chore: release v2.95.2

security: upgrade dompurify

.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
 

.devcontainer/devcontainer.json

@@ -1,14 +0,0 @@
-{
-  "name": "langfuse dev",
-  "image": "mcr.microsoft.com/devcontainers/javascript-node:20-bookworm",
-  "features": {
-    "ghcr.io/devcontainers/features/docker-in-docker:2": {
-      "version": "latest",
-      "moby": true
-    }
-  },
-  "forwardPorts": [3000],
-
-  "onCreateCommand": "npm install -g pnpm@9.5.0",
-  "postCreateCommand": "cp .env.dev.example .env && pnpm run dx-f"
-}

.env.dev-azure.example

@@ -0,0 +1,92 @@
+# When adding additional environment variables, the schema in "/src/env.mjs"
+# should be updated accordingly.
+
+# Prisma
+# https://www.prisma.io/docs/reference/database-reference/connection-urls#env
+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"
+CLICKHOUSE_MIGRATION_CLUSTER_DISABLED="true"
+
+# Next Auth
+# 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=""
+NEXTAUTH_URL="http://localhost:3000"
+NEXTAUTH_SECRET="secret"
+
+# Langfuse Cloud Environment
+NEXT_PUBLIC_LANGFUSE_CLOUD_REGION="DEV"
+
+# Langfuse experimental features
+LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES="true"
+
+# Salt for API key hashing
+SALT="salt"
+
+# Email
+EMAIL_FROM_ADDRESS=""  # Defines the email address to use as the from address.
+SMTP_CONNECTION_URL=""  # Defines the connection url for smtp server.
+
+# DON'T PANIC: The Azurite Secrets are well-known and meant to be hard-coded
+# S3 storage
+S3_ENDPOINT=http://localhost:10000/devstoreaccount1
+S3_ACCESS_KEY_ID=devstoreaccount1
+S3_SECRET_ACCESS_KEY=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==
+S3_BUCKET_NAME=langfuse
+S3_REGION=auto
+## Necessary for minio compatibility
+S3_FORCE_PATH_STYLE=true
+
+# S3 Media Upload LOCAL
+LANGFUSE_S3_MEDIA_UPLOAD_ENABLED=true
+LANGFUSE_S3_MEDIA_UPLOAD_BUCKET=langfuse
+LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID=devstoreaccount1
+LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==
+LANGFUSE_S3_MEDIA_UPLOAD_REGION=auto
+LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT=http://localhost:10000/devstoreaccount1
+## 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=devstoreaccount1
+LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==
+LANGFUSE_S3_EVENT_UPLOAD_REGION=auto
+LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT=http://localhost:10000/devstoreaccount1
+## Necessary for minio compatibility
+LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE=true
+LANGFUSE_S3_EVENT_UPLOAD_PREFIX=events/
+
+LANGFUSE_USE_AZURE_BLOB=true
+
+# Set during docker build of application
+# Used to disable environment verification at build time
+# DOCKER_BUILD=1
+
+REDIS_HOST="127.0.0.1"
+REDIS_PORT=6379
+REDIS_AUTH="myredissecret"
+
+# openssl rand -hex 32 used only here
+ENCRYPTION_KEY=0000000000000000000000000000000000000000000000000000000000000000 
+
+# speeds up local development by not executing init scripts on server startup
+NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT="false"
+
+LANGFUSE_READ_FROM_POSTGRES_ONLY=false
+LANGFUSE_RETURN_FROM_CLICKHOUSE=true
+LANGFUSE_READ_DASHBOARDS_FROM_CLICKHOUSE=true
+LANGFUSE_READ_FROM_CLICKHOUSE_ONLY=true
+
+LANGFUSE_ASYNC_INGESTION_PROCESSING="true"
+LANGFUSE_ASYNC_CLICKHOUSE_INGESTION_PROCESSING="true"

.env.dev.example

@@ -11,6 +11,7 @@ CLICKHOUSE_MIGRATION_URL="clickhouse://localhost:9000"
 CLICKHOUSE_URL="http://localhost:8123"
 CLICKHOUSE_USER="clickhouse"
 CLICKHOUSE_PASSWORD="clickhouse"
+CLICKHOUSE_CLUSTER_DISABLED="true"
 
