a Docker image
+        run: docker compose -f docker-compose.build.yml up -d
+
+      - name: Run Snyk to check Docker image for vulnerabilities (langfuse-server)
+        continue-on-error: true
+        uses: snyk/actions/docker@master
+        env:
+          SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
+        with:
+          image: langfuse-server
+          args: --file=web/Dockerfile
+
+      - name: Upload result to GitHub Code Scanning
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: snyk.sarif
+          category: web
+
+      - name: Run Snyk to check Docker image for vulnerabilities (langfuse-worker)
+        continue-on-error: true
+        uses: snyk/actions/docker@master
+        env:
+          SNYK_TOKEN: ${{ secrets.SNYK_TOKEN }}
+        with:
+          image: langfuse-worker
+          args: --file=worker/Dockerfile
+
+      - name: Upload result to GitHub Code Scanning
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: snyk.sarif
+          category: worker

.gitignore

@@ -35,9 +35,10 @@ yarn-error.log*
 
 # local env files
 # do not commit any .env files to git, except for the .env.example file. https://create.t3.gg/en/usage/env-variables#using-environment-variables
-.env
-.env.local
-.env*.local
+.env*
+!.env.dev.example
+!.env.local.example
+!.env.prod.example
 
 # vercel
 .vercel

.husky/pre-commit

@@ -0,0 +1,22 @@
+#!/bin/sh
+
+# Get the current branch
+current_branch=$(git rev-parse --abbrev-ref HEAD)
+
+# Define the protected branch
+protected_branch="main"
+
+# Check if the current branch is the protected branch
+if [ "$current_branch" = "$protected_branch" ]; then
+    echo "🚨 You are about to commit to the $protected_branch branch. Are you sure? (y/n)"
+    read -r answer < /dev/tty
+    if [ "$answer" != "${answer#[Yy]}" ]; then
+        exit 0 # Commit will proceed
+    else
+        echo "Commit to $protected_branch branch has been canceled."
+        exit 1 # Commit will be blocked
+    fi
+fi
+
+# If not the protected branch, proceed with the commit
+exit 0

.husky/pre-push

@@ -0,0 +1,22 @@
+#!/bin/sh
+
+# Get the current branch
+current_branch=$(git rev-parse --abbrev-ref HEAD)
+
+# Define the protected branch
+protected_branch="main"
+
+# Check if the current branch is the protected branch
+if [ "$current_branch" = "$protected_branch" ]; then
+    echo "🚨 You are about to push to the $protected_branch branch. Are you sure? (y/n)"
+    read -r answer < /dev/tty
+    if [ "$answer" != "${answer#[Yy]}" ]; then
+        exit 0 # Push will proceed
+    else
+        echo "Push to $protected_branch branch has been canceled."
+        exit 1 # Push will be blocked
+    fi
+fi
+
+# If not the protected branch, proceed with the push
+exit 0

.vscode/launch.json

@@ -2,10 +2,10 @@
   "version": "0.2.0",
   "configurations": [
     {
-      "name": "Next.js: debug server-side",
+      "name": "Web and Worker: server side",
       "type": "node-terminal",
       "request": "launch",
-      "command": "npm run dev"
+      "command": "pnpm run dev"
     },
     {
       "name": "Next.js: debug client-side",

.vscode/settings.json

@@ -20,6 +20,7 @@
   "prettier.documentSelectors": [
     "**/*.{cjs,mjs,ts,tsx,astro,md,mdx,json,yaml,yml}"
   ],
+  "prettier.trailingComma": "all",
   "mdx.experimentalLanguageServer": true,
   "typescript.preferences.importModuleSpecifier": "non-relative",
   "docwriter.style": "JSDoc",

CONTRIBUTING.md

@@ -53,9 +53,7 @@ A good first step is to search for open [issues](https://github.com/langfuse/lan
 
 ### Architecture Overview
 
-> [!NOTE]
-> Infrastructure will change in Langfuse version 3.0. More in the [GitHub Discussions](https://github.com/orgs/langfuse/discussions/1902).
-> `langfuse/langfuse/worker` is under active development and not recommended for production use in Langfuse 2.x
+**Langfuse v2**
 
 ```mermaid
 flowchart TB
@@ -93,15 +91,66 @@ flowchart TB
         I --- Prisma
     end
 
-    subgraph s5["Application (langfuse/langfuse/worker)"]
-        Worker_API[Public HTTP API]
+    Prisma --- DB
+    JS --- API
+    Python --- API
+```
+
+**Langfuse v3 (work in progress, not released yet)**
+
+> [!NOTE]
+> Infrastructure will change in Langfuse version 3.0. More in the [GitHub Discussions](https://github.com/orgs/langfuse/discussions/1902).
+> `langfuse/langfuse/worker` is under active development and not recommended for production use in Langfuse 2.x.
+
+```mermaid
+flowchart TB
+    subgraph s4["Clients"]
+        subgraph s2["langfuse/langfuse-python"]
+            Python["Python low-level SDK"]
+            Decorator["observe() decorator"] -->|extends| Python
+            OAI["OpenAI drop-in replacement"] -->|extends| Python
+            Llamaindex["LlamaIndex Integration"] -->|extends| Python
+            LCPYTHON["Langchain Python Integration"] -->|extends| Python
+            Langflow -->|uses| LCPYTHON
+            LiteLLM -->|uses| Python
+        end
+        subgraph s3["langfuse/langfuse-js"]
+            JS["JS SDK"]
+            LCJS["Langchain JS Integration"]  -->|extends| JS
+            Flowise -->|uses| LCJS
+        end
     end
 
-    API --> Worker_API
-    Worker_API --- DB
-    Worker_API --- Redis
+    DB[Postgres Database]
+    Redis[Redis Cache/Queue]
+    Clickhouse[Clickhouse Database]
+
+    subgraph s1["Application (langfuse/langfuse/web)"]
+        API[Public HTTP API]
+        G[TRPC API]
+        I[NextAuth]
+        H[React Frontend]
+        ORM
+        H --> G
+        H --> I
+        G --> I
+        G --- ORM
+        API --- ORM
+        I --- ORM
+    end
+
+    subgraph s5["Application (langfuse/langfuse/worker)"]
+        Worker
+    end
+
+    Worker --- DB
+    Worker --- Redis
+    Worker --- Clickhouse
+
+    ORM --- DB
+    ORM --- Redis
+    ORM --- Clickhouse
 
-    Prisma --- DB
     JS --- API
     Python --- API
 ```
@@ -116,7 +165,7 @@ flowchart LR
    Browser ---|Web UI & TRPC API| App
    Integrations/SDKs ---|Public HTTP API| App
    subgraph i1["Application Network"]
-      App["Langfuse Application (Docker or Serverless)"]
+      App["Langfuse Application"]
    end
    subgraph i2["Database Network"]
       DB["Postgres Database"]
@@ -149,8 +198,11 @@ We built a monorepo using [pnpm](https://pnpm.io/motivation) and [turbo](https:/
 Requirements
 
 - Node.js 20 as specified in the [.nvmrc](.nvmrc)
+- Pnpm v.9.5.0
 - Docker to run the database locally
 
+**Note:** You can also simply run Langfuse in a **GitHub Codespace** via the provided devcontainer. To do this, click on the green "Code" button in the top right corner of the repository and select "Open with Codespaces".
+
 **Steps**
 
 1. Fork the repository and clone it locally
@@ -380,6 +432,20 @@ Example:
 op run --env-file="./.env" -- pnpm --filter=shared run db:deploy
 ```
 
+### Editing default models and prices
+
+You can update the default AI models and prices by adding or updating an entry in `worker/src/constants/default-model-prices.json`.
+
+Please note that
+
+- prices are in USD
+- the list is ordered by ID, so make sure to keep this order
+- the `updated_at` field must be updated with the current date in ISO 8601 format. Otherwise, the change will be ignored.
+
+### Transition period until V3 release
+
+Until the V3 release, both the JSON record must be updated **and** a migration must be created to continue supporting self-hosted users. Note that the migration must updated both the `models` as well as the `prices` table accordingly.
+
 ## License
 
 Langfuse is MIT licensed, except for `ee/` folder. See [LICENSE](LICENSE) and [docs](https://langfuse.com/docs/open-source) for more details.

README.md

@@ -1,5 +1,8 @@
 ![Langfuse GitHub Banner](https://github.com/langfuse/langfuse/assets/121163007/6035f0f3-d691-4963-b5d0-10cf506e9d42)
 
+<div align="center"><h1>Langfuse: Open Source LLM Engineering Platform</h1></div>
+<div align="center"><h4>LLM Observability, Prompt Management, LLM Evaluations,<br/>Datasets, LLM Metrics, and Prompt Playground</h4></div>
+
 <div align="center">
    <div>
       <h3>
@@ -24,18 +27,20 @@
    </div>
    <span>Langfuse uses <a href="https://github.com/orgs/langfuse/discussions"><strong>Github Discussions</strong></a>  for Support and Feature Requests.</span>
    <br/>
+   <span>We're hiring. <a href="https://langfuse.com/careers"><strong>Join us</strong></a> in Product Engineering and Developer Relations.</span>
+   <br/>
    <br/>
    <div>
       <a href="https://github.com/langfuse/langfuse/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-red.svg?style=flat-square" alt="MIT License"></a>
       <a href="https://www.ycombinator.com/companies/langfuse"><img src="https://img.shields.io/badge/Y%20Combinator-W23-orange?style=flat-square" alt="Y Combinator W23"></a>
       <a href="https://github.com/langfuse/langfuse/pkgs/container/langfuse"><img alt="Docker Image" src="https://img.shields.io/badge/docker-langfuse-blue?logo=Docker&logoColor=white&style=flat-square"></a>
-      <a href="https://www.npmjs.com/package/langfuse"><img src="https://img.shields.io/npm/v/langfuse?style=flat-square&label=npm+langfuse" alt="langfuse npm package"></a>
-      <a href="https://pypi.python.org/pypi/langfuse"><img src="https://img.shields.io/pypi/v/langfuse.svg?style=flat-square&label=pypi+langfuse" alt="langfuse Python package on PyPi"></a>
+      <a href="https://pypi.python.org/pypi/langfuse"><img src="https://img.shields.io/pypi/dm/langfuse?style=flat-square&logo=python&logoColor=white&label=pypi%20langfuse&color=blue" alt="langfuse Python package on PyPi"></a>
+      <a href="https://www.npmjs.com/package/langfuse"><img src="https://img.shields.io/npm/dm/langfuse?style=flat-square&logo=npm&logoColor=white&label=npm%20langfuse&color=blue" alt="langfuse npm package"></a>
    </div>
 </div>
 </br>
 
-## Overview
+## Langfuse Overview
 
 _Unmute video for voice-over_
 
@@ -43,18 +48,18 @@ https://github.com/langfuse/langfuse/assets/2834609/a94062e9-c782-4ee9-af59-dee6
 
 ### Develop
 
-- **Observability:** Instrument your app and start ingesting traces to Langfuse ([Quickstart](https://langfuse.com/docs/get-started), [Integrations](https://langfuse.com/docs/integrations) [Tracing](https://langfuse.com/docs/tracing))
+- **LLM Observability:** Instrument your app and start ingesting traces to Langfuse ([Quickstart](https://langfuse.com/docs/get-started), [Integrations](https://langfuse.com/docs/integrations) [Tracing](https://langfuse.com/docs/tracing))
 - **Langfuse UI:** Inspect and debug complex logs ([Demo](https://langfuse.com/docs/demo), [Tracing](https://langfuse.com/docs/tracing))
 - **Prompt Management:** Manage, version and deploy prompts from within Langfuse ([Prompt Management](https://langfuse.com/docs/prompts/get-started))
 - **Prompt Engineering:** Test and iterate on your prompts with the [LLM Playground](https://langfuse.com/docs/playground)
 
 ### Monitor
 
-- **Analytics:** Track metrics (cost, latency, quality) and gain insights from dashboards & data exports ([Analytics](https://langfuse.com/docs/analytics))
-- **Evals:** Collect and calculate scores for your LLM completions ([Scores & Evaluations](https://langfuse.com/docs/scores))
-  - Run model-based evaluations ([Model-based evaluations](https://langfuse.com/docs/scores/model-based-evals)) within Langfuse
+- **LLM Analytics:** Track metrics (cost, latency, quality) and gain insights from dashboards & data exports ([Analytics](https://langfuse.com/docs/analytics))
+- **LLM Evaluations:** Collect and calculate scores for your LLM completions ([Scores & Evaluations](https://langfuse.com/docs/scores))
+  - Run ([Model-based evaluations](https://langfuse.com/docs/scores/model-based-evals)) and LLM-as-a-Judge within Langfuse
   - Collect user feedback ([User Feedback](https://langfuse.com/docs/scores/user-feedback))
-  - Manually score observations in Langfuse ([Manual Scores](https://langfuse.com/docs/scores/manually))
+  - Manually score LLM outputs in Langfuse ([Manual Scores](https://langfuse.com/docs/scores/manually))
 
 ### Test
 
@@ -70,6 +75,8 @@ Managed deployment by the Langfuse team, generous free-tier (hobby plan), no cre
 
 **[» Langfuse Cloud](https://cloud.langfuse.com)**
 
+## Self-Hosting Open Source LLM Observability with Langfuse
+
 ### Localhost (docker)
 
 ```bash
@@ -85,10 +92,10 @@ docker compose up -d
 
 ### Self-host (docker)
 
-Langfuse is simple to self-host and keep updated. It currently requires only a single docker container.
+Langfuse is simple to self-host and keep updated. It currently requires only a single docker container and a postgres database.
 [→ Self Hosting Instructions](https://langfuse.com/docs/deployment/self-host)
 
-Templated deployments: [Railway, GCP Cloud Run, AWS Fargate, Kubernetes and others](https://langfuse.com/docs/deployment/self-host#platform-specific-information)
+Templated deployments: [Railway, GCP, AWS, Azure, Kubernetes and others](https://langfuse.com/docs/deployment/self-host#platform-specific-information)
 
 ## Get Started
 
@@ -96,50 +103,49 @@ Templated deployments: [Railway, GCP Cloud Run, AWS Fargate, Kubernetes and othe
 
 You need a Langfuse public and secret key to get started. Sign up [here](https://cloud.langfuse.com) and find them in your project settings.
 
-### Ingesting Data · Instrumenting Your Application
+### Ingesting Data · Instrumenting Your Application · LLM Observability with Langfuse
 
 Note: We recommend using our fully async, typed [SDKs](https://langfuse.com/docs/sdk) that allow you to instrument any LLM application with any underlying model. They are available in [Python (Decorators)](https://langfuse.com/docs/sdk/python) & [JS/TS](https://langfuse.com/docs/sdk/typescript). The SDKs will always be the most fully featured and stable way to ingest data into Langfuse.
 
-You may want to use another integration to get started quickly or implement a use case that we do not yet support. However, we recommend to migrate to the Langfuse SDKs over time to ensure performance and stability.
-
 See the [→ Quickstart](https://langfuse.com/docs/get-started) to integrate Langfuse.
 
-### Integrations
+### LLM Observability Integrations
 
-| Integration                                              | Supports                   | Description                                                                                                                                      |
-| -------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
-| [SDK](/docs/sdk)                                         | Python, JS/TS              | Manual instrumentation using the SDKs for full flexibility.                                                                                      |
-| [OpenAI](/docs/integrations/openai)                      | Python, JS/TS              | Automated instrumentation using drop-in replacement of OpenAI SDK.                                                                               |
-| [Langchain](/docs/integrations/langchain)                | Python, JS/TS              | Automated instrumentation by passing callback handler to Langchain application.                                                                  |
-| [LlamaIndex](/docs/integrations/llama-index/get-started) | Python                     | Automated instrumentation via LlamaIndex callback system.                                                                                        |
-| [Haystack](/docs/integrations/haystack)                  | Python                     | Automated instrumentation via Haystack content tracing system.                                                                                   |
-| [LiteLLM](/docs/integrations/litellm)                    | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |
-| [API](/docs/api)                                         |                            | Directly call the public API. OpenAPI spec available.                                                                                            |
+| Integration                                                                  | Supports                   | Description                                                                                                                                      |
+| ---------------------------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
+| [SDK](https://langfuse.com/docs/sdk)                                         | Python, JS/TS              | Manual instrumentation using the SDKs for full flexibility.                                                                                      |
+| [OpenAI](https://langfuse.com/docs/integrations/openai)                      | Python, JS/TS              | Automated instrumentation using drop-in replacement of OpenAI SDK.                                                                               |
+| [Langchain](https://langfuse.com/docs/integrations/langchain)                | Python, JS/TS              | Automated instrumentation by passing callback handler to Langchain application.                                                                  |
+| [LlamaIndex](https://langfuse.com/docs/integrations/llama-index/get-started) | Python                     | Automated instrumentation via LlamaIndex callback system.                                                                                        |
+| [Haystack](https://langfuse.com/docs/integrations/haystack)                  | Python                     | Automated instrumentation via Haystack content tracing system.                                                                                   |
+| [LiteLLM](https://langfuse.com/docs/integrations/litellm)                    | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |
+| [Vercel AI SDK](https://langfuse.com/docs/integrations/vercel-ai-sdk)        | JS/TS                      | TypeScript toolkit designed to help developers build AI-powered applications with React, Next.js, Vue, Svelte, Node.js.                          |
+| [API](https://langfuse.com/docs/api)                                         |                            | Directly call the public API. OpenAPI spec available.                                                                                            |
 
-Packages that integrate with Langfuse:
+Packages integrated with Langfuse:
 
-| Name                                                       | Description                                                                                                             |
-| ---------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
-| [Instructor](/docs/integrations/instructor)                | Library to get structured LLM outputs (JSON, Pydantic)                                                                  |
-| [Mirascope](/docs/integrations/mirascope)                  | Python toolkit for building LLM applications.                                                                           |
-| [AI SDK by Vercel](/docs/sdk/typescript/example-vercel-ai) | Typescript SDK that makes streaming LLM outputs super easy.                                                             |
-| [Flowise](/docs/integrations/flowise)                      | JS/TS no-code builder for customized LLM flows.                                                                         |
-| [Langflow](/docs/integrations/langflow)                    | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
-| [Superagent](/docs/integrations/superagent)                | Open Source AI Assistant Framework & API for prototyping and deployment of agents.                                      |
+| Name                                                            | Description                                                                                                             |
+| --------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+| [Instructor](https://langfuse.com/docs/integrations/instructor) | Library to get structured LLM outputs (JSON, Pydantic)                                                                  |
+| [Dify](https://langfuse.com/docs/integrations/dify)             | Open source LLM app development platform with no-code builder.                                                          |
+| [Ollama](https://langfuse.com/docs/integrations/ollama)         | Easily run open source LLMs on your own machine.                                                                        |
+| [Mirascope](https://langfuse.com/docs/integrations/mirascope)   | Python toolkit for building LLM applications.                                                                           |
+| [Flowise](https://langfuse.com/docs/integrations/flowise)       | JS/TS no-code builder for customized LLM flows.                                                                         |
+| [Langflow](https://langfuse.com/docs/integrations/langflow)     | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
 
 ## Questions and feedback
 
 ### Ideas and roadmap
 
-- [GitHub Discussions](https://github.com/orgs/langfuse/discussions)
-- [Feature Requests](https://langfuse.com/idea)
 - [Roadmap](https://langfuse.com/roadmap)
+- [GitHub Discussions](https://github.com/orgs/langfuse/discussions)
+- [Feature Requests](https://langfuse.com/ideas)
 
 ### Support and feedback
 
 In order of preference the best way to communicate with us:
 
-- [GitHub Discussions](https://github.com/orgs/langfuse/discussions): Contribute [ideas](https://langfuse.com/idea) [support requests](https://github.com/orgs/langfuse/discussions/categories/support) and [report bugs](https://github.com/langfuse/langfuse/issues/new?labels=%F0%9F%90%9E%E2%9D%94+unconfirmed+bug&projects=&template=bug_report.yml&title=bug%3A+) (preferred as we create a permanent, indexed artifact for other community members)
+- [GitHub Discussions](https://github.com/orgs/langfuse/discussions) (preferred): Contribute [ideas](https://langfuse.com/ideas), [support requests](https://langfuse.com/gh-support) and [report bugs](https://langfuse.com/issues)
 - [Discord](https://langfuse.com/discord): community support
 - Privately: contact at langfuse dot com
 
@@ -157,7 +163,7 @@ This repository is MIT licensed, except for the `ee` folders. See [LICENSE](LICE
 
 ### GET API to export your data
 
-[**GET routes**](https://langfuse.com/docs/integrations/api) to use data in downstream applications (e.g. embedded analytics).
+[**GET routes**](https://langfuse.com/docs/integrations/api) to use data in downstream applications (e.g. embedded analytics). You can also access them conveniently via the SDKs ([docs](https://langfuse.com/docs/query-traces)).
 