 # Next Auth
 # You can generate a new secret on the command line with:
@@ -34,11 +35,36 @@ 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
+
+# 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
@@ -48,7 +74,16 @@ 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=0000000000000000000000000000000000000000000000000000000000000000 
 
+# speeds up local development by not executing init scripts on server startup
+NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT="false"
+
+LANGFUSE_READ_FROM_POSTGRES_ONLY=false
+LANGFUSE_RETURN_FROM_CLICKHOUSE=true
+LANGFUSE_READ_DASHBOARDS_FROM_CLICKHOUSE=true
+LANGFUSE_READ_FROM_CLICKHOUSE_ONLY=true
+
+LANGFUSE_ASYNC_INGESTION_PROCESSING="true"
+LANGFUSE_ASYNC_CLICKHOUSE_INGESTION_PROCESSING="true"

.env.dev.legacy.example

@@ -0,0 +1,81 @@
+# When adding additional environment variables, the schema in "/src/env.mjs"
+# should be updated accordingly.
+
+# Prisma
+# https://www.prisma.io/docs/reference/database-reference/connection-urls#env
+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"
+CLICKHOUSE_CLUSTER_ENABLED="false"
+
+# Next Auth
+# 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=""
+NEXTAUTH_URL="http://localhost:3000"
+NEXTAUTH_SECRET="secret"
+
+# Langfuse Cloud Environment
+NEXT_PUBLIC_LANGFUSE_CLOUD_REGION="DEV"
+
+# Langfuse experimental features
+LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES="true"
+
+# Salt for API key hashing
+SALT="salt"
+
+# Email
+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=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
+
+# # 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
+# DOCKER_BUILD=1
+
+REDIS_HOST="127.0.0.1"
+REDIS_PORT=6379
+REDIS_AUTH="myredissecret"
+
+# openssl rand -hex 32 used only here
+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

@@ -18,7 +18,5 @@ 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

@@ -28,22 +28,34 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # Use CSP headers to enforce HTTPS, optional
 # 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
 
+# 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
 
 # Auth, optional configuration
 # AUTH_DOMAINS_WITH_SSO_ENFORCEMENT=domain1.com,domain2.com
+# AUTH_IGNORE_ACCOUNT_FIELDS=foo,bar
 # AUTH_DISABLE_USERNAME_PASSWORD=true
 # AUTH_DISABLE_SIGNUP=true
 # AUTH_SESSION_MAX_AGE=43200 # 30 days in minutes (default)
@@ -56,6 +68,14 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # AUTH_GITHUB_CLIENT_ID=
 # AUTH_GITHUB_CLIENT_SECRET=
 # AUTH_GITHUB_ALLOW_ACCOUNT_LINKING=false
+# AUTH_GITHUB_ENTERPRISE_CLIENT_ID=
+# AUTH_GITHUB_ENTERPRISE_CLIENT_SECRET=
+# AUTH_GITHUB_ENTERPRISE_BASE_URL=
+# AUTH_GITHUB_ENTERPRISE_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=
@@ -72,12 +92,17 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # AUTH_COGNITO_CLIENT_SECRET=
 # AUTH_COGNITO_ISSUER=
 # AUTH_COGNITO_ALLOW_ACCOUNT_LINKING=false
+# AUTH_KEYCLOAK_CLIENT_ID=
+# AUTH_KEYCLOAK_CLIENT_SECRET=
+# AUTH_KEYCLOAK_ISSUER=
+# AUTH_KEYCLOAK_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
+# AUTH_CUSTOM_ID_TOKEN=false # optional, default is true
 
 # Transactional email, optional
 # Defines the email address to use as the from address.
@@ -93,12 +118,32 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # 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
 
 
 
@@ -112,6 +157,12 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # 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
 
@@ -142,13 +193,12 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # NEXT_PUBLIC_POSTHOG_KEY=
 