 ### Security & Privacy
 
@@ -175,3 +181,13 @@ This helps us to:
 None of the data is shared with third parties and does not include any sensitive information. We want to be super transparent about this and you can find the exact data we collect [here](/web/src/features/telemetry/index.ts).
 
 You can opt-out by setting `TELEMETRY_ENABLED=false`.
+
+### Star History
+
+<a href="https://star-history.com/#langfuse/langfuse&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=langfuse/langfuse&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=langfuse/langfuse&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=langfuse/langfuse&type=Date" />
+ </picture>
+</a>

careers

@@ -3,7 +3,6 @@ Join us in scaling Langfuse in Berlin, Germany. We are an open source company, w
 
 _Open Roles_
 
-- Backend Engineer, 70-130k EUR, 0.25-0.75% Equity, https://www.ycombinator.com/companies/langfuse/jobs/mnrdwla-backend-engineer
 - Product Engineer, 70-130k EUR, 0.25-0.75% Equity, https://www.ycombinator.com/companies/langfuse/jobs/aAvmoFB-product-engineer
 - Developer Advocate, 60-110k EUR, 0.25-0.5% Equity, https://www.ycombinator.com/companies/langfuse/jobs/uHysbKH-developer-advocate-devrel
 

docker-compose.build.yml

@@ -5,6 +5,8 @@ services:
     build:
       dockerfile: ./web/Dockerfile
       context: .
+      args:
+        - NEXT_PUBLIC_LANGFUSE_CLOUD_REGION=${NEXT_PUBLIC_LANGFUSE_CLOUD_REGION}
     depends_on:
       - db
       - redis
@@ -14,11 +16,19 @@ services:
       - DATABASE_URL=postgresql://postgres:postgres@db:5432/postgres
       - NEXTAUTH_SECRET=mysecret
       - SALT=mysalt
+      - ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000 # generate via `openssl rand -hex 32`
       - NEXTAUTH_URL=http://localhost:3000
       - TELEMETRY_ENABLED=${TELEMETRY_ENABLED:-true}
       - LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES=${LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES:-false}
-      - LANGFUSE_WORKER_HOST=${LANGFUSE_WORKER_HOST:-worker}
-      - LANGFUSE_WORKER_PASSWORD=${LANGFUSE_WORKER_PASSWORD:-mybasicauthsecret}
+      - LANGFUSE_INIT_ORG_ID=${LANGFUSE_INIT_ORG_ID:-}
+      - LANGFUSE_INIT_ORG_NAME=${LANGFUSE_INIT_ORG_NAME:-}
+      - LANGFUSE_INIT_PROJECT_ID=${LANGFUSE_INIT_PROJECT_ID:-}
+      - LANGFUSE_INIT_PROJECT_NAME=${LANGFUSE_INIT_PROJECT_NAME:-}
+      - LANGFUSE_INIT_PROJECT_PUBLIC_KEY=${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
+      - LANGFUSE_INIT_PROJECT_SECRET_KEY=${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
+      - LANGFUSE_INIT_USER_EMAIL=${LANGFUSE_INIT_USER_EMAIL:-}
+      - LANGFUSE_INIT_USER_NAME=${LANGFUSE_INIT_USER_NAME:-}
+      - LANGFUSE_INIT_USER_PASSWORD=${LANGFUSE_INIT_USER_PASSWORD:-}
     restart: always
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:3000/api/public/health"]
@@ -30,6 +40,8 @@ services:
     build:
       dockerfile: ./worker/Dockerfile
       context: .
+      args:
+        - NEXT_PUBLIC_LANGFUSE_CLOUD_REGION=${NEXT_PUBLIC_LANGFUSE_CLOUD_REGION}
     depends_on:
       - db
       - redis
@@ -44,7 +56,6 @@ services:
       - REDIS_HOST=${REDIS_HOST:-redis}
       - REDIS_PORT=${REDIS_PORT:-6379}
       - REDIS_AUTH=${REDIS_AUTH:-myredissecret}
-      - LANGFUSE_WORKER_PASSWORD=${LANGFUSE_WORKER_PASSWORD:-mybasicauthsecret}
     restart: always
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:3030/api/health"]

docker-compose.dev.yml

@@ -1,6 +1,43 @@
-version: "3.5"
-
 services:
+  clickhouse:
+    image: clickhouse/clickhouse-server
+    user: "101:101"
+    container_name: clickhouse
+    hostname: clickhouse
+    environment:
+      CLICKHOUSE_DB: default
+      CLICKHOUSE_USER: clickhouse
+      CLICKHOUSE_PASSWORD: clickhouse
+    volumes:
+      - langfuse_clickhouse_data:/var/lib/clickhouse
+      - langfuse_clickhouse_logs:/var/log/clickhouse-server
+    ports:
+      - "8123:8123"
+      - "9000:9000"
+    depends_on:
+      - postgres
+
+  minio:
+    image: minio/minio
+    container_name: minio
+    entrypoint: sh
+    # create the 'langfuse' bucket before starting the service
+    command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
+    environment:
+      MINIO_ACCESS_KEY: minio
+      MINIO_SECRET_KEY: miniosecret
+    ports:
+      - "9090:9000"
+      - "9091:9001"
+    volumes:
+      - langfuse_minio_data:/data
+    healthcheck:
+      test: ["CMD", "mc", "ready", "local"]
+      interval: 1s
+      timeout: 5s
+      retries: 5
+      start_period: 1s
+
   redis:
     image: redis:7.2.4
     restart: always
@@ -9,9 +46,14 @@ services:
     ports:
       - 6379:6379
 
-  db:
-    image: postgres
+  postgres:
+    image: postgres:${POSTGRES_VERSION:-latest}
     restart: always
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U postgres"]
+      interval: 3s
+      timeout: 3s
+      retries: 10
     command: ["postgres", "-c", "log_statement=all"]
     environment:
       - POSTGRES_USER=postgres
@@ -20,8 +62,14 @@ services:
     ports:
       - 5432:5432
     volumes:
-      - database_data:/var/lib/postgresql/data
+      - langfuse_postgres_data:/var/lib/postgresql/data
 
 volumes:
-  database_data:
+  langfuse_postgres_data:
+    driver: local
+  langfuse_clickhouse_data:
+    driver: local
+  langfuse_clickhouse_logs:
+    driver: local
+  langfuse_minio_data:
     driver: local

docker-compose.v3preview.yml

@@ -0,0 +1,135 @@
+services:
+  langfuse-worker:
+    image: langfuse/langfuse-worker:latest
+    depends_on: &langfuse-depends-on
+      postgres:
+        condition: service_healthy
+      minio:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    ports:
+      - "3030:3030"
+    environment: &langfuse-worker-env
+      DATABASE_URL: postgresql://postgres:postgres@postgres:5432/postgres
+      SALT: "mysalt"
+      ENCRYPTION_KEY: "0000000000000000000000000000000000000000000000000000000000000000" # generate via `openssl rand -hex 32`
+      TELEMETRY_ENABLED: ${TELEMETRY_ENABLED:-true}
+      LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES: ${LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES:-true}
+      LANGFUSE_ASYNC_INGESTION_PROCESSING: ${LANGFUSE_ASYNC_INGESTION_PROCESSING:-true}
+      LANGFUSE_ASYNC_CLICKHOUSE_INGESTION_PROCESSING: ${LANGFUSE_ASYNC_CLICKHOUSE_INGESTION_PROCESSING:-true}
+      LANGFUSE_READ_DASHBOARDS_FROM_CLICKHOUSE: ${LANGFUSE_READ_DASHBOARDS_FROM_CLICKHOUSE:-true}
+      LANGFUSE_READ_FROM_POSTGRES_ONLY: ${LANGFUSE_READ_FROM_POSTGRES_ONLY:-false}
+      LANGFUSE_RETURN_FROM_CLICKHOUSE: ${LANGFUSE_RETURN_FROM_CLICKHOUSE:-true}
+      CLICKHOUSE_MIGRATION_URL: ${CLICKHOUSE_MIGRATION_URL:-clickhouse://clickhouse:9000}
+      CLICKHOUSE_URL: ${CLICKHOUSE_URL:-http://clickhouse:8123}
+      CLICKHOUSE_USER: ${CLICKHOUSE_USER:-clickhouse}
+      CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-clickhouse}
+      LANGFUSE_S3_EVENT_UPLOAD_ENABLED: ${LANGFUSE_S3_EVENT_UPLOAD_ENABLED:-true}
+      LANGFUSE_S3_EVENT_UPLOAD_BUCKET: ${LANGFUSE_S3_EVENT_UPLOAD_BUCKET:-langfuse}
+      LANGFUSE_S3_EVENT_UPLOAD_REGION: ${LANGFUSE_S3_EVENT_UPLOAD_REGION:-us-east-1}
+      LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID:-minio}
+      LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY: ${LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY:-miniosecret}
+      LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT: ${LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT:-http://minio:9000}
+      LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE: ${LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE:-true}
+      REDIS_HOST: ${REDIS_HOST:-redis}
+      REDIS_PORT: ${REDIS_PORT:-6379}
+      REDIS_AUTH: ${REDIS_AUTH:-myredissecret}
+
+  langfuse-web:
+    image: langfuse/langfuse:latest
+    depends_on: *langfuse-depends-on
+    ports:
+      - "3000:3000"
+    environment:
+      <<: *langfuse-worker-env
+      NEXTAUTH_URL: http://localhost:3000
+      NEXTAUTH_SECRET: mysecret
+      LANGFUSE_INIT_ORG_ID: ${LANGFUSE_INIT_ORG_ID:-}
+      LANGFUSE_INIT_ORG_NAME: ${LANGFUSE_INIT_ORG_NAME:-}
+      LANGFUSE_INIT_PROJECT_ID: ${LANGFUSE_INIT_PROJECT_ID:-}
+      LANGFUSE_INIT_PROJECT_NAME: ${LANGFUSE_INIT_PROJECT_NAME:-}
+      LANGFUSE_INIT_PROJECT_PUBLIC_KEY: ${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
+      LANGFUSE_INIT_PROJECT_SECRET_KEY: ${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
+      LANGFUSE_INIT_USER_EMAIL: ${LANGFUSE_INIT_USER_EMAIL:-}
+      LANGFUSE_INIT_USER_NAME: ${LANGFUSE_INIT_USER_NAME:-}
+      LANGFUSE_INIT_USER_PASSWORD: ${LANGFUSE_INIT_USER_PASSWORD:-}
+
+  clickhouse:
+    image: clickhouse/clickhouse-server
+    user: "101:101"
+    container_name: clickhouse
+    hostname: clickhouse
+    environment:
+      CLICKHOUSE_DB: default
+      CLICKHOUSE_USER: clickhouse
+      CLICKHOUSE_PASSWORD: clickhouse
+    volumes:
+      - langfuse_clickhouse_data:/var/lib/clickhouse
+      - langfuse_clickhouse_logs:/var/log/clickhouse-server
+    ports:
+      - "8123:8123"
+      - "9000:9000"
+    depends_on:
+      - postgres
+
+  minio:
+    image: minio/minio
+    container_name: minio
+    entrypoint: sh
+    # create the 'langfuse' bucket before starting the service
+    command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
+    environment:
+      MINIO_ROOT_USER: minio
+      MINIO_ROOT_PASSWORD: miniosecret
+    ports:
+      - "9090:9000"
+      - "9091:9001"
+    volumes:
+      - langfuse_minio_data:/data
+    healthcheck:
+      test: ["CMD", "mc", "ready", "local"]
+      interval: 1s
+      timeout: 5s
+      retries: 5
+      start_period: 1s
+
+  redis:
+    image: redis:7
+    restart: always
+    command: >
+      --requirepass ${REDIS_AUTH:-myredissecret}
+    ports:
+      - 6379:6379
+    healthcheck:
+      test: [ 'CMD', 'redis-cli', 'ping' ]
+      interval: 3s
+      timeout: 10s
+      retries: 10
+
+  postgres:
+    image: postgres:${POSTGRES_VERSION:-latest}
+    restart: always
+    healthcheck:
+      test: [ "CMD-SHELL", "pg_isready -U postgres" ]
+      interval: 3s
+      timeout: 3s
+      retries: 10
+    environment:
+      POSTGRES_USER: postgres
+      POSTGRES_PASSWORD: postgres
+      POSTGRES_DB: postgres
+    ports:
+      - 5432:5432
+    volumes:
+      - langfuse_postgres_data:/var/lib/postgresql/data
+
+volumes:
+  langfuse_postgres_data:
+    driver: local
+  langfuse_clickhouse_data:
+    driver: local
+  langfuse_clickhouse_logs:
+    driver: local
+  langfuse_minio_data:
+    driver: local

docker-compose.yml

@@ -1,8 +1,6 @@
-version: "3.5"
-
 services:
   langfuse-server:
-    image: ghcr.io/langfuse/langfuse:latest
+    image: langfuse/langfuse:2
     depends_on:
       db:
         condition: service_healthy
@@ -12,9 +10,19 @@ services:
       - DATABASE_URL=postgresql://postgres:postgres@db:5432/postgres
       - NEXTAUTH_SECRET=mysecret
       - SALT=mysalt
+      - ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000 # generate via `openssl rand -hex 32`
       - NEXTAUTH_URL=http://localhost:3000
       - TELEMETRY_ENABLED=${TELEMETRY_ENABLED:-true}
       - LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES=${LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES:-false}
+      - LANGFUSE_INIT_ORG_ID=${LANGFUSE_INIT_ORG_ID:-}
+      - LANGFUSE_INIT_ORG_NAME=${LANGFUSE_INIT_ORG_NAME:-}
+      - LANGFUSE_INIT_PROJECT_ID=${LANGFUSE_INIT_PROJECT_ID:-}
+      - LANGFUSE_INIT_PROJECT_NAME=${LANGFUSE_INIT_PROJECT_NAME:-}
+      - LANGFUSE_INIT_PROJECT_PUBLIC_KEY=${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
+      - LANGFUSE_INIT_PROJECT_SECRET_KEY=${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
+      - LANGFUSE_INIT_USER_EMAIL=${LANGFUSE_INIT_USER_EMAIL:-}
+      - LANGFUSE_INIT_USER_NAME=${LANGFUSE_INIT_USER_NAME:-}
+      - LANGFUSE_INIT_USER_PASSWORD=${LANGFUSE_INIT_USER_PASSWORD:-}
 
   db:
     image: postgres

ee/package.json

@@ -15,32 +15,39 @@
     }
   },
   "engines": {
-    "node": ">=20"
+    "node": "20"
   },
   "scripts": {
     "build": "tsc",
     "dev": "tsc --watch",
-    "lint": "eslint . --ext .js,.jsx,.ts,.tsx",
+    "lint": "eslint . --ext .js,.jsx,.ts,.tsx --max-warnings 0",
     "lint:fix": "eslint . --ext .js,.jsx,.ts,.tsx --fix"
   },
   "dependencies": {
     "@langfuse/shared": "workspace:*",
-    "next": "^14.2.3",
+    "@opentelemetry/api": ">=1.0.0 <1.10.0",
+    "axios": "^1.7.7",
+    "next": "^14.2.15",
     "next-auth": "^4.24.7",
-    "zod": "^3.22.4"
+    "zod": "^3.23.8"
   },
   "devDependencies": {
-    "@repo/eslint-config": "*",
-    "@repo/typescript-config": "*",
+    "@repo/eslint-config": "workspace:*",
+    "@repo/typescript-config": "workspace:*",
     "@types/node": "^20.11.29",
     "@typescript-eslint/parser": "^7.12.0",
     "eslint": "^8.57.0",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",
     "eslint-plugin-prettier": "^5.1.3",
-    "prettier": "^3.2.5",
+    "prettier": "^3.3.3",
     "ts-node": "^10.9.2",
     "tsc-watch": "^6.2.0",
     "typescript": "^5.4.5"
+  },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.0"
+    }
   }
 }

ee/prettierrc.json

@@ -1,4 +0,0 @@
-{
-  "trailingComma": "es5",
-  "printWidth": 120
-}

ee/src/ee-license-check/index.ts

@@ -1,4 +1,5 @@
 import { env } from "../env";
 
 export const isEeAvailable: boolean =
-  env.NEXT_PUBLIC_LANGFUSE_CLOUD_REGION !== undefined;
+  env.NEXT_PUBLIC_LANGFUSE_CLOUD_REGION !== undefined ||
+  env.LANGFUSE_EE_LICENSE_KEY !== undefined;

ee/src/env.ts

@@ -1,9 +1,12 @@
 import { z } from "zod";
-import { env as sharedEnv } from "@langfuse/shared";
+import { env as sharedEnv, removeEmptyEnvVariables } from "@langfuse/shared";
 
 const EnvSchema = z.object({
   NEXT_PUBLIC_LANGFUSE_CLOUD_REGION: z.string().optional(),
-  ADMIN_API_KEY: z.string().optional(),
+  LANGFUSE_EE_LICENSE_KEY: z.string().optional(),
 });
 