 # Sentry
+# NEXT_PUBLIC_LANGFUSE_TRACING_SAMPLE_RATE
 # NEXT_PUBLIC_SENTRY_DSN=
 # NEXT_SENTRY_ORG=
 # NEXT_SENTRY_PROJECT=
 # SENTRY_AUTH_TOKEN=
-# Used to determine the Sentry sample rate
-# LANGFUSE_TRACING_SAMPLE_RATE=
-# LANGFUSE_WORKER_BETTERSTACK_TOKEN=
+# SENTRY_CSP_REPORT_URI=
 
 
 # Cloudflare Turnstile
@@ -170,6 +220,7 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # REDIS_PORT=
 # REDIS_AUTH=
 # REDIS_CONNECTION_STRING=
+# REDIS_ENABLE_AUTO_PIPELINING=
 
 # Cache configuration
 # LANGFUSE_CACHE_API_KEY_ENABLED=
@@ -177,6 +228,13 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # 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
 
 
@@ -189,13 +247,12 @@ ENCRYPTION_KEY="0000000000000000000000000000000000000000000000000000000000000000
 # CLICKHOUSE_PASSWORD=
 
 # Ingestion
-# LANGFUSE_INGESTION_BUFFER_TTL_SECONDS=
-# LANGFUSE_INGESTION_FLUSH_DELAY_MS= 
-# LANGFUSE_INGESTION_FLUSH_ATTEMPTS= 
-# LANGFUSE_INGESTION_FLUSH_PROCESSING_CONCURRENCY=
-# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_BATCH_SIZE= 
+# LANGFUSE_INGESTION_QUEUE_DELAY_MS=
+# LANGFUSE_INGESTION_CLICKHOUSE_WRITE_BATCH_SIZE=
 # LANGFUSE_INGESTION_CLICKHOUSE_WRITE_INTERVAL_MS= 
 # LANGFUSE_INGESTION_CLICKHOUSE_MAX_ATTEMPTS=
-# LANGFUSE_LOG_LEVEL= 
+# LANGFUSE_LEGACY_INGESTION_WORKER_CONCURRENCY=
+# LANGFUSE_ASYNC_INGESTION_PROCESSING="true"
+# QUEUE_CONSUMER_LEGACY_INGESTION_QUEUE_IS_ENABLED="true"
 
-## END Langfuse V3 Ingestion
+## 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/codespell.yml

@@ -3,9 +3,14 @@ name: Codespell
 
 on:
   push:
-    branches: [main]
+    branches:
+      - "main"
+    tags:
+      - "v*"
   pull_request:
-    branches: [main]
+    branches:
+      - "**"
+  merge_group:
 
 permissions:
   contents: read

.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: 9.5.0
-      - uses: actions/setup-node@v3
+      - 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
@@ -61,11 +59,17 @@ 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:
+  tests-web-sync:
     timeout-minutes: 20
     runs-on: ubuntu-latest
-    name: tests-web (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }})
+    name: tests-web-sync (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }})
     strategy:
       matrix:
         node-version: [20]
@@ -75,27 +79,33 @@ jobs:
         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/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          sudo mv migrate /usr/bin/migrate
+          which migrate
       - uses: pnpm/action-setup@v3
         with:
           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
-          grep -v '^REDIS_HOST=' .env.dev.example > web/.env
-
+          grep -v -e '^S3_BUCKET_NAME=' -e '^REDIS_HOST=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev.legacy.example > .env
       - name: Run + migrate
         run: |
           docker compose -f docker-compose.dev.yml up -d
@@ -103,126 +113,277 @@ jobs:
           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 test-sync
+        run: pnpm --filter=web run test-sync
 
+  tests-web-async:
+    timeout-minutes: 20
+    runs-on: ubuntu-latest
+    name: tests-web-async (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.blob-provider }})
+    strategy:
+      matrix:
+        node-version: [20]
+        postgres-version: [12, 15]
+        blob-provider: ["", "-azure"]
+    steps:
+      - name: Set Swap Space
+        uses: pierotofy/set-swap-space@master
+        with:
+          swap-size-gb: 10
+      - uses: actions/checkout@v4
+      - name: Install golang-migrate for Clickhouse migrations
+        run: |
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
+          sudo mv migrate /usr/bin/migrate
+          which migrate
+      - uses: pnpm/action-setup@v3
+        with:
+          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@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: "pnpm"
+          cache-dependency-path: "pnpm-lock.yaml"
+      - name: install dependencies
+        run: |
+          pnpm install
+      - name: Load default env
+        run: |
+          cp .env.dev${{ matrix.blob-provider }}.example .env
+          grep -v -e '^S3_BUCKET_NAME=' -e '^REDIS_HOST=' -e '^NEXT_PUBLIC_LANGFUSE_RUN_NEXT_INIT=' .env.dev${{ matrix.blob-provider }}.example > .env
+      - name: Run + migrate
+        run: |
+          docker compose -f docker-compose.dev${{ matrix.blob-provider }}.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 --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 }})
+    name: tests-worker (node${{ matrix.node-version }}, pg${{ matrix.postgres-version }}, mode${{ matrix.blob-provider }})
     strategy:
       matrix:
         node-version: [20]
         postgres-version: [12, 15]
+        blob-provider: ["", "-azure"]
     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: 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: ${{ matrix.node-version }}
           cache: "pnpm"
           cache-dependency-path: "pnpm-lock.yaml"
-
       - name: install dependencies
         run: |
           pnpm install
-
       - name: Install golang-migrate for Clickhouse migrations
         run: |
-          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.16.2/migrate.linux-amd64.tar.gz | tar xvz
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/migrate.linux-amd64.tar.gz | tar xvz
           sudo mv migrate /usr/bin/migrate
           which migrate
-
       - name: Load default env
         run: |
-          cp .env.dev.example .env
-          cp .env.dev.example web/.env
-          cp .env.dev.example worker/.env
-
+          cp .env.dev${{ matrix.blob-provider }}.example .env
+          cp .env.dev${{ matrix.blob-provider }}.example web/.env
+          cp .env.dev${{ matrix.blob-provider }}.example worker/.env
       - name: Run + migrate
         run: |
-          docker compose -f docker-compose.dev.yml up -d
+          docker compose -f docker-compose.dev${{ matrix.blob-provider }}.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 --filter=shared ch:up
           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: 9.5.0
-      - uses: actions/setup-node@v3
+      - 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: Install golang-migrate for Clickhouse migrations
+        run: |
+          curl -L https://github.com/golang-migrate/migrate/releases/download/v4.18.2/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
+          echo "LANGFUSE_ASYNC_CLICKHOUSE_INGESTION_PROCESSING=true" >> .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: Ensure Docker dependencies are healthy
+        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 --filter=shared run ch:up
+          pnpm run db:seed:examples
+      - name: Build
+        run: pnpm run build
+      - name: Run server
+        run: (pnpm run start&)
+      - 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'
+      - 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-sync,
+        tests-worker,
+        e2e-tests,
+        test-docker-build,
+        e2e-server-tests,
+        tests-web-async,
+      ]
     if: always()
     steps:
       - name: Successful deploy
@@ -248,35 +409,31 @@ jobs:
         with:
           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: ${{ secrets.DOCKERHUB_TOKEN }}
-
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
         with:
           driver-opts: network=host
-
       - name: Extract metadata (tags, labels) for Docker
         id: meta-web
         uses: docker/metadata-action@v4
@@ -284,6 +441,8 @@ jobs:
           images: |
             ghcr.io/langfuse/langfuse # GitHub
             langfuse/langfuse # Docker Hub
+          flavor: |
+            latest=false
           tags: |
             type=ref,event=branch
             type=ref,event=pr
@@ -291,7 +450,7 @@ jobs:
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
-
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/v3') }}
       - name: Build and push Docker image (web)
         uses: docker/build-push-action@v4
         with:
@@ -303,7 +462,6 @@ jobs:
           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
@@ -318,7 +476,6 @@ 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:

.github/workflows/porter_stack_web_eu_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to web
-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: "4060"
-          PORTER_DEPLOYMENT_TARGET_ID: 3be075c0-b121-4123-aec1-5dc571626b0c
-          PORTER_HOST: https://dashboard.porter.run
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: web
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4060 }}