-export const env = { ...sharedEnv, ...EnvSchema.parse(process.env) };
+export const env = {
+  ...sharedEnv,
+  ...EnvSchema.parse(removeEmptyEnvVariables(process.env)),
+};

ee/src/index.ts

@@ -1 +0,0 @@
-export { isEeAvailable } from "./ee-license-check";

fern/apis/client/definition/score.yml

@@ -9,7 +9,6 @@ service:
       method: POST
       path: /scores
       request: CreateScoreRequest
-      response: Score
 
 types:
   CreateScoreRequest:
@@ -17,15 +16,119 @@ types:
       id: optional<string>
       traceId: string
       name: string
-      value: double
+      value:
+        type: CreateScoreValue
+        docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores. Boolean score values must equal either 1 or 0 (true or false)
       observationId: optional<string>
       comment: optional<string>
-  Score:
+      dataType:
+        type: optional<ScoreDataType>
+        docs: When set, must match the score value's type. If not set, will be inferred from the score value or config
+      configId:
+        type: optional<string>
+        docs: Reference a score config on a score. When set, the score name must equal the config name and scores must comply with the config's range and data type. For categorical scores, the value must map to a config category. Numeric scores might be constrained by the score config's max and min values
+    examples:
+      - value:
+          name: "novelty"
+          value: 0.9
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "consistency"
+          value: 1.2
+          dataType: "NUMERIC"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "accuracy"
+          value: 0.9
+          dataType: "NUMERIC"
+          configId: "9203-4567-89ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "toxicity"
+          value: "not toxic"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "correctness"
+          value: "partially correct"
+          dataType: "CATEGORICAL"
+          configId: "1234-5678-90ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "hallucination"
+          value: 0
+          dataType: "BOOLEAN"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "helpfulness"
+          value: 1
+          dataType: "BOOLEAN"
+          configId: "1234-5678-90ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+  BaseScore:
     properties:
       id: string
       traceId: string
       name: string
-      value: double
+      source: ScoreSource
       observationId: optional<string>
       timestamp: datetime
+      createdAt: datetime
+      updatedAt: datetime
+      authorUserId: optional<string>
       comment: optional<string>
+      configId:
+        type: optional<string>
+        docs: Reference a score config on a score. When set, config and score name must be equal and value must comply to optionally defined numerical range
+  NumericScore:
+    extends: BaseScore
+    properties:
+      value:
+        type: double
+        docs: The numeric value of the score
+  BooleanScore:
+    extends: BaseScore
+    properties:
+      value:
+        type: double
+        docs: The numeric value of the score. Equals 1 for "True" and 0 for "False"
+      stringValue:
+        type: string
+        docs: The string representation of the score value. Is inferred from the numeric value and equals "True" or "False"
+  CategoricalScore:
+    extends: BaseScore
+    properties:
+      value:
+        type: optional<double>
+        docs: Only defined if a config is linked. Represents the numeric category mapping of the stringValue
+      stringValue:
+        type: string
+        docs: The string representation of the score value. If no config is linked, can be any string. Otherwise, must map to a config category
+  Score:
+    discriminant: "dataType"
+    union:
+      NUMERIC:
+        type: NumericScore
+        docs: "Score with NUMERIC data type"
+      CATEGORICAL:
+        type: CategoricalScore
+        docs: "Score with CATEGORICAL data type"
+      BOOLEAN:
+        type: BooleanScore
+        docs: "Score with BOOLEAN data type"
+  ScoreSource:
+    enum:
+      - ANNOTATION
+      - API
+      - EVAL
+  ScoreDataType:
+    enum:
+      - NUMERIC
+      - CATEGORICAL
+      - BOOLEAN
+
+  CreateScoreValue:
+    discriminated: false
+    union:
+      - double
+      - string
+    docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores

fern/apis/server/definition/comments.yml

@@ -0,0 +1,73 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  pagination: ./utils/pagination.yml
+  commons: ./commons.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    create:
+      docs: Create a comment. Comments may be attached to different object types (trace, observation, session, prompt).
+      method: POST
+      path: /comments
+      request: CreateCommentRequest
+      response: CreateCommentResponse
+    get:
+      docs: Get all comments
+      method: GET
+      path: /comments
+      request:
+        name: GetCommentsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: Page number, starts at 1.
+          limit:
+            type: optional<integer>
+            docs: Limit of items per page. If you encounter api issues due to too large page sizes, try to reduce the limit
+          objectType:
+            type: optional<string>
+            docs: Filter comments by object type (trace, observation, session, prompt).
+          objectId:
+            type: optional<string>
+            docs: Filter comments by object id. If objectType is not provided, an error will be thrown.
+          authorUserId:
+            type: optional<string>
+            docs: Filter comments by author user id.
+      response: GetCommentsResponse
+    get-by-id:
+      docs: Get a comment by id
+      method: GET
+      path: /comments/{commentId}
+      path-parameters:
+        commentId:
+          type: string
+          docs: The unique langfuse identifier of a comment
+      response: commons.Comment
+types:
+  CreateCommentRequest:
+    properties:
+      projectId:
+        type: string
+        docs: The id of the project to attach the comment to.
+      objectType:
+        type: string
+        docs: The type of the object to attach the comment to (trace, observation, session, prompt).
+      objectId:
+        type: string
+        docs: The id of the object to attach the comment to. If this does not reference a valid existing object, an error will be thrown.
+      content:
+        type: string
+        docs: The content of the comment. May include markdown. Currently limited to 500 characters.
+      authorUserId:
+        type: optional<string>
+        docs: The id of the user who created the comment.
+  CreateCommentResponse:
+    properties:
+      id:
+        type: string
+        docs: The id of the created object in Langfuse
+  GetCommentsResponse:
+    properties:
+      data: list<commons.Comment>
+      meta: pagination.MetaResponse

fern/apis/server/definition/commons.yml

@@ -5,16 +5,36 @@ types:
       id:
         type: string
         docs: The unique identifier of a trace
-      timestamp: datetime
-      name: optional<string>
-      input: optional<unknown>
-      output: optional<unknown>
-      sessionId: optional<string>
-      release: optional<string>
-      version: optional<string>
-      userId: optional<string>
-      metadata: optional<unknown>
-      tags: optional<list<string>>
+      timestamp:
+        type: datetime
+        docs: The timestamp when the trace was created
+      name:
+        type: optional<string>
+        docs: The name of the trace
+      input:
+        type: optional<unknown>
+        docs: The input data of the trace. Can be any JSON.
+      output:
+        type: optional<unknown>
+        docs: The output data of the trace. Can be any JSON.
+      sessionId:
+        type: optional<string>
+        docs: The session identifier associated with the trace
+      release:
+        type: optional<string>
+        docs: The release version of the application when the trace was created
+      version:
+        type: optional<string>
+        docs: The version of the trace
+      userId:
+        type: optional<string>
+        docs: The user identifier associated with the trace
+      metadata:
+        type: optional<unknown>
+        docs: The metadata associated with the trace. Can be any JSON.
+      tags:
+        type: optional<list<string>>
+        docs: The tags associated with the trace. Can be an array of strings or null.
       public:
         type: optional<boolean>
         docs: Public traces are accessible via url without login
@@ -42,11 +62,18 @@ types:
       htmlPath:
         type: string
         docs: Path of trace in Langfuse UI
+      latency:
+        type: double
+        docs: Latency of trace in seconds
       totalCost:
         type: double
         docs: Cost of trace in USD
-      observations: list<ObservationsView>
-      scores: list<Score>
+      observations:
+        type: list<ObservationsView>
+        docs: List of observations
+      scores:
+        type: list<Score>
+        docs: List of scores
   Session:
     properties:
       id: string
@@ -58,36 +85,97 @@ types:
       traces: list<Trace>
   Observation:
     properties:
-      id: string
-      traceId: optional<string>
-      type: string
-      name: optional<string>
-      startTime: datetime
-      endTime: optional<datetime>
-      completionStartTime: optional<datetime>
-      model: optional<string>
-      modelParameters: optional<map<string, MapValue>>
-      input: optional<unknown>
-      version: optional<string>
-      metadata: optional<unknown>
-      output: optional<unknown>
-      usage: optional<Usage>
-      level: ObservationLevel
-      statusMessage: optional<string>
-      parentObservationId: optional<string>
-      promptId: optional<string>
+      id:
+        type: string
+        docs: The unique identifier of the observation
+      traceId:
+        type: optional<string>
+        docs: The trace ID associated with the observation
+      type:
+        type: string
+        docs: The type of the observation
+      name:
+        type: optional<string>
+        docs: The name of the observation
+      startTime:
+        type: datetime
+        docs: The start time of the observation
+      endTime:
+        type: optional<datetime>
+        docs: The end time of the observation.
+      completionStartTime:
+        type: optional<datetime>
+        docs: The completion start time of the observation
+      model:
+        type: optional<string>
+        docs: The model used for the observation
+      modelParameters:
+        type: optional<map<string, MapValue>>
+        docs: The parameters of the model used for the observation
+      input:
+        type: optional<unknown>
+        docs: The input data of the observation
+      version:
+        type: optional<string>
+        docs: The version of the observation
+      metadata:
+        type: optional<unknown>
+        docs: Additional metadata of the observation
+      output:
+        type: optional<unknown>
+        docs: The output data of the observation
+      usage:
+        type: optional<Usage>
+        docs: The usage data of the observation
+      level:
+        type: ObservationLevel
+        docs: The level of the observation
+      statusMessage:
+        type: optional<string>
+        docs: The status message of the observation
+      parentObservationId:
+        type: optional<string>
+        docs: The parent observation ID
+      promptId:
+        type: optional<string>
+        docs: The prompt ID associated with the observation
 
   ObservationsView:
     extends: Observation
     properties:
-      modelId: optional<string>
-      inputPrice: optional<double>
-      outputPrice: optional<double>
-      totalPrice: optional<double>
-      calculatedInputCost: optional<double>
-      calculatedOutputCost: optional<double>
-      calculatedTotalCost: optional<double>
-      latency: optional<double>
+      promptName:
+        type: optional<string>
+        docs: The name of the prompt associated with the observation
+      promptVersion:
+        type: optional<integer>
+        docs: The version of the prompt associated with the observation
+      modelId:
+        type: optional<string>
+        docs: The unique identifier of the model
+      inputPrice:
+        type: optional<double>
+        docs: The price of the input in USD
+      outputPrice:
+        type: optional<double>
+        docs: The price of the output in USD.
+      totalPrice:
+        type: optional<double>
+        docs: The total price in USD.
+      calculatedInputCost:
+        type: optional<double>
+        docs: The calculated cost of the input in USD
+      calculatedOutputCost:
+        type: optional<double>
+        docs: The calculated cost of the output in USD
+      calculatedTotalCost:
+        type: optional<double>
+        docs: The calculated total cost in USD
+      latency:
+        type: optional<double>
+        docs: The latency in seconds.
+      timeToFirstToken:
+        type: optional<double>
+        docs: The time to the first token in seconds
 
   Usage:
     docs: Standard interface for usage and cost
@@ -111,18 +199,106 @@ types:
       totalCost:
         docs: USD total cost, defaults to input+output
         type: optional<double>
-
-  Score:
+  ScoreConfig:
+    docs: Configuration for a score
+    properties:
+      id: string
+      name: string
+      createdAt: datetime
+      updatedAt: datetime
+      projectId: string
+      dataType: ScoreDataType
+      isArchived:
+        type: boolean
+        docs: Whether the score config is archived. Defaults to false
+      minValue:
+        type: optional<double>
+        docs: Sets minimum value for numerical scores. If not set, the minimum value defaults to -∞
+      maxValue:
+        type: optional<double>
+        docs: Sets maximum value for numerical scores. If not set, the maximum value defaults to +∞
+      categories:
+        type: optional<list<ConfigCategory>>
+        docs: Configures custom categories for categorical scores
+      description: optional<string>
+  ConfigCategory:
+    properties:
+      value: double
+      label: string
+  BaseScore:
     properties:
       id: string
       traceId: string
       name: string
-      value: double
       source: ScoreSource
       observationId: optional<string>
       timestamp: datetime
+      createdAt: datetime
+      updatedAt: datetime
+      authorUserId: optional<string>
       comment: optional<string>
-  DatasetCore:
+      configId:
+        type: optional<string>
+        docs: Reference a score config on a score. When set, config and score name must be equal and value must comply to optionally defined numerical range
+      queueId:
+        type: optional<string>
+        docs: Reference an annotation queue on a score. Populated if the score was initially created in an annotation queue.
+  NumericScore:
+    extends: BaseScore
+    properties:
+      value:
+        type: double
+        docs: The numeric value of the score
+  BooleanScore:
+    extends: BaseScore
+    properties:
+      value:
+        type: double
+        docs: The numeric value of the score. Equals 1 for "True" and 0 for "False"
+      stringValue:
+        type: string
+        docs: The string representation of the score value. Is inferred from the numeric value and equals "True" or "False"
+  CategoricalScore:
+    extends: BaseScore
+    properties:
+      value:
+        type: optional<double>
+        docs: Only defined if a config is linked. Represents the numeric category mapping of the stringValue
+      stringValue:
+        type: string
+        docs: The string representation of the score value. If no config is linked, can be any string. Otherwise, must map to a config category
+  Score:
+    discriminant: "dataType"
+    union:
+      NUMERIC:
+        type: NumericScore
+        docs: "Score with NUMERIC data type"
+      CATEGORICAL:
+        type: CategoricalScore
+        docs: "Score with CATEGORICAL data type"
+      BOOLEAN:
+        type: BooleanScore
+        docs: "Score with BOOLEAN data type"
+
+  CreateScoreValue:
+    discriminated: false
+    union:
+      - double
+      - string
+    docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores
+
+  Comment:
+    properties:
+      id: string
+      projectId: string
+      createdAt: datetime
+      updatedAt: datetime
+      objectType: CommentObjectType
+      objectId: string
+      content: string
+      authorUserId: optional<string>
+
+  Dataset:
     properties:
       id: string
       name: string
@@ -131,21 +307,6 @@ types:
       projectId: string
       createdAt: datetime
       updatedAt: datetime
-  DatasetWithReferences: # GET datasets
-    extends: DatasetCore
-    properties:
-      items:
-        type: list<string>
-        docs: list of dataset item ids
-      runs:
-        type: list<string>
-        docs: list of dataset run names
-  Dataset: # GET datasets/[name]
-    docs: Dataset including all items
-    extends: DatasetCore
-    properties:
-      items: list<DatasetItem>
-      runs: list<string>
   DatasetItem:
     properties:
       id: string
@@ -171,15 +332,67 @@ types:
       updatedAt: datetime
   DatasetRun:
     properties:
-      id: string
-      name: string
-      description: optional<string>
-      metadata: optional<unknown>
-      datasetId: string
-      datasetName: string
-      createdAt: datetime
-      updatedAt: datetime
+      id:
+        type: string
+        docs: Unique identifier of the dataset run
+      name:
+        type: string
+        docs: Name of the dataset run
+      description:
+        type: optional<string>
+        docs: Description of the run
+      metadata:
+        type: optional<unknown>
+        docs: Metadata of the dataset run
+      datasetId:
+        type: string
+        docs: Id of the associated dataset
+      datasetName:
+        type: string
+        docs: Name of the associated dataset
+      createdAt:
+        type: datetime
+        docs: The date and time when the dataset run was created
+      updatedAt:
+        type: datetime
+        docs: The date and time when the dataset run was last updated
+  DatasetRunWithItems:
+    extends: DatasetRun
+    properties:
       datasetRunItems: list<DatasetRunItem>
+  Model:
+    docs: Model definition used for transforming usage into USD cost and/or tokenization.
+    properties:
+      id: string
+      modelName:
+        docs: "Name of the model definition. If multiple with the same name exist, they are applied in the following order: (1) custom over built-in, (2) newest according to startTime where model.startTime<observation.startTime"
+        type: string
+      matchPattern:
+        docs: "Regex pattern which matches this model definition to generation.model. Useful in case of fine-tuned models. If you want to exact match, use `(?i)^modelname$`"
+        type: string
+      startDate:
+        docs: Apply only to generations which are newer than this ISO date.
+        type: optional<date>
+      unit:
+        docs: Unit used by this model.
+        type: ModelUsageUnit
+      inputPrice:
+        docs: Price (USD) per input unit
+        type: optional<double>
+      outputPrice:
+        docs: Price (USD) per output unit
+        type: optional<double>
+      totalPrice:
+        docs: Price (USD) per total unit. Cannot be set if input or output price is set.
+        type: optional<double>
+      tokenizerId:
+        docs: Optional. Tokenizer to be applied to observations which match to this model. See docs for more details.
+        type: optional<string>
+      tokenizerConfig:
+        docs: Optional. Configuration for the selected tokenizer. Needs to be JSON. See docs for more details.
+        type: optional<unknown>
+      isLangfuseManaged:
+        type: boolean
 