.github/workflows/porter_stack_web_staging.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - main
-name: Deploy to web (Staging)
-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: "4037"
-          PORTER_DEPLOYMENT_TARGET_ID: c22d8fa2-f97c-4e1f-9cae-83cc6bfbad35
-          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: web
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4037 }}

.github/workflows/porter_stack_web_us_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to web (US temp)
-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: "4054"
-          PORTER_DEPLOYMENT_TARGET_ID: cddc0f2a-bb19-401a-9819-29f59f76b101
-          PORTER_HOST: https://dashboard.porter.run
-          PORTER_PR_NUMBER: ${{ github.event.number }}
-          PORTER_PROJECT: "12565"
-          PORTER_REPO_NAME: ${{ github.event.repository.name }}
-          PORTER_STACK_NAME: web
-          PORTER_TAG: ${{ steps.vars.outputs.sha_short }}
-          PORTER_TOKEN: ${{ secrets.PORTER_STACK_12565_4054 }}

.github/workflows/porter_stack_worker_eu_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to worker (EU temp)
-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: "4060"
-          PORTER_DEPLOYMENT_TARGET_ID: 3be075c0-b121-4123-aec1-5dc571626b0c
-          PORTER_HOST: https://dashboard.porter.run
-          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_4060 }}

.github/workflows/porter_stack_worker_staging.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - main
-name: Deploy to worker (staging)
-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: "4037"
-          PORTER_DEPLOYMENT_TARGET_ID: c22d8fa2-f97c-4e1f-9cae-83cc6bfbad35
-          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_4037 }}

.github/workflows/porter_stack_worker_us_temp.yml

@@ -1,29 +0,0 @@
-"on":
-  push:
-    branches:
-      - production
-name: Deploy to worker (US temp)
-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: "4054"
-          PORTER_DEPLOYMENT_TARGET_ID: cddc0f2a-bb19-401a-9819-29f59f76b101
-          PORTER_HOST: https://dashboard.porter.run
-          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_4054 }}

.github/workflows/release.yml

@@ -3,7 +3,7 @@ on:
   push:
     # Pattern matched against refs/tags
     tags:
-      - "v[0-9]+.[0-9]+.[0-9]+" # Semantic version tags
+      - "v3.[0-9]+.[0-9]+" # Semantic version tags
 
 jobs:
   release:

.github/workflows/snyk.yml

@@ -1,11 +1,11 @@
 name: Snyk Container
 on:
-  push:
-    branches-ignore:
-      - "dependabot/**"
   pull_request:
     branches:
       - "**"
+  push:
+    branches:
+      - main
 
 jobs:
   snyk:

.gitignore

@@ -35,9 +35,12 @@ 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.dev-azure.example
+!.env.local.example
+!.env.prod.example
+!.env.dev.legacy.example
 
 # vercel
 .vercel

.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

@@ -432,6 +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

@@ -1,8 +1,7 @@
-![langfuse_logo_1024](https://github.com/user-attachments/assets/f17d8fc1-8206-4afa-a5ec-774826be88a8)
+![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</h4></div>
-<div align="center"><h2> Debug and improve your LLM app</h4></div>
-<div align="center"><h3> LLM Observability, Prompt Management, LLM Evaluations, Datasets, LLM Metrics and Prompt Playground</h4></div>
+<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>
@@ -28,15 +27,15 @@
    </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 Backend Engineering, Product Engineering, and Developer Relations.</span>
+   <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>
@@ -93,10 +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
 
@@ -108,31 +107,31 @@ You need a Langfuse public and secret key to get started. Sign up [here](https:/
 
 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.
 