   # Utilities
   ModelUsageUnit:
@@ -190,6 +403,7 @@ types:
       - MILLISECONDS
       - SECONDS
       - IMAGES
+      - REQUESTS
   ObservationLevel:
     enum:
       - DEBUG
@@ -203,6 +417,12 @@ types:
       - optional<integer>
       - optional<boolean>
       - optional<list<string>>
+  CommentObjectType:
+    enum:
+      - TRACE
+      - OBSERVATION
+      - SESSION
+      - PROMPT
   DatasetStatus:
     enum:
       - ACTIVE
@@ -212,6 +432,11 @@ types:
       - ANNOTATION
       - API
       - EVAL
+  ScoreDataType:
+    enum:
+      - NUMERIC
+      - BOOLEAN
+      - CATEGORICAL
 
 errors:
   Error:

fern/apis/server/definition/dataset-items.yml

@@ -1,6 +1,7 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
 imports:
   commons: ./commons.yml
+  pagination: ./utils/pagination.yml
 service:
   auth: true
   base-path: /api/public
@@ -19,6 +20,23 @@ service:
         id:
           type: string
       response: commons.DatasetItem
+    list:
+      docs: Get dataset items
+      method: GET
+      path: /dataset-items
+      request:
+        name: GetDatasetItemsRequest
+        query-parameters:
+          datasetName: optional<string>
+          sourceTraceId: optional<string>
+          sourceObservationId: optional<string>
+          page:
+            type: optional<integer>
+            docs: page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: limit of items per page
+      response: PaginatedDatasetItems
 
 types:
   CreateDatasetItemRequest:
@@ -31,7 +49,11 @@ types:
       sourceObservationId: optional<string>
       id:
         type: optional<string>
-        docs: Dataset items are upserted on their id
+        docs: Dataset items are upserted on their id. Id needs to be unique (project-level) and cannot be reused across datasets.
       status:
         type: optional<commons.DatasetStatus>
         docs: Defaults to ACTIVE for newly created items
+  PaginatedDatasetItems:
+    properties:
+      data: list<commons.DatasetItem>
+      meta: pagination.MetaResponse

fern/apis/server/definition/datasets.yml

@@ -9,42 +9,66 @@ service:
     list:
       method: GET
       docs: Get all datasets
-      path: /datasets
+      path: /v2/datasets
       request:
         name: GetDatasetsRequest
         query-parameters:
-          page: optional<integer>
-          limit: optional<integer>
+          page:
+            type: optional<integer>
+            docs: page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: limit of items per page
       response: PaginatedDatasets
     get:
       method: GET
-      docs: Get a dataset and its items
-      path: /datasets/{datasetName}
+      docs: Get a dataset
+      path: /v2/datasets/{datasetName}
       path-parameters:
         datasetName: string
       response: commons.Dataset
     create:
       method: POST
       docs: Create a dataset
-      path: /datasets
+      path: /v2/datasets
       request: CreateDatasetRequest
       response: commons.Dataset
-    getRuns:
+    getRun:
       method: GET
       docs: Get a dataset run and its items
       path: /datasets/{datasetName}/runs/{runName}
       path-parameters:
         datasetName: string
         runName: string
-      response: commons.DatasetRun
+      response: commons.DatasetRunWithItems
+    getRuns:
+      method: GET
+      docs: Get dataset runs
+      path: /datasets/{datasetName}/runs
+      path-parameters:
+        datasetName: string
+      request:
+        name: GetDatasetRunsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: limit of items per page
+      response: PaginatedDatasetRuns
 
 types:
   PaginatedDatasets:
     properties:
-      data: list<commons.DatasetWithReferences>
+      data: list<commons.Dataset>
       meta: pagination.MetaResponse
   CreateDatasetRequest:
     properties:
       name: string
       description: optional<string>
       metadata: optional<unknown>
+  PaginatedDatasetRuns:
+    properties:
+      data: list<commons.DatasetRun>
+      meta: pagination.MetaResponse

fern/apis/server/definition/ingestion.yml

@@ -7,28 +7,57 @@ service:
   base-path: /api/public
   endpoints:
     batch:
-      docs: Batched ingestion for Langfuse Tracing
+      docs: |
+        Batched ingestion for Langfuse Tracing. If you want to use tracing via the API, such as to build your own Langfuse client implementation, this is the only API route you need to implement.
+
+        Notes:
+        - Batch sizes are limited to 3.5 MB in total. You need to adjust the number of events per batch accordingly.
+        - The API does not return a 4xx status code for input errors. Instead, it responds with a 207 status code, which includes a list of the encountered errors.
       method: POST
       path: /ingestion
       request:
         name: IngestionRequest
         body:
           properties:
-            batch: list<IngestionEvent>
-      response: IngestionResponse # will be reportet as 200 response, but endpoint returns 207
+            batch:
+              type: list<IngestionEvent>
+              docs: "Batch of tracing events to be ingested. Discriminated by attribute `type`."
+            metadata:
+              type: optional<unknown>
+              docs: Optional. Metadata field used by the Langfuse SDKs for debugging.
+      response:
+        type: IngestionResponse
+        status-code: 207
 
 types:
   IngestionEvent:
     discriminant: "type"
     union:
-      trace-create: TraceEvent
-      score-create: ScoreEvent
-      event-create: CreateEventEvent
-      generation-create: CreateGenerationEvent
-      generation-update: UpdateGenerationEvent
-      span-create: CreateSpanEvent
-      span-update: UpdateSpanEvent
-      sdk-log: SDKLogEvent
+      trace-create:
+        type: TraceEvent
+        docs: Creates a new trace. Upserts on id for updates if trace with id exists.
+      score-create:
+        type: ScoreEvent
+        docs: Creates a new score. Upserts on id for updates if score with id exists.
+      span-create:
+        type: CreateSpanEvent
+        docs: Creates a new span.
+      span-update:
+        type: UpdateSpanEvent
+        docs: Updates span based on id.
+      generation-create:
+        type: CreateGenerationEvent
+        docs: Creates a new generation.
+      generation-update:
+        type: UpdateGenerationEvent
+        docs: Updates a generation based on id.
+      event-create:
+        type: CreateEventEvent
+        docs: Creates an event.
+
+      sdk-log:
+        type: SDKLogEvent
+        docs: Langfuse SDKs only, used for debugging purposes.
 
       # both are legacy
       observation-create:
@@ -156,15 +185,66 @@ types:
       id: optional<string>
       traceId: string
       name: string
-      value: double
+      value:
+        type: commons.CreateScoreValue
+        docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores. Boolean score values must equal either 1 or 0 (true or false)
       observationId: optional<string>
       comment: optional<string>
+      dataType:
+        type: optional<commons.ScoreDataType>
+        docs: When set, must match the score value's type. If not set, will be inferred from the score value or config
+      configId:
+        type: optional<string>
+        docs: Reference a score config on a score. When set, the score name must equal the config name and scores must comply with the config's range and data type. For categorical scores, the value must map to a config category. Numeric scores might be constrained by the score config's max and min values
+    examples:
+      - value:
+          name: "novelty"
+          value: 0.9
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "consistency"
+          value: 1.2
+          dataType: "NUMERIC"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "accuracy"
+          value: 0.9
+          dataType: "NUMERIC"
+          configId: "9203-4567-89ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "toxicity"
+          value: "not toxic"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "correctness"
+          value: "partially correct"
+          dataType: "CATEGORICAL"
+          configId: "1234-5678-90ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "hallucination"
+          value: 0
+          dataType: "BOOLEAN"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "helpfulness"
+          value: 1
+          dataType: "BOOLEAN"
+          configId: "1234-5678-90ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
 
   BaseEvent:
     properties:
-      id: string
-      timestamp: string
-      metadata: unknown
+      id:
+        type: string
+        docs: UUID v4 that identifies the event
+      timestamp:
+        type: string
+        docs: "Datetime (ISO 8601) of event creation in client. Should be as close to actual event creation in client as possible, this timestamp will be used for ordering of events in future release. Resolution: milliseconds (required), microseconds (optimal)."
+      metadata:
+        type: optional<unknown>
+        docs: Optional. Metadata field used by the Langfuse SDKs for debugging.
 
   TraceEvent:
     extends: BaseEvent

fern/apis/server/definition/media.yml

@@ -0,0 +1,101 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  commons: ./commons.yml
+
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    get:
+      docs: Get a media record
+      method: GET
+      path: /media/{mediaId}
+      path-parameters:
+        mediaId:
+          type: string
+          docs: The unique langfuse identifier of a media record
+      response: GetMediaResponse
+
+    patch:
+      docs: Patch a media record
+      method: PATCH
+      path: /media/{mediaId}
+      path-parameters:
+        mediaId:
+          type: string
+          docs: The unique langfuse identifier of a media record
+      request: PatchMediaBody
+
+    getUploadUrl:
+      docs: Get a presigned upload URL for a media record
+      method: POST
+      path: /media
+      request: GetMediaUploadUrlRequest
+      response: GetMediaUploadUrlResponse
+
+types:
+  GetMediaResponse:
+    properties:
+      mediaId:
+        type: string
+        docs: The unique langfuse identifier of a media record
+      contentType:
+        type: string
+        docs: The MIME type of the media record
+      contentLength:
+        type: integer
+        docs: The size of the media record in bytes
+      uploadedAt:
+        type: datetime
+        docs: The date and time when the media record was uploaded
+      url:
+        type: string
+        docs: The download URL of the media record
+      urlExpiry:
+        type: string
+        docs: The expiry date and time of the media record download URL
+
+  PatchMediaBody:
+    properties:
+      uploadedAt:
+        type: datetime
+        docs: The date and time when the media record was uploaded
+      uploadHttpStatus:
+        type: integer
+        docs: The HTTP status code of the upload
+      uploadHttpError:
+        type: optional<string>
+        docs: The HTTP error message of the upload
+      uploadTimeMs:
+        type: optional<integer>
+        docs: The time in milliseconds it took to upload the media record
+
+  GetMediaUploadUrlRequest:
+    properties:
+      traceId:
+        type: string
+        docs: The trace ID associated with the media record
+      observationId:
+        type: optional<string>
+        docs: The observation ID associated with the media record. If the media record is associated directly with a trace, this will be null.
+      contentType:
+        type: string
+        docs: The MIME type of the media record
+      contentLength:
+        type: integer
+        docs: The size of the media record in bytes
+      sha256Hash:
+        type: string
+        docs: The SHA-256 hash of the media record
+      field:
+        type: string
+        docs: The trace / observation field the media record is associated with. This can be one of `input`, `output`, `metadata`
+
+  GetMediaUploadUrlResponse:
+    properties:
+      uploadUrl:
+        type: optional<string>
+        docs: The presigned upload URL. If the asset is already uploaded, this will be null
+      mediaId:
+        type: string
+        docs: The unique langfuse identifier of a media record

fern/apis/server/definition/metrics.yml

@@ -31,10 +31,10 @@ service:
             docs: Optional filter for metrics where traces include all of these tags
           fromTimestamp:
             type: optional<datetime>
-            docs: Optional filter to only include traces on or after a certain datetime (ISO 8601)
+            docs: Optional filter to only include traces and observations on or after a certain datetime (ISO 8601)
           toTimestamp:
             type: optional<datetime>
-            docs: Optional filter to only include traces before a certain datetime (ISO 8601)
+            docs: Optional filter to only include traces and observations before a certain datetime (ISO 8601)
       response: DailyMetrics
 types:
   DailyMetrics:

fern/apis/server/definition/models.yml

@@ -0,0 +1,76 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  commons: ./commons.yml
+  pagination: ./utils/pagination.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    create:
+      method: POST
+      docs: Create a model
+      path: /models
+      request: CreateModelRequest
+      response: commons.Model
+    list:
+      method: GET
+      docs: Get all models
+      path: /models
+      request:
+        name: GetModelsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: limit of items per page
+      response: PaginatedModels
+    get:
+      method: GET
+      docs: Get a model
+      path: /models/{id}
+      path-parameters:
+        id: string
+      response: commons.Model
+    delete:
+      method: DELETE
+      docs: Delete a model. Cannot delete models managed by Langfuse. You can create your own definition with the same modelName to override the definition though.
+      path: /models/{id}
+      path-parameters:
+        id: string
+
+types:
+  PaginatedModels:
+    properties:
+      data: list<commons.Model>
+      meta: pagination.MetaResponse
+  CreateModelRequest:
+    properties:
+      modelName:
+        docs: "Name of the model definition. If multiple with the same name exist, they are applied in the following order: (1) custom over built-in, (2) newest according to startTime where model.startTime<observation.startTime"
+        type: string
+      matchPattern:
+        docs: "Regex pattern which matches this model definition to generation.model. Useful in case of fine-tuned models. If you want to exact match, use `(?i)^modelname$`"
+        type: string
+      startDate:
+        docs: Apply only to generations which are newer than this ISO date.
+        type: optional<datetime>
+      unit:
+        docs: Unit used by this model.
+        type: commons.ModelUsageUnit
+      inputPrice:
+        docs: Price (USD) per input unit
+        type: optional<double>
+      outputPrice:
+        docs: Price (USD) per output unit
+        type: optional<double>
+      totalPrice:
+        docs: Price (USD) per total units. Cannot be set if input or output price is set.
+        type: optional<double>
+      tokenizerId:
+        docs: Optional. Tokenizer to be applied to observations which match to this model. See docs for more details.
+        type: optional<string>
+      tokenizerConfig:
+        docs: Optional. Configuration for the selected tokenizer. Needs to be JSON. See docs for more details.
+        type: optional<unknown>

fern/apis/server/definition/observations.yml

@@ -35,7 +35,13 @@ service:
           parentObservationId: optional<string>
           fromStartTime:
             type: optional<datetime>
-            docs: Retrieve only observations with a start_time greater than this datetime (ISO 8601).
+            docs: Retrieve only observations with a start_time or or after this datetime (ISO 8601).
+          toStartTime:
+            type: optional<datetime>
+            docs: Retrieve only observations with a start_time before this datetime (ISO 8601).
+          version:
+            type: optional<string>
+            docs: Optional filter to only include observations with a certain version.
       response: ObservationsViews
 
 types:

fern/apis/server/definition/prompts.yml

@@ -35,13 +35,23 @@ service:
           name: optional<string>
           label: optional<string>
           tag: optional<string>
-          page: optional<integer>
-          limit: optional<integer>
+          page:
+            type: optional<integer>
+            docs: page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: limit of items per page
+          fromUpdatedAt:
+            type: optional<datetime>
+            docs: Optional filter to only include prompt versions created/updated on or after a certain datetime (ISO 8601)
+          toUpdatedAt:
+            type: optional<datetime>
+            docs: Optional filter to only include prompt versions created/updated before a certain datetime (ISO 8601)
 
       response: PromptMetaListResponse
 
     create:
-      docs: Create a prompt
+      docs: Create a new version for the prompt with the given `name`
       method: POST
       path: /prompts
       request: CreatePromptRequest
@@ -59,6 +69,10 @@ types:
       versions: list<integer>
       labels: list<string>
       tags: list<string>
+      lastUpdatedAt: datetime
+      lastConfig:
+        type: unknown
+        docs: Config object of the most recent prompt version that matches the filters (if any are provided)
 
   CreatePromptRequest:
     union:

fern/apis/server/definition/score-configs.yml

@@ -0,0 +1,58 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fern-api/fern/main/fern.schema.json
+imports:
+  pagination: ./utils/pagination.yml
+  commons: ./commons.yml
+service:
+  auth: true
+  base-path: /api/public
+  endpoints:
+    create:
+      docs: Create a score configuration (config). Score configs are used to define the structure of scores
+      method: POST
+      path: /score-configs
+      request: CreateScoreConfigRequest
+      response: commons.ScoreConfig
+    get:
+      docs: Get all score configs
+      method: GET
+      path: /score-configs
+      request:
+        name: GetScoreConfigsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: Page number, starts at 1.
+          limit:
+            type: optional<integer>
+            docs: Limit of items per page. If you encounter api issues due to too large page sizes, try to reduce the limit
+      response: ScoreConfigs
+    get-by-id:
+      docs: Get a score config
+      method: GET
+      path: /score-configs/{configId}
+      path-parameters:
+        configId:
+          type: string
+          docs: The unique langfuse identifier of a score config
+      response: commons.ScoreConfig
+types:
+  ScoreConfigs:
+    properties:
+      data: list<commons.ScoreConfig>
+      meta: pagination.MetaResponse
+  CreateScoreConfigRequest:
+    properties:
+      name: string
+      dataType: commons.ScoreDataType
+      categories:
+        type: optional<list<commons.ConfigCategory>>
+        docs: Configure custom categories for categorical scores. Pass a list of objects with `label` and `value` properties. Categories are autogenerated for boolean configs and cannot be passed
+      minValue:
+        type: optional<double>
+        docs: Configure a minimum value for numerical scores. If not set, the minimum value defaults to -∞
+      maxValue:
+        type: optional<double>
+        docs: Configure a maximum value for numerical scores. If not set, the maximum value defaults to +∞
+      description:
+        type: optional<string>
+        docs: Description is shown across the Langfuse UI and can be used to e.g. explain the config categories in detail, why a numeric range was set, or provide additional context on config name or usage

fern/apis/server/definition/score.yml

@@ -11,7 +11,7 @@ service:
       method: POST
       path: /scores
       request: CreateScoreRequest
-      response: commons.Score
+      response: CreateScoreResponse
     get:
       docs: Get a list of scores
       method: GET
@@ -25,13 +25,20 @@ service:
           limit:
             type: optional<integer>
             docs: Limit of items per page. If you encounter api issues due to too large page sizes, try to reduce the limit.
-          userId: optional<string>
-          name: optional<string>
+          userId:
+            type: optional<string>
+            docs: Retrieve only scores with this userId associated to the trace.
+          name:
+            type: optional<string>
+            docs: Retrieve only scores with this name.
           fromTimestamp:
             type: optional<datetime>
-            docs: Retrieve only scores newer than this datetime (ISO 8601).
+            docs: Optional filter to only include scores created on or after a certain datetime (ISO 8601)
+          toTimestamp:
+            type: optional<datetime>
+            docs: Optional filter to only include scores created before a certain datetime (ISO 8601)
           source:
-            type: commons.ScoreSource
+            type: optional<commons.ScoreSource>
             docs: Retrieve only scores from a specific source.
           operator:
             type: optional<string>
@@ -39,7 +46,23 @@ service:
           value:
             type: optional<double>
             docs: Retrieve only scores with <operator> value.
-      response: Scores
+          scoreIds:
+            type: optional<string>
+            docs: Comma-separated list of score IDs to limit the results to.
+          configId:
+            type: optional<string>
+            docs: Retrieve only scores with a specific configId.
+          queueId:
+            type: optional<string>
+            docs: Retrieve only scores with a specific annotation queueId.
+          dataType:
+            type: optional<commons.ScoreDataType>
+            docs: Retrieve only scores with a specific dataType.
+          traceTags:
+            type: optional<list<string>>
+            allow-multiple: true
+            docs: Only scores linked to traces that include all of these tags will be returned.
+      response: GetScoresResponse
     get-by-id:
       docs: Get a score
       method: GET
@@ -63,10 +86,91 @@ types:
       id: optional<string>
       traceId: string
       name: string
-      value: double
+      value:
+        type: commons.CreateScoreValue
+        docs: The value of the score. Must be passed as string for categorical scores, and numeric for boolean and numeric scores. Boolean score values must equal either 1 or 0 (true or false)
       observationId: optional<string>
       comment: optional<string>
-  Scores:
+      dataType:
+        type: optional<commons.ScoreDataType>
+        docs: The data type of the score. When passing a configId this field is inferred. Otherwise, this field must be passed or will default to numeric.
+      configId:
+        type: optional<string>
+        docs: Reference a score config on a score. The unique langfuse identifier of a score config. When passing this field, the dataType and stringValue fields are automatically populated.
+    examples:
+      - value:
+          name: "novelty"
+          value: 0.9
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "consistency"
+          value: 1.2
+          dataType: "NUMERIC"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "accuracy"
+          value: 0.9
+          dataType: "NUMERIC"
+          configId: "9203-4567-89ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "toxicity"
+          value: "not toxic"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "correctness"
+          value: "partially correct"
+          dataType: "CATEGORICAL"
+          configId: "1234-5678-90ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "hallucination"
+          value: 0
+          dataType: "BOOLEAN"
+          traceId: "cdef-1234-5678-90ab"
+      - value:
+          name: "helpfulness"
+          value: 1
+          dataType: "BOOLEAN"
+          configId: "1234-5678-90ab-cdef"
+          traceId: "cdef-1234-5678-90ab"
+  CreateScoreResponse:
     properties:
-      data: list<commons.Score>
+      id:
+        type: string
+        docs: The id of the created object in Langfuse
+  GetScoresResponseTraceData:
+    properties:
+      userId:
+        type: optional<string>
+        docs: The user ID associated with the trace referenced by score
+      tags:
+        type: optional<list<string>>
+        docs: A list of tags associated with the trace referenced by score
+
+  GetScoresResponseDataNumeric:
+    extends: commons.NumericScore
+    properties:
+      trace: GetScoresResponseTraceData
+
+  GetScoresResponseDataCategorical:
+    extends: commons.CategoricalScore
+    properties:
+      trace: GetScoresResponseTraceData
+
+  GetScoresResponseDataBoolean:
+    extends: commons.BooleanScore
+    properties:
+      trace: GetScoresResponseTraceData
+
+  GetScoresResponseData:
+    discriminant: dataType
+    union:
+      NUMERIC: GetScoresResponseDataNumeric
+      CATEGORICAL: GetScoresResponseDataCategorical
+      BOOLEAN: GetScoresResponseDataBoolean
+
+  GetScoresResponse:
+    properties:
+      data: list<GetScoresResponseData>
       meta: pagination.MetaResponse

fern/apis/server/definition/sessions.yml

@@ -6,6 +6,26 @@ service:
   auth: true
   base-path: /api/public
   endpoints:
+    list:
+      docs: Get sessions
+      method: GET
+      path: /sessions
+      request:
+        name: GetSessionsRequest
+        query-parameters:
+          page:
+            type: optional<integer>
+            docs: Page number, starts at 1
+          limit:
+            type: optional<integer>
+            docs: Limit of items per page. If you encounter api issues due to too large page sizes, try to reduce the limit.
+          fromTimestamp:
+            type: optional<datetime>
+            docs: Optional filter to only include sessions created on or after a certain datetime (ISO 8601)
+          toTimestamp:
+            type: optional<datetime>
+            docs: Optional filter to only include sessions created before a certain datetime (ISO 8601)
+      response: PaginatedSessions
     get:
       docs: Get a session. Please note that `traces` on this endpoint are not paginated, if you plan to fetch large sessions, consider `GET /api/public/traces?sessionId=<sessionId>`
       method: GET
@@ -15,3 +35,8 @@ service:
           type: string
           docs: The unique id of a session
       response: commons.SessionWithTraces
+types:
+  PaginatedSessions:
+    properties:
+      data: list<commons.Session>
+      meta: pagination.MetaResponse

fern/apis/server/definition/trace.yml

@@ -16,7 +16,7 @@ service:
           docs: The unique langfuse identifier of a trace
       response: commons.TraceWithFullDetails
     list:
-      docs: Get list of traces.
+      docs: Get list of traces
       method: GET
       path: /traces
       request:
@@ -33,7 +33,10 @@ service:
           sessionId: optional<string>
           fromTimestamp:
             type: optional<datetime>
-            docs: Retrieve only traces newer than this datetime (ISO 8601).
+            docs: Optional filter to only include traces with a trace.timestamp on or after a certain datetime (ISO 8601)
+          toTimestamp:
+            type: optional<datetime>
+            docs: Optional filter to only include traces with a trace.timestamp before a certain datetime (ISO 8601)
           orderBy:
             type: optional<string>
             docs: "Format of the string [field].[asc/desc]. Fields: id, timestamp, name, userId, release, version, public, bookmarked, sessionId. Example: timestamp.asc"
@@ -41,6 +44,12 @@ service:
             type: optional<string>
             allow-multiple: true
             docs: Only traces that include all of these tags will be returned.
+          version:
+            type: optional<string>
+            docs: Optional filter to only include traces with a certain version.
+          release:
+            type: optional<string>
+            docs: Optional filter to only include traces with a certain release.
       response: Traces
 
 types:

fern/apis/server/definition/utils/pagination.yml

@@ -1,4 +1,13 @@
 types:
+  # to be used as copy/paste template for query strings
+  # PaginationRequest:
+  #   properties:
+  #     page:
+  #       type: optional<integer>
+  #       docs: page number, starts at 1
+  #     limit:
+  #       type: optional<integer>
+  #       docs: limit of items per page
   MetaResponse:
     properties:
       page:

fern/apis/server/generators.yml

@@ -3,32 +3,22 @@ groups:
   local:
     generators:
       - name: fernapi/fern-openapi
-        version: 0.0.28
+        version: 0.0.31
         output:
           location: local-file-system
           path: ../../../web/public/generated/api
-        config:
-          namespaceExport: Langfuse
-          allowCustomFetcher: true
       - name: fernapi/fern-python-sdk
-        version: 1.1.0-rc2
+        version: 2.16.0
         output:
           location: local-file-system
           path: ../../../generated/python
         config:
           client_class_name: FernLangfuse
           improved_imports: false
+          inline_request_params: false
           pydantic_config:
             require_optional_fields: false
             use_str_enums: false
-      - name: fernapi/fern-typescript-node-sdk
-        version: 0.7.1
-        output:
-          location: local-file-system
-          path: ../../../generated/typescript-server
-        config:
-          namespaceExport: Langfuse
-          allowCustomFetcher: true
       - name: fernapi/fern-postman
         version: 0.0.45
         output:

fern/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization": "finto",
-  "version": "0.21.0"
+  "version": "0.43.7"
 }

package.json

@@ -1,42 +1,53 @@
 {
   "name": "langfuse",
-  "version": "2.49.2",
+  "version": "2.90.1",
   "author": "engineering@langfuse.com",
   "license": "MIT",
   "private": true,
   "engines": {
-    "node": ">=20",
-    "pnpm": "<9"
+    "node": "20"
   },
   "scripts": {
     "preinstall": "npx only-allow pnpm",
-    "infra:dev:up": "docker compose -f ./docker-compose.dev.yml up -d",
+    "infra:dev:up": "docker compose -f ./docker-compose.dev.yml up -d --wait",
     "infra:dev:down": "docker compose -f ./docker-compose.dev.yml down",
+    "infra:dev:prune": "docker compose -f ./docker-compose.dev.yml down -v",
     "db:generate": "turbo run db:generate",
     "db:migrate": "turbo run db:migrate",
     "db:seed": "turbo run db:seed",
     "db:seed:examples": "turbo run db:seed:examples",
     "nuke": "bash ./scripts/nuke.sh",
-    "dx": "pnpm i && pnpm --filter=shared run db:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
+    "dx": "pnpm i && pnpm run infra:dev:prune && pnpm run infra:dev:up --pull always && pnpm --filter=shared run db:reset && pnpm --filter=shared run ch:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
+    "dx-f": "pnpm i && pnpm run infra:dev:prune && pnpm run infra:dev:up --pull always && pnpm --filter=shared run db:reset -f && pnpm --filter=shared run ch:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
+    "dx:skip-infra": "pnpm i && pnpm --filter=shared run db:reset && pnpm --filter=shared run ch:reset && pnpm --filter=shared run db:seed:examples && pnpm run dev",
     "build": "turbo run build",
     "start": "turbo run start",
     "dev": "turbo run dev",
     "lint": "turbo run lint",
     "test": "turbo run test",
     "models:migrate": "turbo run models:migrate",
-    "release": "dotenv -e ../.env -- release-it"
+    "release": "dotenv -e ../.env -- release-it",
+    "prepare": "husky"
   },
   "devDependencies": {
     "@release-it/bumper": "^6.0.1",
+    "braces": "3.0.3",
     "dotenv-cli": "^7.4.2",
-    "prettier": "^3.2.5",
-    "release-it": "^17.2.1",
-    "turbo": "^1.13.3"
+    "husky": "^9.0.11",
+    "prettier": "^3.3.3",
+    "release-it": "^17.3.0",
+    "turbo": "^1.13.4"
   },
   "release-it": {
     "git": {
       "commitMessage": "chore: release v${version}",
-      "tagName": "v${version}"
+      "tagName": "v${version}",
+      "commitArgs": [
+        "--no-verify"
+      ],
+      "pushArgs": [
+        "--no-verify"
+      ]
     },
     "plugins": {
       "@release-it/bumper": {
@@ -69,5 +80,11 @@
         "pr": ":rocket: _This pull request is included in v${version}. See [${releaseName}](${releaseUrl}) for release notes._"
       }
     }
-  }
+  },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.0"
+    }
+  },
+  "packageManager": "pnpm@9.5.0"
 }

packages/config-eslint/package.json

@@ -11,9 +11,9 @@
     "@typescript-eslint/eslint-plugin": "^7.1.0",
     "@typescript-eslint/parser": "^7.12.0",
     "@vercel/style-guide": "^6.0.0",
-    "eslint-config-next": "^14.2.3",
+    "eslint-config-next": "^14.2.15",
     "eslint-config-prettier": "^9.1.0",
-    "eslint-config-turbo": "^1.13.3",
+    "eslint-config-turbo": "^1.13.4",
     "eslint-plugin-only-warn": "^1.1.0",
     "typescript": "^5.4.5"
   }

packages/shared/clickhouse/migrations/0001_traces.down.sql

@@ -0,0 +1 @@
+DROP TABLE traces;

packages/shared/clickhouse/migrations/0001_traces.up.sql

@@ -0,0 +1,32 @@
+CREATE TABLE traces (
+    `id` String,
+    `timestamp` DateTime64(3),
+    `name` String,
+    `user_id` Nullable(String),
+    `metadata` Map(LowCardinality(String), String),
+    `release` Nullable(String),
+    `version` Nullable(String),
+    `project_id` String,
+    `public` Bool,
+    `bookmarked` Bool,
+    `tags` Array(String),
+    `input` Nullable(String) CODEC(ZSTD(3)),
+    `output` Nullable(String) CODEC(ZSTD(3)),
+    `session_id` Nullable(String),
+    `created_at` DateTime64(3) DEFAULT now(),
+    updated_at DateTime64(3) DEFAULT now(),
+    `event_ts` DateTime64(3),
+    `is_deleted` UInt8,
+    INDEX idx_id id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_res_metadata_key mapKeys(metadata) TYPE bloom_filter(0.01) GRANULARITY 1,
+    INDEX idx_res_metadata_value mapValues(metadata) TYPE bloom_filter(0.01) GRANULARITY 1
+) ENGINE = ReplacingMergeTree(event_ts, is_deleted) Partition by toYYYYMM(timestamp)
+PRIMARY KEY (
+        project_id,
+        toDate(timestamp)
+)
+ORDER BY (
+        project_id,
+        toDate(timestamp),
+        id
+    );

packages/shared/clickhouse/migrations/0002_observations.down.sql

@@ -0,0 +1 @@
+DROP TABLE observations;

packages/shared/clickhouse/migrations/0002_observations.up.sql

@@ -0,0 +1,47 @@
+CREATE TABLE observations (
+    `id` String,
+    `trace_id` String,
+    `project_id` String,
+    `type` LowCardinality(String),
+    `parent_observation_id` Nullable(String),
+    `start_time` DateTime64(3),
+    `end_time` Nullable(DateTime64(3)),
+    `name` String,
+    `metadata` Map(LowCardinality(String), String),
+    `level` LowCardinality(String),
+    `status_message` Nullable(String),
+    `version` Nullable(String),
+    `input` Nullable(String) CODEC(ZSTD(3)),
+    `output` Nullable(String) CODEC(ZSTD(3)),
+    `provided_model_name` Nullable(String),
+    `internal_model_id` Nullable(String),
+    `model_parameters` Nullable(String),
+    `provided_usage_details` Map(LowCardinality(String), UInt64),
+    `usage_details` Map(LowCardinality(String), UInt64),
+    `provided_cost_details` Map(LowCardinality(String), Decimal64(12)),
+    `cost_details` Map(LowCardinality(String), Decimal64(12)),
+    `total_cost` Nullable(Decimal64(12)),
+    `completion_start_time` Nullable(DateTime64(3)),
+    `prompt_id` Nullable(String),
+    `prompt_name` Nullable(String),
+    `prompt_version` Nullable(UInt16),
+    `created_at` DateTime64(3) DEFAULT now(),
+    `updated_at` DateTime64(3) DEFAULT now(),
+    event_ts DateTime64(3),
+    is_deleted UInt8,
+    INDEX idx_id id TYPE bloom_filter() GRANULARITY 1,
+    INDEX idx_trace_id trace_id TYPE bloom_filter() GRANULARITY 1,
+    INDEX idx_project_id project_id TYPE bloom_filter() GRANULARITY 1
+) ENGINE = ReplacingMergeTree(event_ts, is_deleted) Partition by toYYYYMM(start_time)
+PRIMARY KEY (
+        project_id,
+        `type`,
+        toDate(start_time)
+    )
+ORDER BY (
+        project_id,
+        `type`,
+        toDate(start_time),
+        id
+    );
+

packages/shared/clickhouse/migrations/0003_scores.down.sql

@@ -0,0 +1 @@
+DROP TABLE scores;

packages/shared/clickhouse/migrations/0003_scores.up.sql

@@ -0,0 +1,33 @@
+CREATE TABLE scores (
+    `id` String,
+    `timestamp` DateTime64(3),
+    `project_id` String,
+    `trace_id` String,
+    `observation_id` Nullable(String),
+    `name` String,
+    `value` Float64,
+    `source` String,
+    `comment` Nullable(String) CODEC(ZSTD(1)),
+    `author_user_id` Nullable(String),
+    `config_id` Nullable(String),
+    `data_type` String,
+    `string_value` Nullable(String),
+    `queue_id` Nullable(String),
+    `created_at` DateTime64(3) DEFAULT now(),
+    `updated_at` DateTime64(3) DEFAULT now(),
+    event_ts DateTime64(3),
+    `is_deleted` UInt8,
+    INDEX idx_id id TYPE bloom_filter(0.001) GRANULARITY 1,
+    INDEX idx_project_trace_observation (project_id, trace_id, observation_id) TYPE bloom_filter(0.001) GRANULARITY 1
+) ENGINE = ReplacingMergeTree(event_ts, is_deleted) Partition by toYYYYMM(timestamp)
+PRIMARY KEY (
+        project_id,
+        toDate(timestamp),
+        name
+    )
+ORDER BY (
+        project_id,
+        toDate(timestamp),
+        name,
+        id
+    )

packages/shared/clickhouse/migrations/0004_drop_observations_index.down.sql

@@ -0,0 +1 @@
+ALTER TABLE observations ADD INDEX IF NOT EXISTS idx_project_id project_id TYPE bloom_filter() GRANULARITY 1;

packages/shared/clickhouse/migrations/0004_drop_observations_index.up.sql

@@ -0,0 +1 @@
+ALTER TABLE observations DROP INDEX IF EXISTS idx_project_id;

packages/shared/clickhouse/migrations/0005_add_session_id_index.down.sql

@@ -0,0 +1 @@
+ALTER TABLE traces DROP INDEX IF EXISTS idx_session_id;

packages/shared/clickhouse/migrations/0005_add_session_id_index.up.sql

@@ -0,0 +1,2 @@
+ALTER TABLE traces ADD INDEX IF NOT EXISTS idx_session_id session_id TYPE bloom_filter() GRANULARITY 1;
+ALTER TABLE traces MATERIALIZE INDEX IF EXISTS idx_session_id;

packages/shared/clickhouse/scripts/down.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+# Load environment variables
+source ../../.env
+
+# Check if golang-migrate is installed
+if ! command -v migrate &> /dev/null
+then
+    echo "Error: golang-migrate is not installed or not in PATH."
+    echo "Please install golang-migrate via 'brew install golang-migrate' to run this script."
+    echo "Visit https://github.com/golang-migrate/migrate for more installation instructions."
+    exit 1
+fi
+
+# Construct the database URL
+if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
+    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&secure=true&skip_verify=true&x-migrations-table-engine=MergeTree"
+else
+    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-migrations-table-engine=MergeTree"
+fi
+# Execute the down command
+migrate -source file://clickhouse/migrations -database "$DATABASE_URL" down

packages/shared/clickhouse/scripts/drop.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+# Load environment variables
+source ../../.env
+
+# Check if golang-migrate is installed
+if ! command -v migrate &> /dev/null
+then
+    echo "Error: golang-migrate is not installed or not in PATH."
+    echo "Please install golang-migrate via 'brew install golang-migrate' to run this script."
+    echo "Visit https://github.com/golang-migrate/migrate for more installation instructions."
+    exit 1
+fi
+
+# Construct the database URL
+if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
+    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&secure=true&skip_verify=true&x-migrations-table-engine=MergeTree"
+else
+    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-migrations-table-engine=MergeTree"
+fi
+# Execute the drop command
+migrate -source file://clickhouse/migrations -database "$DATABASE_URL" drop

packages/shared/clickhouse/scripts/seed.ts

@@ -0,0 +1,25 @@
+import { clickhouseClient } from "@langfuse/shared/src/server";
+import { prisma } from "../../src/db";
+import { redis } from "@langfuse/shared/src/server";
+import { prepareClickhouse } from "../../scripts/prepareClickhouse";
+
+async function main() {
+  try {
+    const projectIds = ["7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"]; // Example project IDs
+    await prepareClickhouse(projectIds, {
+      numberOfDays: 3,
+      totalObservations: 10000,
+    });
+
+    console.log("Clickhouse preparation completed successfully.");
+  } catch (error) {
+    console.error("Error during Clickhouse preparation:", error);
+  } finally {
+    await clickhouseClient.close();
+    await prisma.$disconnect();
+    redis?.disconnect();
+    console.log("Disconnected from Clickhouse.");
+  }
+}
+
+main();

packages/shared/clickhouse/scripts/up.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+# Load environment variables
+[ -f ../../.env ] && source ../../.env
+
+# Check if CLICKHOUSE_URL is configured
+if [ -z "${CLICKHOUSE_URL}" ]; then
+  echo "Info: CLICKHOUSE_URL not configured, skipping migration."
+  exit 0
+fi
+
+# Check if golang-migrate is installed
+if ! command -v migrate &> /dev/null
+then
+    echo "Error: golang-migrate is not installed or not in PATH."
+    echo "Please install golang-migrate via 'brew install golang-migrate' to run this script."
+    echo "Visit https://github.com/golang-migrate/migrate for more installation instructions."
+    exit 1
+fi
+
+# Construct the database URL
+if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
+    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&secure=true&skip_verify=true&x-migrations-table-engine=MergeTree"
+else
+    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-migrations-table-engine=MergeTree"
+fi
+
+# Execute the up command
+migrate -source file://clickhouse/migrations -database "$DATABASE_URL" up