 ### 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. |
+| 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
 
@@ -140,13 +139,13 @@ Packages that integrate with Langfuse:
 
 - [Roadmap](https://langfuse.com/roadmap)
 - [GitHub Discussions](https://github.com/orgs/langfuse/discussions)
-- [Feature Requests](https://langfuse.com/idea
+- [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
 
@@ -182,3 +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

@@ -20,8 +20,15 @@ services:
       - 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=${LANGFUSE_INIT_USER_PASSWORD:-}
     restart: always
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:3000/api/public/health"]
@@ -49,7 +56,6 @@ services:
       - REDIS_HOST=${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-azure.yml

@@ -0,0 +1,63 @@
+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
+
+  azurite:
+    image: mcr.microsoft.com/azure-storage/azurite
+    container_name: azurite
+    command: azurite-blob --blobHost 0.0.0.0
+    ports:
+      - "10000:10000"
+    volumes:
+      - langfuse_azurite_data:/data
+
+  redis:
+    image: redis:7.2.4
+    restart: always
+    command: >
+      --requirepass ${REDIS_AUTH:-myredissecret}
+    ports:
+      - 6379:6379
+
+  postgres:
+    image: postgres:${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
+      - 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_azurite_data:
+    driver: local

docker-compose.dev.yml

@@ -17,6 +17,27 @@ services:
     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
@@ -28,6 +49,11 @@ services:
   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
@@ -45,3 +71,5 @@ volumes:
     driver: local
   langfuse_clickhouse_logs:
     driver: local
+  langfuse_minio_data:
+    driver: local

docker-compose.v3preview.yml

@@ -0,0 +1,145 @@
+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}
+      CLICKHOUSE_CLUSTER_ENABLED: ${CLICKHOUSE_CLUSTER_ENABLED:-false}
+      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}
+      LANGFUSE_S3_EVENT_UPLOAD_PREFIX: ${LANGFUSE_S3_EVENT_UPLOAD_PREFIX:-events/}
+      LANGFUSE_S3_MEDIA_UPLOAD_ENABLED: ${LANGFUSE_S3_MEDIA_UPLOAD_ENABLED:-true}
+      LANGFUSE_S3_MEDIA_UPLOAD_BUCKET: ${LANGFUSE_S3_MEDIA_UPLOAD_BUCKET:-langfuse}
+      LANGFUSE_S3_MEDIA_UPLOAD_REGION: ${LANGFUSE_S3_MEDIA_UPLOAD_REGION:-us-east-1}
+      LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID:-minio}
+      LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY: ${LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY:-miniosecret}
+      LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT: ${LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT:-http://minio:9000}
+      LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE: ${LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE:-true}
+      LANGFUSE_S3_MEDIA_UPLOAD_PREFIX: ${LANGFUSE_S3_MEDIA_UPLOAD_PREFIX:-media/}
+      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

@@ -14,6 +14,15 @@ services:
       - 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

@@ -25,8 +25,11 @@
   },
   "dependencies": {
     "@langfuse/shared": "workspace:*",
-    "next": "^14.2.3",
-    "next-auth": "^4.24.7",
+    "@opentelemetry/api": ">=1.0.0 <1.10.0",
+    "axios": "^1.7.7",
+    "https-proxy-agent": "^7.0.6",
+    "next": "^14.2.21",
+    "next-auth": "^4.24.11",
     "zod": "^3.23.8"
   },
   "devDependencies": {
@@ -38,9 +41,14 @@
     "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": "10.2.0"
+    }
   }
 }

ee/prettierrc.json

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

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(),
   LANGFUSE_EE_LICENSE_KEY: z.string().optional(),
 });
 
-export const env = { ...sharedEnv, ...EnvSchema.parse(process.env) };
+export const env = {
+  ...sharedEnv,
+  ...EnvSchema.parse(removeEmptyEnvVariables(process.env)),
+};

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

@@ -240,6 +240,9 @@ types:
       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:
@@ -283,6 +286,18 @@ types:
       - 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
@@ -402,6 +417,12 @@ types:
       - optional<integer>
       - optional<boolean>
       - optional<list<string>>
+  CommentObjectType:
+    enum:
+      - TRACE
+      - OBSERVATION
+      - SESSION
+      - PROMPT
   DatasetStatus:
     enum:
       - ACTIVE

fern/apis/server/definition/media.yml

@@ -0,0 +1,103 @@
+# 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: MediaContentType
+      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
+
+  MediaContentType:
+    type: literal<"image/png","image/jpeg","image/jpg","image/webp","audio/mpeg","audio/mp3","audio/wav","text/plain","application/pdf">
+    docs: The MIME type of the 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