packages/shared/package.json

@@ -6,7 +6,7 @@
   "main": "./dist/src/index.js",
   "types": "./dist/src/index.d.ts",
   "engines": {
-    "node": ">=20"
+    "node": "20"
   },
   "exports": {
     ".": {
@@ -17,9 +17,13 @@
       "import": "./dist/src/db.js",
       "require": "./dist/src/db.js"
     },
-    "./src/server/auth": {
-      "import": "./dist/src/server/auth.js",
-      "require": "./dist/src/server/auth.js"
+    "./src/server": {
+      "import": "./dist/src/server/index.js",
+      "require": "./dist/src/server/index.js"
+    },
+    "./src/server/auth/apiKeys": {
+      "import": "./dist/src/server/auth/apiKeys.js",
+      "require": "./dist/src/server/auth/apiKeys.js"
     },
     "./encryption": {
       "import": "./dist/src/encryption/index.js",
@@ -38,46 +42,84 @@
     "db:seed": "dotenv -e ../../.env -- npx prisma db seed",
     "db:generate": "dotenv -e ../../.env -- npx prisma generate",
     "db:seed:examples": "dotenv -e ../../.env -- npx prisma db seed -- --environment examples",
-    "db:seed:load": "dotenv -e ../../.env -- npx prisma db seed -- --environment load"
+    "db:seed:load": "dotenv -e ../../.env -- npx prisma db seed -- --environment load",
+    "ch:status": "dotenv -e ../../.env -- goose -dir './clickhouse/migrations/' status",
+    "ch:up": "bash clickhouse/scripts/up.sh",
+    "ch:down": "bash clickhouse/scripts/down.sh",
+    "ch:drop": "bash clickhouse/scripts/drop.sh",
+    "ch:reset": "pnpm run ch:down && pnpm run ch:up && pnpm run ch:seed",
+    "ch:seed": "dotenv -e ../../.env -- tsx clickhouse/scripts/seed.ts",
+    "load:setup": "dotenv -e ../../.env -- tsx scripts/load-seed.ts"
   },
   "prisma": {
     "seed": "ts-node -r tsconfig-paths/register -r dotenv/config --compiler-options {\"module\":\"CommonJS\"} prisma/seed.ts"
   },
   "dependencies": {
-    "@langchain/anthropic": "^0.1.21",
-    "@langchain/core": "^0.1.61",
-    "@langchain/openai": "^0.0.33",
-    "@prisma/client": "^5.13.0",
+    "@anthropic-ai/tokenizer": "^0.0.4",
+    "@aws-sdk/client-cloudwatch": "^3.675.0",
+    "@aws-sdk/client-s3": "^3.675.0",
+    "@aws-sdk/lib-storage": "^3.675.0",
+    "@aws-sdk/s3-request-presigner": "^3.679.0",
+    "@clickhouse/client": "^1.4.0",
+    "@langchain/anthropic": "^0.3.1",
+    "@langchain/aws": "^0.1.0",
+    "@langchain/core": "^0.3.9",
+    "@langchain/openai": "^0.3.0",
+    "@opentelemetry/api": ">=1.0.0 <1.10.0",
+    "@prisma/client": "^5.20.0",
+    "@react-email/components": "^0.0.19",
+    "@react-email/render": "^0.0.15",
     "@types/bcryptjs": "^2.4.6",
+    "axios": "^1.7.7",
     "bcryptjs": "^2.4.3",
-    "kysely": "^0.27.3",
-    "langchain": "^0.1.36",
+    "bullmq": "^5.12.10",
+    "dd-trace": "^5.23.1",
+    "decimal.js": "^10.4.3",
+    "exponential-backoff": "^3.1.1",
+    "ioredis": "^5.4.1",
+    "kysely": "^0.27.4",
+    "langchain": "^0.3.2",
     "lodash": "^4.17.21",
+    "next-auth": "^4.24.7",
+    "nodemailer": "^6.9.15",
     "prisma-extension-kysely": "^2.1.0",
-    "zod": "^3.22.4",
-    "zod-to-json-schema": "^3.22.5"
+    "uuid": "^9.0.1",
+    "winston": "^3.15.0",
+    "zod": "^3.23.8",
+    "zod-to-json-schema": "^3.23.5"
   },
   "devDependencies": {
-    "@repo/eslint-config": "*",
-    "@repo/typescript-config": "*",
-    "@types/lodash": "^4.17.4",
+    "@repo/eslint-config": "workspace:*",
+    "@repo/typescript-config": "workspace:*",
+    "@types/lodash": "^4.17.10",
     "@types/node": "^20.11.29",
-    "@types/pg": "^8.11.6",
+    "@types/nodemailer": "^6.4.16",
+    "@types/pg": "^8.11.10",
     "@types/uuid": "^9.0.8",
     "@typescript-eslint/parser": "^7.12.0",
     "eslint": "^8.57.0",
     "eslint-config-prettier": "^9.1.0",
     "eslint-config-standard": "^17.1.0",
     "eslint-plugin-prettier": "^5.1.3",
-    "kysely-codegen": "^0.11.0",
-    "nodemon": "^3.0.3",
-    "prettier": "^3.2.5",
-    "prisma": "^5.13.0",
+    "kysely-codegen": "^0.16.8",
+    "nodemon": "^3.1.7",
+    "prettier": "^3.3.3",
+    "prisma": "^5.20.0",
     "prisma-erd-generator": "^1.11.2",
     "prisma-kysely": "^1.8.0",
     "ts-node": "^10.9.2",
     "tsc-watch": "^6.2.0",
+    "tsx": "^4.19.1",
     "typescript": "^5.4.5",
-    "vitest": "^1.5.3"
+    "vitest": "^2.1.2"
+  },
+  "peerDependencies": {
+    "@types/react": "~18.2.79",
+    "react": "~18.2.0"
+  },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.0"
+    }
   }
 }

packages/shared/prettierrc.json

@@ -1,4 +0,0 @@
-{
-  "trailingComma": "es5",
-  "printWidth": 120
-}

packages/shared/prisma/generated/types.ts

@@ -4,13 +4,14 @@ export type Generated<T> = T extends ColumnType<infer S, infer I, infer U>
   : ColumnType<T, T | undefined, T>;
 export type Timestamp = ColumnType<Date, Date | string, Date | string>;
 
-export const ProjectRole = {
+export const Role = {
     OWNER: "OWNER",
     ADMIN: "ADMIN",
     MEMBER: "MEMBER",
-    VIEWER: "VIEWER"
+    VIEWER: "VIEWER",
+    NONE: "NONE"
 } as const;
-export type ProjectRole = (typeof ProjectRole)[keyof typeof ProjectRole];
+export type Role = (typeof Role)[keyof typeof Role];
 export const ObservationType = {
     SPAN: "SPAN",
     EVENT: "EVENT",
@@ -36,11 +37,28 @@ export const ScoreDataType = {
     BOOLEAN: "BOOLEAN"
 } as const;
 export type ScoreDataType = (typeof ScoreDataType)[keyof typeof ScoreDataType];
+export const AnnotationQueueStatus = {
+    PENDING: "PENDING",
+    COMPLETED: "COMPLETED"
+} as const;
+export type AnnotationQueueStatus = (typeof AnnotationQueueStatus)[keyof typeof AnnotationQueueStatus];
+export const AnnotationQueueObjectType = {
+    TRACE: "TRACE",
+    OBSERVATION: "OBSERVATION"
+} as const;
+export type AnnotationQueueObjectType = (typeof AnnotationQueueObjectType)[keyof typeof AnnotationQueueObjectType];
 export const DatasetStatus = {
     ACTIVE: "ACTIVE",
     ARCHIVED: "ARCHIVED"
 } as const;
 export type DatasetStatus = (typeof DatasetStatus)[keyof typeof DatasetStatus];
+export const CommentObjectType = {
+    TRACE: "TRACE",
+    OBSERVATION: "OBSERVATION",
+    SESSION: "SESSION",
+    PROMPT: "PROMPT"
+} as const;
+export type CommentObjectType = (typeof CommentObjectType)[keyof typeof CommentObjectType];
 export const JobType = {
     EVAL: "EVAL"
 } as const;
@@ -72,6 +90,31 @@ export type Account = {
     scope: string | null;
     id_token: string | null;
     session_state: string | null;
+    refresh_token_expires_in: number | null;
+    created_at: number | null;
+};
+export type AnnotationQueue = {
+    id: string;
+    name: string;
+    description: string | null;
+    score_config_ids: Generated<string[]>;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+};
+export type AnnotationQueueItem = {
+    id: string;
+    queue_id: string;
+    object_id: string;
+    object_type: AnnotationQueueObjectType;
+    status: Generated<AnnotationQueueStatus>;
+    locked_at: Timestamp | null;
+    locked_by_user_id: string | null;
+    annotator_user_id: string | null;
+    completed_at: Timestamp | null;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
 };
 export type ApiKey = {
     id: string;
@@ -90,14 +133,53 @@ export type AuditLog = {
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
     user_id: string;
-    project_id: string;
-    user_project_role: ProjectRole;
+    org_id: string;
+    user_org_role: string;
+    project_id: string | null;
+    user_project_role: string | null;
     resource_type: string;
     resource_id: string;
     action: string;
     before: string | null;
     after: string | null;
 };
+export type BackgroundMigration = {
+    id: string;
+    name: string;
+    script: string;
+    args: unknown;
+    state: Generated<unknown>;
+    finished_at: Timestamp | null;
+    failed_at: Timestamp | null;
+    failed_reason: string | null;
+    worker_id: string | null;
+    locked_at: Timestamp | null;
+};
+export type BatchExport = {
+    id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    project_id: string;
+    user_id: string;
+    finished_at: Timestamp | null;
+    expires_at: Timestamp | null;
+    name: string;
+    status: string;
+    query: unknown;
+    format: string;
+    url: string | null;
+    log: string | null;
+};
+export type Comment = {
+    id: string;
+    project_id: string;
+    object_type: CommentObjectType;
+    object_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    content: string;
+    author_user_id: string | null;
+};
 export type CronJobs = {
     name: string;
     last_run: Timestamp | null;
@@ -106,15 +188,16 @@ export type CronJobs = {
 };
 export type Dataset = {
     id: string;
+    project_id: string;
     name: string;
     description: string | null;
     metadata: unknown | null;
-    project_id: string;
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
 };
 export type DatasetItem = {
     id: string;
+    project_id: string;
     status: Generated<DatasetStatus>;
     input: unknown | null;
     expected_output: unknown | null;
@@ -127,6 +210,7 @@ export type DatasetItem = {
 };
 export type DatasetRunItems = {
     id: string;
+    project_id: string;
     dataset_run_id: string;
     dataset_item_id: string;
     trace_id: string;
@@ -136,6 +220,7 @@ export type DatasetRunItems = {
 };
 export type DatasetRuns = {
     id: string;
+    project_id: string;
     name: string;
     description: string | null;
     metadata: unknown | null;
@@ -152,6 +237,7 @@ export type EvalTemplate = {
     version: number;
     prompt: string;
     model: string;
+    provider: string;
     model_params: unknown;
     vars: Generated<string[]>;
     output_schema: unknown;
@@ -199,16 +285,37 @@ export type LlmApiKeys = {
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
     provider: string;
+    adapter: string;
     display_secret_key: string;
     secret_key: string;
+    base_url: string | null;
+    custom_models: Generated<string[]>;
+    with_default_models: Generated<boolean>;
+    config: unknown | null;
     project_id: string;
 };
+export type Media = {
+    id: string;
+    sha_256_hash: string;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    uploaded_at: Timestamp | null;
+    upload_http_status: number | null;
+    upload_http_error: string | null;
+    bucket_path: string;
+    bucket_name: string;
+    content_type: string;
+    content_length: string;
+};
 export type MembershipInvitation = {
     id: string;
     email: string;
-    role: ProjectRole;
-    project_id: string;
-    sender_id: string | null;
+    org_id: string;
+    org_role: Role;
+    project_id: string | null;
+    project_role: Role | null;
+    invited_by_user_id: string | null;
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
 };
@@ -223,7 +330,7 @@ export type Model = {
     input_price: string | null;
     output_price: string | null;
     total_price: string | null;
-    unit: string;
+    unit: string | null;
     tokenizer_id: string | null;
     tokenizer_config: unknown | null;
 };
@@ -244,6 +351,7 @@ export type Observation = {
     updated_at: Generated<Timestamp>;
     model: string | null;
     internal_model: string | null;
+    internal_model_id: string | null;
     modelParameters: unknown | null;
     input: unknown | null;
     output: unknown | null;
@@ -254,15 +362,28 @@ export type Observation = {
     input_cost: string | null;
     output_cost: string | null;
     total_cost: string | null;
+    calculated_input_cost: string | null;
+    calculated_output_cost: string | null;
+    calculated_total_cost: string | null;
     completion_start_time: Timestamp | null;
     prompt_id: string | null;
 };
+export type ObservationMedia = {
+    id: string;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    media_id: string;
+    trace_id: string;
+    observation_id: string;
+    field: string;
+};
 export type ObservationView = {
     id: string;
     trace_id: string | null;
     project_id: string;
     type: ObservationType;
-    start_time: Generated<Timestamp>;
+    start_time: Timestamp;
     end_time: Timestamp | null;
     name: string | null;
     metadata: unknown | null;
@@ -270,7 +391,8 @@ export type ObservationView = {
     level: Generated<ObservationLevel>;
     status_message: string | null;
     version: string | null;
-    created_at: Generated<Timestamp>;
+    created_at: Timestamp;
+    updated_at: Timestamp;
     model: string | null;
     modelParameters: unknown | null;
     input: unknown | null;
@@ -281,6 +403,8 @@ export type ObservationView = {
     unit: string | null;
     completion_start_time: Timestamp | null;
     prompt_id: string | null;
+    prompt_name: string | null;
+    prompt_version: number | null;
     model_id: string | null;
     input_price: string | null;
     output_price: string | null;
@@ -291,6 +415,21 @@ export type ObservationView = {
     latency: number | null;
     time_to_first_token: number | null;
 };
+export type Organization = {
+    id: string;
+    name: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    cloud_config: unknown | null;
+};
+export type OrganizationMembership = {
+    id: string;
+    org_id: string;
+    user_id: string;
+    role: Role;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+};
 export type PosthogIntegration = {
     project_id: string;
     encrypted_posthog_api_key: string;
@@ -299,17 +438,26 @@ export type PosthogIntegration = {
     enabled: boolean;
     created_at: Generated<Timestamp>;
 };
-export type Project = {
+export type Price = {
     id: string;
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
+    model_id: string;
+    usage_type: string;
+    price: string;
+};
+export type Project = {
+    id: string;
+    org_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
     name: string;
-    cloud_config: unknown | null;
 };
 export type ProjectMembership = {
+    org_membership_id: string;
     project_id: string;
     user_id: string;
-    role: ProjectRole;
+    role: Role;
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
 };
@@ -333,7 +481,7 @@ export type Score = {
     timestamp: Generated<Timestamp>;
     project_id: string;
     name: string;
-    value: number;
+    value: number | null;
     source: ScoreSource;
     author_user_id: string | null;
     comment: string | null;
@@ -341,6 +489,7 @@ export type Score = {
     observation_id: string | null;
     config_id: string | null;
     string_value: string | null;
+    queue_id: string | null;
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
     data_type: Generated<ScoreDataType>;
@@ -390,6 +539,15 @@ export type Trace = {
     created_at: Generated<Timestamp>;
     updated_at: Generated<Timestamp>;
 };
+export type TraceMedia = {
+    id: string;
+    project_id: string;
+    created_at: Generated<Timestamp>;
+    updated_at: Generated<Timestamp>;
+    media_id: string;
+    trace_id: string;
+    field: string;
+};
 export type TraceSession = {
     id: string;
     created_at: Generated<Timestamp>;
@@ -414,6 +572,8 @@ export type TraceView = {
     input: unknown | null;
     output: unknown | null;
     session_id: string | null;
+    created_at: Timestamp;
+    updated_at: Timestamp;
     duration: number | null;
 };
 export type User = {
@@ -435,8 +595,13 @@ export type VerificationToken = {
 };
 export type DB = {
     Account: Account;
+    annotation_queue_items: AnnotationQueueItem;
+    annotation_queues: AnnotationQueue;
     api_keys: ApiKey;
     audit_logs: AuditLog;
+    background_migrations: BackgroundMigration;
+    batch_exports: BatchExport;
+    comments: Comment;
     cron_jobs: CronJobs;
     dataset_items: DatasetItem;
     dataset_run_items: DatasetRunItems;
@@ -447,11 +612,16 @@ export type DB = {
     job_configurations: JobConfiguration;
     job_executions: JobExecution;
     llm_api_keys: LlmApiKeys;
+    media: Media;
     membership_invitations: MembershipInvitation;
     models: Model;
+    observation_media: ObservationMedia;
     observations: Observation;
     observations_view: ObservationView;
+    organization_memberships: OrganizationMembership;
+    organizations: Organization;
     posthog_integrations: PosthogIntegration;
+    prices: Price;
     project_memberships: ProjectMembership;
     projects: Project;
     prompts: Prompt;
@@ -459,6 +629,7 @@ export type DB = {
     scores: Score;
     Session: Session;
     sso_configs: SsoConfig;
+    trace_media: TraceMedia;
     trace_sessions: TraceSession;
     traces: Trace;
     traces_view: TraceView;

packages/shared/prisma/migrations/20240530212419_model_price_anthropic_via_google_vertex/migration.sql

@@ -1,7 +0,0 @@
--- Google Vertex uses @ to separate model name and version
-
-UPDATE "public"."models" SET "match_pattern" = '(?i)^(claude-3-haiku(-|@)?20240307)$' WHERE "id" = 'cltr0w45b000008k1407o9qv1';
-
-UPDATE "public"."models" SET "match_pattern" = '(?i)^(claude-3-opus(-|@)?20240229)$' WHERE "id" = 'cltgy0iuw000008le3vod1hhy';
-
-UPDATE "public"."models" SET "match_pattern" = '(?i)^(claude-3-sonnet(-|@)?20240229)$' WHERE "id" = 'cltgy0pp6000108le56se7bl3';

packages/shared/prisma/migrations/20240606090858_pricings_add_latest_gemini_models/migration.sql

@@ -1,5 +0,0 @@
--- does not include pricing yet, will be added as soon as it is calculated at ingestion time
-
-INSERT INTO "public"."models" ("id", "model_name", "match_pattern", "unit") VALUES ('clx30djsn0000w9mzebiv41we', 'gemini-1.5-flash', '(?i)^(gemini-1.5-flash)(@[a-zA-Z0-9]+)?$', 'CHARACTERS');
-
-INSERT INTO "public"."models" ("id", "model_name", "match_pattern", "unit") VALUES ('clx30hkrx0000w9mz7lqi0ial', 'gemini-1.5-pro', '(?i)^(gemini-1.5-pro)(@[a-zA-Z0-9]+)?$', 'CHARACTERS');

packages/shared/prisma/migrations/20240607090858_pricings_add_latest_gemini_models/migration.sql

@@ -0,0 +1,8 @@
+-- does not include pricing yet, will be added as soon as it is calculated at ingestion time
+
+-- remove model if added by faulty migration, context: https://github.com/langfuse/langfuse/issues/2266
+DELETE FROM models WHERE id in ('clx30djsn0000w9mzebiv41we', 'clx30hkrx0000w9mz7lqi0ial');
+
+INSERT INTO "models" ("id", "model_name", "match_pattern", "unit") VALUES ('clx30djsn0000w9mzebiv41we', 'gemini-1.5-flash', '(?i)^(gemini-1.5-flash)(@[a-zA-Z0-9]+)?$', 'CHARACTERS');
+
+INSERT INTO "models" ("id", "model_name", "match_pattern", "unit") VALUES ('clx30hkrx0000w9mz7lqi0ial', 'gemini-1.5-pro', '(?i)^(gemini-1.5-pro)(@[a-zA-Z0-9]+)?$', 'CHARACTERS');

packages/shared/prisma/migrations/20240607212419_model_price_anthropic_via_google_vertex/migration.sql

@@ -0,0 +1,7 @@
+-- Google Vertex uses @ to separate model name and version
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-haiku(-|@)?20240307)$' WHERE "id" = 'cltr0w45b000008k1407o9qv1';
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-opus(-|@)?20240229)$' WHERE "id" = 'cltgy0iuw000008le3vod1hhy';
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-sonnet(-|@)?20240229)$' WHERE "id" = 'cltgy0pp6000108le56se7bl3';

packages/shared/prisma/migrations/20240611105521_llm_api_keys_custom_endpoints/migration.sql

@@ -0,0 +1,24 @@
+BEGIN;
+
+  ALTER TABLE "llm_api_keys" 
+    ADD COLUMN "base_url" TEXT,
+    ADD COLUMN "adapter" TEXT,
+    ADD COLUMN "custom_models" TEXT[] NOT NULL DEFAULT '{}'::TEXT[],
+    ADD COLUMN "with_default_models" BOOLEAN NOT NULL DEFAULT true;
+
+  UPDATE "llm_api_keys"
+    SET "adapter" = "provider";
+
+  ALTER TABLE "llm_api_keys" 
+    ALTER COLUMN "adapter" SET NOT NULL;
+
+  ALTER TABLE "eval_templates"
+    ADD COLUMN "provider" TEXT;
+  
+  UPDATE "eval_templates"
+    SET "provider" = 'openai';
+  
+  ALTER TABLE "eval_templates"
+    ALTER COLUMN "provider" SET NOT NULL;
+
+COMMIT;

packages/shared/prisma/migrations/20240611113517_backfill_manual_score_configs/migration.sql

@@ -10,7 +10,7 @@ INSERT INTO score_configs (id,
 		max_value,
 		description)
 SELECT
-	gen_random_uuid () AS id,
+	md5(random()::text || clock_timestamp()::text || s.project_id::text)::uuid AS id,
 	s.project_id,
 	'manual-score',
 	'NUMERIC',
@@ -24,6 +24,7 @@ FROM ( SELECT DISTINCT
 		scores
 	WHERE
 		name = 'manual-score'
+		AND config_id IS NULL
 		AND source = 'ANNOTATION') s
 WHERE
 	NOT EXISTS (
@@ -47,4 +48,4 @@ FROM
 WHERE
 	scores.project_id = pc.project_id
 	AND scores.name = 'manual-score';
-COMMIT;
+COMMIT;

packages/shared/prisma/migrations/20240612101858_add_index_observations_project_id_prompt_id/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX CONCURRENTLY "observations_project_id_prompt_id_idx" ON "observations"("project_id", "prompt_id");

packages/shared/prisma/migrations/20240617094803_observations_remove_prompt_fk_constraint/migration.sql

@@ -0,0 +1,2 @@
+-- DropForeignKey
+ALTER TABLE "observations" DROP CONSTRAINT "observations_prompt_id_fkey";

packages/shared/prisma/migrations/20240618134129_add_batch_exports_table/migration.sql

@@ -0,0 +1,27 @@
+-- CreateTable
+CREATE TABLE "batch_exports" (
+    "id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "project_id" TEXT NOT NULL,
+    "user_id" TEXT NOT NULL,
+    "finished_at" TIMESTAMP(3),
+    "expires_at" TIMESTAMP(3),
+    "name" TEXT NOT NULL,
+    "status" TEXT NOT NULL,
+    "query" JSONB NOT NULL,
+    "format" TEXT NOT NULL,
+    "url" TEXT,
+    "log" TEXT,
+
+    CONSTRAINT "batch_exports_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "batch_exports_project_id_user_id_idx" ON "batch_exports"("project_id", "user_id");
+
+-- CreateIndex
+CREATE INDEX "batch_exports_status_idx" ON "batch_exports"("status");
+
+-- AddForeignKey
+ALTER TABLE "batch_exports" ADD CONSTRAINT "batch_exports_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20240618164950_drop_observations_parent_observation_id_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "observations_parent_observation_id_idx";

packages/shared/prisma/migrations/20240618164951_drop_observations_updated_at_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "observations_updated_at_idx";

packages/shared/prisma/migrations/20240618164952_drop_scores_updated_at_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "scores_updated_at_idx";

packages/shared/prisma/migrations/20240618164953_drop_traces_external_id_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "traces_external_id_idx";

packages/shared/prisma/migrations/20240618164954_drop_traces_release_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "traces_release_idx";

packages/shared/prisma/migrations/20240618164955_drop_traces_updated_at_idx/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY IF EXISTS "traces_updated_at_idx";

packages/shared/prisma/migrations/20240618164956_create_traces_project_id_timestamp_idx/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE INDEX CONCURRENTLY "traces_project_id_timestamp_idx" ON "traces"("project_id", "timestamp");

packages/shared/prisma/migrations/20240624133412_models_add_anthropic_3_5_sonnet/migration.sql

@@ -0,0 +1,15 @@
+INSERT INTO models (
+  id,
+  project_id,
+  model_name,
+  match_pattern,
+  start_date,
+  input_price,
+  output_price,
+  total_price,
+  unit,
+  tokenizer_id
+)
+VALUES
+  -- add 3.5 sonnet model
+  ('clxt0n0m60000pumz1j5b7zsf', NULL, 'claude-3-5-sonnet-20240620', '(?i)^(claude-3-5-sonnet(-|@)?20240620)$', NULL, 0.000003, 0.000015, NULL, 'TOKENS', 'claude')

packages/shared/prisma/migrations/20240625103957_observations_add_calculated_cost_columns/migration.sql

@@ -0,0 +1,5 @@
+-- AlterTable
+ALTER TABLE "observations" ADD COLUMN     "calculated_input_cost" DECIMAL(65,30),
+ADD COLUMN     "calculated_output_cost" DECIMAL(65,30),
+ADD COLUMN     "calculated_total_cost" DECIMAL(65,30),
+ADD COLUMN     "internal_model_id" TEXT;

packages/shared/prisma/migrations/20240625103958_fix_model_match_gpt4_vision/migration.sql

@@ -0,0 +1,17 @@
+/*
+Previously, the pattern did not allow for model specifications like "1106" or any other 4-digit block. 
+This led to missing models on the generation-update call where the exact model name that was used was provided (including the 4-digit block).
+The new pattern allows for:
+
+- "gpt-4-vision-preview" as set on generation-create
+- "gpt-4-1106-vision-preview" as set on generation-update
+
+*/
+
+UPDATE
+	"models"
+SET
+	"match_pattern" = '(?i)^(gpt-4(-\d{4})?-vision-preview)$'
+WHERE
+	"id" = 'clrkvx5gp000108juaogs54ea'
+	AND "model_name" = 'gpt-4-turbo-vision';

packages/shared/prisma/migrations/20240703214747_models_anthropic_aws_bedrock/migration.sql

@@ -0,0 +1,9 @@
+-- Add AWS Bedrock model names for Anthropic models
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-haiku-20240307|anthropic\.claude-3-haiku-20240307-v1:0|claude-3-haiku@20240307)$' WHERE "id" = 'cltr0w45b000008k1407o9qv1';
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-sonnet-20240229|anthropic\.claude-3-sonnet-20240229-v1:0|claude-3-sonnet@20240229)$' WHERE "id" = 'cltgy0pp6000108le56se7bl3';
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-opus-20240229|anthropic\.claude-3-opus-20240229-v1:0|claude-3-opus@20240229)$' WHERE "id" = 'cltgy0iuw000008le3vod1hhy';
+
+UPDATE "models" SET "match_pattern" = '(?i)^(claude-3-5-sonnet-20240620|anthropic\.claude-3-5-sonnet-20240620-v1:0|claude-3-5-sonnet@20240620)$' WHERE "id" = 'clxt0n0m60000pumz1j5b7zsf';

packages/shared/prisma/migrations/20240704103900_observations_view_read_from_calculated/migration.sql

@@ -0,0 +1,88 @@
+DROP VIEW IF EXISTS "observations_view"; -- Drop view as column was added in 20240528214726_add_cursor_new_columns_observations and update view must have same columns
+CREATE VIEW "observations_view" AS -- Specify the columns that should be returned in the view, as calculated columns are added but exist in the observations table already
+SELECT
+    o.id,
+    o.name,
+    o.start_time,
+    o.end_time,
+    o.parent_observation_id,
+    o.type,
+    o.trace_id,
+    o.metadata,
+    o.model,
+    o."modelParameters",
+    o.input,
+    o.output,
+    o.level,
+    o.status_message,
+    o.completion_start_time,
+    o.completion_tokens,
+    o.prompt_tokens,
+    o.total_tokens,
+    o.version,
+    o.project_id,
+    o.created_at,
+    o.unit,
+    o.prompt_id,
+    o.input_cost,
+    o.output_cost,
+    o.total_cost,
+    o.internal_model,
+    m.id AS "model_id",
+    m.start_date AS "model_start_date",
+    m.input_price,
+    m.output_price,
+    m.total_price,
+    m.tokenizer_config AS "tokenizer_config",
+    CASE 
+        WHEN o.calculated_input_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.prompt_tokens::decimal * m.input_price
+        ELSE
+            COALESCE(o.calculated_input_cost, o.input_cost)
+    END AS "calculated_input_cost",
+    CASE 
+        WHEN o.calculated_output_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.completion_tokens::decimal * m.output_price
+        ELSE
+            COALESCE(o.calculated_output_cost, o.output_cost)
+    END AS "calculated_output_cost",
+    CASE 
+        WHEN o.calculated_total_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            CASE 
+                WHEN m.total_price IS NOT NULL AND o.total_tokens IS NOT NULL THEN
+                    m.total_price * o.total_tokens
+                ELSE
+                    o.prompt_tokens::decimal * m.input_price + 
+                    o.completion_tokens::decimal * m.output_price
+            END
+        ELSE
+            COALESCE(o.calculated_total_cost, o.total_cost)
+    END AS "calculated_total_cost",
+    CASE WHEN o.end_time IS NULL THEN NULL ELSE (EXTRACT(EPOCH FROM o."end_time") - EXTRACT(EPOCH FROM o."start_time"))::double precision END AS "latency",
+    CASE WHEN o.completion_start_time IS NOT NULL AND o.start_time IS NOT NULL THEN EXTRACT(EPOCH FROM (completion_start_time - start_time))::double precision ELSE NULL END as "time_to_first_token"
+    
+FROM
+    observations o
+LEFT JOIN LATERAL (
+    SELECT
+        models.*
+    FROM
+        models
+    WHERE (models.project_id = o.project_id OR models.project_id IS NULL)
+    AND models.model_name = o.internal_model
+    AND (models.start_date < o.start_time OR models.start_date IS NULL)
+    AND o.unit::TEXT = models.unit
+    ORDER BY
+        models.project_id ASC, -- in postgres, NULLs are sorted last when ordering ASC
+        models.start_date DESC NULLS LAST -- now, NULLs are sorted last when ordering DESC as well
+    LIMIT 1
+) m ON TRUE
+
+
+-- requirements:
+-- 1. The view should return all columns from the observations table
+-- 2. The view should match with only one model for each observation if:
+--     a. The model has the same project_id as the observation, otherwise the model without project_id. 
+--     b. The model has the same model_name as the observation
+--     c. The model has a start_date that is less than the observation start_time, otherwise the model without start_date
+--     d. The model has the same unit as the observation

packages/shared/prisma/migrations/20240704103901_scores_make_value_optional/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "scores" ALTER COLUMN "value" DROP NOT NULL;

packages/shared/prisma/migrations/20240705152639_traces_view_add_created_at_updated_at/migration.sql

@@ -0,0 +1,20 @@
+-- Drop and create to be able to change columns, otherwise new t.* cols cannot be added
+
+DROP VIEW IF EXISTS traces_view;
+CREATE VIEW traces_view AS
+WITH observations_metrics AS (
+    SELECT
+        trace_id,
+        project_id,
+        EXTRACT(EPOCH FROM COALESCE(MAX(o.end_time), MAX(o.start_time))) - EXTRACT(EPOCH FROM MIN(o.start_time))::double precision AS duration
+    FROM
+        observations o
+    GROUP BY
+        project_id, trace_id
+)
+SELECT
+    t.*,
+    o.duration
+FROM
+    traces t
+    LEFT JOIN observations_metrics o ON t.id = o.trace_id and t.project_id = o.project_id

packages/shared/prisma/migrations/20240705154048_observation_view_add_created_at_updated_at/migration.sql

@@ -0,0 +1,89 @@
+DROP VIEW IF EXISTS "observations_view"; -- Drop view as column was added in 20240704103900_observations_view_read_from_calculated and update view must have same columns
+CREATE VIEW "observations_view" AS -- Specify the columns that should be returned in the view, as calculated columns are added but exist in the observations table already
+SELECT
+    o.id,
+    o.name,
+    o.start_time,
+    o.end_time,
+    o.parent_observation_id,
+    o.type,
+    o.trace_id,
+    o.metadata,
+    o.model,
+    o."modelParameters",
+    o.input,
+    o.output,
+    o.level,
+    o.status_message,
+    o.completion_start_time,
+    o.completion_tokens,
+    o.prompt_tokens,
+    o.total_tokens,
+    o.version,
+    o.project_id,
+    o.created_at,
+    o.updated_at,
+    o.unit,
+    o.prompt_id,
+    o.input_cost,
+    o.output_cost,
+    o.total_cost,
+    o.internal_model,
+    m.id AS "model_id",
+    m.start_date AS "model_start_date",
+    m.input_price,
+    m.output_price,
+    m.total_price,
+    m.tokenizer_config AS "tokenizer_config",
+    CASE 
+        WHEN o.calculated_input_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.prompt_tokens::decimal * m.input_price
+        ELSE
+            COALESCE(o.calculated_input_cost, o.input_cost)
+    END AS "calculated_input_cost",
+    CASE 
+        WHEN o.calculated_output_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.completion_tokens::decimal * m.output_price
+        ELSE
+            COALESCE(o.calculated_output_cost, o.output_cost)
+    END AS "calculated_output_cost",
+    CASE 
+        WHEN o.calculated_total_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            CASE 
+                WHEN m.total_price IS NOT NULL AND o.total_tokens IS NOT NULL THEN
+                    m.total_price * o.total_tokens
+                ELSE
+                    o.prompt_tokens::decimal * m.input_price + 
+                    o.completion_tokens::decimal * m.output_price
+            END
+        ELSE
+            COALESCE(o.calculated_total_cost, o.total_cost)
+    END AS "calculated_total_cost",
+    CASE WHEN o.end_time IS NULL THEN NULL ELSE (EXTRACT(EPOCH FROM o."end_time") - EXTRACT(EPOCH FROM o."start_time"))::double precision END AS "latency",
+    CASE WHEN o.completion_start_time IS NOT NULL AND o.start_time IS NOT NULL THEN EXTRACT(EPOCH FROM (completion_start_time - start_time))::double precision ELSE NULL END as "time_to_first_token"
+    
+FROM
+    observations o
+LEFT JOIN LATERAL (
+    SELECT
+        models.*
+    FROM
+        models
+    WHERE (models.project_id = o.project_id OR models.project_id IS NULL)
+    AND models.model_name = o.internal_model
+    AND (models.start_date < o.start_time OR models.start_date IS NULL)
+    AND o.unit::TEXT = models.unit
+    ORDER BY
+        models.project_id ASC, -- in postgres, NULLs are sorted last when ordering ASC
+        models.start_date DESC NULLS LAST -- now, NULLs are sorted last when ordering DESC as well
+    LIMIT 1
+) m ON TRUE
+
+
+-- requirements:
+-- 1. The view should return all columns from the observations table
+-- 2. The view should match with only one model for each observation if:
+--     a. The model has the same project_id as the observation, otherwise the model without project_id. 
+--     b. The model has the same model_name as the observation
+--     c. The model has a start_date that is less than the observation start_time, otherwise the model without start_date
+--     d. The model has the same unit as the observation

packages/shared/prisma/migrations/20240710114043_score_configs_drop_empty_categories_array_for_numeric_scores/migration.sql

@@ -0,0 +1,6 @@
+-- Migration script to update score_configs entries
+-- Set categories to NULL where data_type is 'NUMERIC' and categories is an empty array
+
+UPDATE score_configs
+SET categories = NULL
+WHERE data_type = 'NUMERIC' AND categories IS NOT NULL;

packages/shared/prisma/migrations/20240710114044_add_pricing_gpt4o_mini/migration.sql