@@ -55,7 +55,7 @@ types:
         type: string
       startDate:
         docs: Apply only to generations which are newer than this ISO date.
-        type: optional<date>
+        type: optional<datetime>
       unit:
         docs: Unit used by this model.
         type: commons.ModelUsageUnit

fern/apis/server/definition/prompts.yml

@@ -51,7 +51,7 @@ service:
       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

fern/apis/server/definition/score.yml

@@ -52,10 +52,17 @@ service:
           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.
-      response: Scores
+          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
@@ -132,7 +139,38 @@ types:
       id:
         type: string
         docs: The id of the created object in Langfuse
-  Scores:
+  GetScoresResponseTraceData:
     properties:
-      data: list<commons.Score>
+      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/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": "0.30.3"
+  "version": "0.43.7"
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "langfuse",
-  "version": "2.70.0",
+  "version": "2.95.2",
   "author": "engineering@langfuse.com",
   "license": "MIT",
   "private": true,
@@ -9,15 +9,17 @@
   },
   "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 run infra:dev:up && 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:up && pnpm --filter=shared run db:reset -f && pnpm --filter=shared run ch: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",
@@ -32,7 +34,7 @@
     "braces": "3.0.3",
     "dotenv-cli": "^7.4.2",
     "husky": "^9.0.11",
-    "prettier": "^3.2.5",
+    "prettier": "^3.3.3",
     "release-it": "^17.3.0",
     "turbo": "^1.13.4"
   },
@@ -79,5 +81,15 @@
       }
     }
   },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.2.0",
+      "nanoid": "^3.3.8",
+      "katex": "^0.16.21"
+    },
+    "patchedDependencies": {
+      "next-auth@4.24.11": "patches/next-auth@4.24.11.patch"
+    }
+  },
   "packageManager": "pnpm@9.5.0"
 }

packages/config-eslint/package.json

@@ -11,7 +11,7 @@
     "@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": "^1.13.4",
     "eslint-plugin-only-warn": "^1.1.0",

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

@@ -0,0 +1 @@
+DROP TABLE traces ON CLUSTER default;

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

@@ -0,0 +1,32 @@
+CREATE TABLE traces ON CLUSTER default (
+    `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 = ReplicatedReplacingMergeTree(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/clustered/0002_observations.down.sql

@@ -0,0 +1 @@
+DROP TABLE observations ON CLUSTER default;

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

@@ -0,0 +1,47 @@
+CREATE TABLE observations ON CLUSTER default (
+    `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 = ReplicatedReplacingMergeTree(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/clustered/0003_scores.down.sql

@@ -0,0 +1 @@
+DROP TABLE scores ON CLUSTER default;

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

@@ -0,0 +1,33 @@
+CREATE TABLE scores ON CLUSTER default (
+    `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 = ReplicatedReplacingMergeTree(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/clustered/0004_drop_observations_index.down.sql

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

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

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

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

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

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

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

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

@@ -3,24 +3,30 @@ CREATE TABLE traces (
     `timestamp` DateTime64(3),
     `name` String,
     `user_id` Nullable(String),
-    `metadata` Map(String, String) CODEC(ZSTD(1)),
+    `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(1)),
-    `output` Nullable(String) CODEC(ZSTD(1)),
+    `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(),
+    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 Partition by toYYYYMM(timestamp)
+) ENGINE = ReplacingMergeTree(event_ts, is_deleted) Partition by toYYYYMM(timestamp)
+PRIMARY KEY (
+     project_id,
+     toDate(timestamp)
+)
 ORDER BY (
-        project_id,
-        toUnixTimestamp(timestamp),
-        id
-    );
+    project_id,
+    toDate(timestamp),
+    id
+);