@@ -0,0 +1,20 @@
+INSERT INTO models (
+  id,
+  project_id,
+  model_name,
+  match_pattern,
+  start_date,
+  input_price,
+  output_price,
+  total_price,
+  unit,
+  tokenizer_id,
+  tokenizer_config
+)
+VALUES
+  -- gpt-4o-mini
+  ('clyrjp56f0000t0mzapoocd7u', NULL, 'gpt-4o-mini', '(?i)^(gpt-4o-mini)$', NULL, 0.00000015, 0.0000006, NULL, 'TOKENS', 'openai', '{ "tokensPerMessage": 3, "tokensPerName": 1, "tokenizerModel": "gpt-4o" }'),
+  
+  -- gpt-4o-mini-2024-07-18
+  ('clyrjpbe20000t0mzcbwc42rg', NULL, 'gpt-4o-mini-2024-07-18', '(?i)^(gpt-4o-mini-2024-07-18)$', NULL, 0.00000015, 0.0000006, NULL, 'TOKENS', 'openai', '{ "tokensPerMessage": 3, "tokensPerName": 1, "tokenizerModel": "gpt-4o" }')
+  

packages/shared/prisma/migrations/20240718004923_datasets_tables_add_projectid_composite_key/migration.sql

@@ -0,0 +1,68 @@
+-- Add project_id to datasets, dataset_items, dataset_runs, dataset_run_items
+ALTER TABLE "dataset_items" 
+ADD COLUMN "project_id" TEXT;
+
+ALTER TABLE "dataset_run_items" 
+ADD COLUMN "project_id" TEXT;
+
+ALTER TABLE "dataset_runs" 
+ADD COLUMN "project_id" TEXT;
+
+-- Backfill project_id for dataset_items
+UPDATE dataset_items
+SET project_id = datasets.project_id
+FROM datasets
+WHERE dataset_items.dataset_id = datasets.id;
+
+-- Backfill project_id for dataset_runs
+UPDATE dataset_runs
+SET project_id = datasets.project_id
+FROM datasets
+WHERE dataset_runs.dataset_id = datasets.id;
+
+-- Backfill project_id for dataset_run_items
+UPDATE dataset_run_items
+SET project_id = dataset_runs.project_id
+FROM dataset_runs
+WHERE dataset_run_items.dataset_run_id = dataset_runs.id;
+
+-- Drop the old foreign keys
+ALTER TABLE "dataset_run_items" 
+DROP CONSTRAINT "dataset_run_items_dataset_item_id_fkey",
+DROP CONSTRAINT "dataset_run_items_dataset_run_id_fkey";
+
+ALTER TABLE "dataset_items" 
+DROP CONSTRAINT "dataset_items_dataset_id_fkey";
+
+ALTER TABLE "dataset_runs" 
+DROP CONSTRAINT "dataset_runs_dataset_id_fkey";
+
+-- Now alter the columns to NOT NULL and update primary keys
+ALTER TABLE "datasets" 
+DROP CONSTRAINT "datasets_pkey",
+ADD CONSTRAINT "datasets_pkey" PRIMARY KEY ("id", "project_id");
+
+ALTER TABLE "dataset_items" 
+ALTER COLUMN "project_id" SET NOT NULL,
+DROP CONSTRAINT "dataset_items_pkey",
+ADD CONSTRAINT "dataset_items_pkey" PRIMARY KEY ("id", "project_id");
+
+ALTER TABLE "dataset_runs" 
+ALTER COLUMN "project_id" SET NOT NULL,
+DROP CONSTRAINT "dataset_runs_pkey",
+ADD CONSTRAINT "dataset_runs_pkey" PRIMARY KEY ("id", "project_id");
+
+ALTER TABLE "dataset_run_items" 
+ALTER COLUMN "project_id" SET NOT NULL,
+DROP CONSTRAINT "dataset_run_items_pkey",
+ADD CONSTRAINT "dataset_run_items_pkey" PRIMARY KEY ("id", "project_id");
+
+
+-- Add new foreign keys
+ALTER TABLE "dataset_items" ADD CONSTRAINT "dataset_items_dataset_id_project_id_fkey" FOREIGN KEY ("dataset_id", "project_id") REFERENCES "datasets"("id", "project_id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+ALTER TABLE "dataset_runs" ADD CONSTRAINT "dataset_runs_dataset_id_project_id_fkey" FOREIGN KEY ("dataset_id", "project_id") REFERENCES "datasets"("id", "project_id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+ALTER TABLE "dataset_run_items" ADD CONSTRAINT "dataset_run_items_dataset_run_id_project_id_fkey" FOREIGN KEY ("dataset_run_id", "project_id") REFERENCES "dataset_runs"("id", "project_id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+ALTER TABLE "dataset_run_items" ADD CONSTRAINT "dataset_run_items_dataset_item_id_project_id_fkey" FOREIGN KEY ("dataset_item_id", "project_id") REFERENCES "dataset_items"("id", "project_id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20240718011733_dataset_runs_add_unique_dataset_id_project_id_name copy/migration.sql

@@ -0,0 +1,2 @@
+-- CreateIndex
+CREATE UNIQUE INDEX CONCURRENTLY "dataset_runs_dataset_id_project_id_name_key" ON "dataset_runs"("dataset_id", "project_id", "name");

packages/shared/prisma/migrations/20240718011734_dataset_runs_drop_unique_dataset_id_name/migration.sql

@@ -0,0 +1,2 @@
+-- DropIndex
+DROP INDEX CONCURRENTLY "dataset_runs_dataset_id_name_key";

packages/shared/prisma/migrations/20240718011735_observation_view_add_prompt_name_and_version/migration.sql

@@ -0,0 +1,100 @@
+DROP VIEW IF EXISTS "observations_view"; -- Drop view as column was added in 20240705154048_observation_view_add_created_at_updated_at and update view must have same columns
+CREATE VIEW "observations_view" AS -- Specify the columns that should be returned in the view, as calculated columns are added but exist in the observations table already
+SELECT
+    o.id,
+    o.name,
+    o.start_time,
+    o.end_time,
+    o.parent_observation_id,
+    o.type,
+    o.trace_id,
+    o.metadata,
+    o.model,
+    o."modelParameters",
+    o.input,
+    o.output,
+    o.level,
+    o.status_message,
+    o.completion_start_time,
+    o.completion_tokens,
+    o.prompt_tokens,
+    o.total_tokens,
+    o.version,
+    o.project_id,
+    o.created_at,
+    o.updated_at,
+    o.unit,
+    o.prompt_id,
+    p.name as prompt_name,         -- added in this change
+    p.version as prompt_version,   -- added in this change
+    o.input_cost,
+    o.output_cost,
+    o.total_cost,
+    o.internal_model,
+    m.id AS "model_id",
+    m.start_date AS "model_start_date",
+    m.input_price,
+    m.output_price,
+    m.total_price,
+    m.tokenizer_config AS "tokenizer_config",
+    CASE 
+        WHEN o.calculated_input_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.prompt_tokens::decimal * m.input_price
+        ELSE
+            COALESCE(o.calculated_input_cost, o.input_cost)
+    END AS "calculated_input_cost",
+    CASE 
+        WHEN o.calculated_output_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            o.completion_tokens::decimal * m.output_price
+        ELSE
+            COALESCE(o.calculated_output_cost, o.output_cost)
+    END AS "calculated_output_cost",
+    CASE 
+        WHEN o.calculated_total_cost IS NULL AND o.input_cost IS NULL AND o.output_cost IS NULL AND o.total_cost IS NULL THEN
+            CASE 
+                WHEN m.total_price IS NOT NULL AND o.total_tokens IS NOT NULL THEN
+                    m.total_price * o.total_tokens
+                ELSE
+                    o.prompt_tokens::decimal * m.input_price + 
+                    o.completion_tokens::decimal * m.output_price
+            END
+        ELSE
+            COALESCE(o.calculated_total_cost, o.total_cost)
+    END AS "calculated_total_cost",
+    CASE WHEN o.end_time IS NULL THEN NULL ELSE (EXTRACT(EPOCH FROM o."end_time") - EXTRACT(EPOCH FROM o."start_time"))::double precision END AS "latency",
+    CASE WHEN o.completion_start_time IS NOT NULL AND o.start_time IS NOT NULL THEN EXTRACT(EPOCH FROM (completion_start_time - start_time))::double precision ELSE NULL END as "time_to_first_token"
+    
+FROM
+    observations o
+LEFT JOIN LATERAL (
+    SELECT
+        models.*
+    FROM
+        models
+    WHERE (models.project_id = o.project_id OR models.project_id IS NULL)
+    AND models.model_name = o.internal_model
+    AND (models.start_date < o.start_time OR models.start_date IS NULL)
+    AND o.unit::TEXT = models.unit
+    ORDER BY
+        models.project_id ASC, -- in postgres, NULLs are sorted last when ordering ASC
+        models.start_date DESC NULLS LAST -- now, NULLs are sorted last when ordering DESC as well
+    LIMIT 1
+) m ON TRUE
+LEFT JOIN LATERAL (
+    SELECT
+        prompts.*
+    FROM
+        prompts
+    WHERE prompts.id = o.prompt_id
+    AND prompts.project_id = o.project_id
+    LIMIT 1
+) p ON TRUE
+
+
+-- requirements:
+-- 1. The view should return all columns from the observations table
+-- 2. The view should match with only one model for each observation if:
+--     a. The model has the same project_id as the observation, otherwise the model without project_id. 
+--     b. The model has the same model_name as the observation
+--     c. The model has a start_date that is less than the observation start_time, otherwise the model without start_date
+--     d. The model has the same unit as the observation

packages/shared/prisma/migrations/20240807111358_models_add_openai_gpt_4o_2024_08_06/migration.sql

@@ -0,0 +1,18 @@
+
+INSERT INTO models (
+  id,
+  project_id,
+  model_name,
+  match_pattern,
+  start_date,
+  input_price,
+  output_price,
+  total_price,
+  unit,
+  tokenizer_id,
+  tokenizer_config
+)
+VALUES
+  -- gpt-4o-2024-08-06
+  ('clzjr85f70000ymmzg7hqffra', NULL, 'gpt-4o-2024-08-06', '(?i)^(gpt-4o-2024-08-06)$', NULL, 0.0000025, 0.000010, NULL, 'TOKENS', 'openai', '{ "tokensPerMessage": 3, "tokensPerName": 1, "tokenizerModel": "gpt-4o" }')
+  

packages/shared/prisma/migrations/20240807111359_add_organizations_main_migration/migration.sql

@@ -0,0 +1,164 @@
+-- Table ORGANIZATIONS
+-- Create empty table ORGANIZATIONS
+CREATE TABLE "organizations" (
+    "id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "cloud_config" JSONB,
+
+    CONSTRAINT "organizations_pkey" PRIMARY KEY ("id")
+);
+-- Backfill table ORGANIZATIONS: create a new organization for each project, move cloudConfig, and set the org_id on the project to project_id prefixed with 'o'
+INSERT INTO "organizations" ("id", "name", "cloud_config", "created_at")
+SELECT
+  CONCAT('o', "id") as "id", -- This mapping is used in other migration steps as well, keep it consistent
+  "name",
+  "cloud_config",
+  "created_at"
+FROM "projects";
+-- Drop column cloud_config from projects as it's now on organization level
+ALTER TABLE "projects" DROP COLUMN "cloud_config";
+
+
+-- PROJECT.ORG_ID
+-- Add org_id to projects
+ALTER TABLE "projects" ADD COLUMN "org_id" TEXT;
+-- Backfill: org_id on projects, set it to project_id prefixed with 'o'
+UPDATE "projects"
+SET "org_id" = CONCAT('o', "id");
+-- Set not null after backfill
+ALTER TABLE "projects" ALTER COLUMN "org_id" SET NOT NULL;
+-- AddForeignKey
+ALTER TABLE "projects" ADD CONSTRAINT "projects_org_id_fkey" FOREIGN KEY ("org_id") REFERENCES "organizations"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+-- CreateIndex
+CREATE INDEX "projects_org_id_idx" ON "projects"("org_id");
+
+
+-- ORGANIZATION MEMBERSHIPS
+-- Create UserRole ENUM
+CREATE TYPE "Role" AS ENUM ('OWNER', 'ADMIN', 'MEMBER', 'VIEWER', 'NONE');
+-- Create empty table
+CREATE TABLE "organization_memberships" (
+    "id" TEXT NOT NULL,
+    "org_id" TEXT NOT NULL,
+    "user_id" TEXT NOT NULL,
+    "role" "Role" NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "organization_memberships_pkey" PRIMARY KEY ("id")
+);
+-- Add indexes
+CREATE INDEX "organization_memberships_user_id_idx" ON "organization_memberships"("user_id");
+CREATE INDEX "organization_memberships_org_id_idx" ON "organization_memberships"("org_id");
+CREATE UNIQUE INDEX "organization_memberships_org_id_user_id_key" ON "organization_memberships"("org_id", "user_id");
+-- AddForeignKey
+ALTER TABLE "organization_memberships" ADD CONSTRAINT "organization_memberships_org_id_fkey" FOREIGN KEY ("org_id") REFERENCES "organizations"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+-- AddForeignKey
+ALTER TABLE "organization_memberships" ADD CONSTRAINT "organization_memberships_user_id_fkey" FOREIGN KEY ("user_id") REFERENCES "users"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+
+
+-- Migrate project memberships to organization memberships
+INSERT INTO "organization_memberships" ("id", "org_id", "user_id", "role", "created_at", "updated_at")
+SELECT
+  md5(random()::text || clock_timestamp()::text || project_id::text || user_id::text)::uuid AS "id",
+  CONCAT('o', "project_id") as "org_id",
+  "user_id",
+  "role"::text::"Role" as "role",
+  "created_at",
+  "updated_at"
+FROM "project_memberships";
+
+
+
+-- Delete all project memberships after migration to organization memberships
+DELETE FROM "project_memberships";
+
+-- Add org_membership_id to project_memberships, ok to be not null as it's a new column on a now empty table
+ALTER TABLE "project_memberships" ADD COLUMN     "org_membership_id" TEXT NOT NULL;
+-- Switch to new UserRole enum
+ALTER TABLE "project_memberships" DROP COLUMN "role",
+ADD COLUMN     "role" "Role" NOT NULL;
+-- AddForeignKey
+ALTER TABLE "project_memberships" ADD CONSTRAINT "project_memberships_org_membership_id_fkey" FOREIGN KEY ("org_membership_id") REFERENCES "organization_memberships"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+-- CreateIndex
+CREATE INDEX "project_memberships_project_id_idx" ON "project_memberships"("project_id");
+-- CreateIndex
+CREATE INDEX "project_memberships_org_membership_id_idx" ON "project_memberships"("org_membership_id");
+
+
+
+-- AUDIT LOGS
+-- DropForeignKey, just index on these, should remain after project/org/user deletions
+ALTER TABLE "audit_logs" DROP CONSTRAINT "audit_logs_user_id_fkey";
+ALTER TABLE "audit_logs" DROP CONSTRAINT "audit_logs_project_id_fkey";
+-- Drop not null on project level cols
+ALTER TABLE "audit_logs" ALTER COLUMN "project_id" DROP NOT NULL;
+ALTER TABLE "audit_logs" ALTER COLUMN "user_project_role" DROP NOT NULL;
+-- Add org-level cols
+ALTER TABLE "audit_logs" ADD COLUMN "org_id" TEXT;
+ALTER TABLE "audit_logs" ADD COLUMN "user_org_role" TEXT;
+-- Backfill org_id
+UPDATE "audit_logs"
+SET "org_id" = "projects"."org_id"
+FROM "projects"
+WHERE "audit_logs"."project_id" = "projects"."id";
+-- Backfill user_org_role with value from user_project_role
+UPDATE "audit_logs"
+SET "user_org_role" = "user_project_role"::text::"Role";
+-- Drop and recreate user_project_role column as text column going forward, empty for historical data as it's all on org level now
+ALTER TABLE "audit_logs" DROP COLUMN "user_project_role";
+ALTER TABLE "audit_logs" ADD COLUMN "user_project_role" TEXT; -- nullable
+-- Add not null on org level cols
+ALTER TABLE "audit_logs" ALTER COLUMN "org_id" SET NOT NULL;
+ALTER TABLE "audit_logs" ALTER COLUMN "user_org_role" SET NOT NULL;
+-- CreateIndex
+CREATE INDEX "audit_logs_user_id_idx" ON "audit_logs"("user_id");
+CREATE INDEX "audit_logs_org_id_idx" ON "audit_logs"("org_id");
+
+
+-- MEMBERSHIP INVITATIONS
+-- Rename sender_id to invited_by_user_id
+ALTER TABLE "membership_invitations" DROP CONSTRAINT "membership_invitations_sender_id_fkey";
+ALTER TABLE "membership_invitations" RENAME COLUMN "sender_id" TO "invited_by_user_id";
+ALTER TABLE "membership_invitations" ADD CONSTRAINT "membership_invitations_invited_by_user_id_fkey" FOREIGN KEY ("invited_by_user_id") REFERENCES "users"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+-- DropForeignKey
+ALTER TABLE "membership_invitations" DROP CONSTRAINT "membership_invitations_project_id_fkey";
+-- AlterTable
+ALTER TABLE "membership_invitations" RENAME COLUMN "role" TO "project_role";
+ALTER TABLE "membership_invitations" ADD COLUMN "org_id" TEXT;
+ALTER TABLE "membership_invitations" ADD COLUMN "org_role" "Role";
+ALTER TABLE "membership_invitations" ALTER COLUMN "project_id" DROP NOT NULL;
+ALTER TABLE "membership_invitations" ALTER COLUMN "project_role" DROP NOT NULL;
+-- Backfill org id
+UPDATE "membership_invitations"
+SET "org_id" = "projects"."org_id"
+FROM "projects"
+WHERE "membership_invitations"."project_id" = "projects"."id";
+-- AddForeignKey
+ALTER TABLE "membership_invitations" ADD CONSTRAINT "membership_invitations_org_id_fkey" FOREIGN KEY ("org_id") REFERENCES "organizations"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+-- Backfill org role with value from project role
+UPDATE "membership_invitations"
+SET "org_role" = "project_role"::text::"Role";
+-- Set project-level cols to null, as it's now org level for all existing invitations and role enum will change below
+UPDATE "membership_invitations"
+SET "project_role" = NULL, "project_id" = NULL;
+-- Switch to new UserRole enum
+ALTER TABLE "membership_invitations" DROP COLUMN "project_role",
+ADD COLUMN     "project_role" "Role";
+
+-- AddForeignKey
+ALTER TABLE "membership_invitations" ADD CONSTRAINT "membership_invitations_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+
+-- Add not null on org level cols after backfill
+ALTER TABLE "membership_invitations"
+ALTER COLUMN "org_id" SET NOT NULL,
+ALTER COLUMN "org_role" SET NOT NULL;
+-- CreateIndex
+CREATE INDEX "membership_invitations_org_id_idx" ON "membership_invitations"("org_id");
+
+
+-- Drop ProjectRole enum as it is replaced by Role
+DROP TYPE "ProjectRole";