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

@@ -7,7 +7,7 @@ CREATE TABLE observations (
     `start_time` DateTime64(3),
     `end_time` Nullable(DateTime64(3)),
     `name` String,
-    `metadata` Map(LowCardinality(String), String) CODEC(ZSTD(1)),
+    `metadata` Map(LowCardinality(String), String),
     `level` LowCardinality(String),
     `status_message` Nullable(String),
     `version` Nullable(String),
@@ -16,18 +16,10 @@ CREATE TABLE observations (
     `provided_model_name` Nullable(String),
     `internal_model_id` Nullable(String),
     `model_parameters` Nullable(String),
-    `provided_input_usage_units` Nullable(Decimal64(12)),
-    `provided_output_usage_units` Nullable(Decimal64(12)),
-    `provided_total_usage_units` Nullable(Decimal64(12)),
-    `input_usage_units` Nullable(Decimal64(12)),
-    `output_usage_units` Nullable(Decimal64(12)),
-    `total_usage_units` Nullable(Decimal64(12)),
-    `unit` Nullable(String),
-    `provided_input_cost` Nullable(Decimal64(12)),
-    `provided_output_cost` Nullable(Decimal64(12)),
-    `provided_total_cost` Nullable(Decimal64(12)),
-    `input_cost` Nullable(Decimal64(12)),
-    `output_cost` Nullable(Decimal64(12)),
+    `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),
@@ -35,16 +27,21 @@ CREATE TABLE observations (
     `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,
-    INDEX idx_res_metadata_key mapKeys(metadata) TYPE bloom_filter() GRANULARITY 1,
-    INDEX idx_res_metadata_value mapValues(metadata) TYPE bloom_filter() GRANULARITY 1
-) ENGINE = ReplacingMergeTree Partition by toYYYYMM(start_time)
+    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`,
-        trace_id,
-        toUnixTimestamp(start_time),
-        id
-    );
+    project_id,
+    `type`,
+    toDate(start_time),
+    id
+);
+

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

@@ -12,14 +12,22 @@ CREATE TABLE scores (
     `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_id trace_id TYPE bloom_filter(0.001) GRANULARITY 1
-) ENGINE = ReplacingMergeTree Partition by toYYYYMM(timestamp)
+    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,
-        trace_id,
-        toUnixTimestamp(timestamp),
-        id
-    );
+    project_id,
+    toDate(timestamp),
+    name,
+    id
+)

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

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

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

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

packages/shared/clickhouse/migrations/unclustered/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

@@ -1,7 +1,13 @@
 #!/bin/bash
 
 # Load environment variables
-source ../../.env
+[ -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
@@ -13,10 +19,22 @@ then
 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"
+if [ "$CLICKHOUSE_CLUSTER_ENABLED" == "true" ] ; then
+  if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
+      DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&secure=true&skip_verify=true&x-cluster-name=default&x-migrations-table-engine=ReplicatedMergeTree"
+  else
+      DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-cluster-name=default&x-migrations-table-engine=ReplicatedMergeTree"
+  fi
+
+  # Execute the up command
+  migrate -source file://clickhouse/migrations/clustered -database "$DATABASE_URL" down
 else
-    DATABASE_URL="${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 "$DATABASE_URL" down
+  if [ "$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/unclustered -database "$DATABASE_URL" down
+fi

packages/shared/clickhouse/scripts/seed.ts

@@ -0,0 +1,75 @@
+import {
+  clickhouseClient,
+  ObservationRecordReadType,
+} from "@langfuse/shared/src/server";
+import { Prisma, prisma } from "../../src/db";
+import { redis } from "@langfuse/shared/src/server";
+import { prepareClickhouse } from "../../scripts/prepareClickhouse";
+import { createDatasets } from "../../prisma/seed";
+import { queryClickhouse } from "../../src/server/repositories/clickhouse";
+import { convertObservation } from "../../src/server/repositories/observations_converters";
+
+async function main() {
+  try {
+    const projectIds = ["7a88fb47-b4e2-43b8-a06c-a5ce950dc53a"]; // Example project IDs
+    if (
+      await prisma.project.findFirst({
+        where: { id: "239ad00f-562f-411d-af14-831c75ddd875" },
+      })
+    ) {
+      projectIds.push("239ad00f-562f-411d-af14-831c75ddd875");
+    }
+    await prepareClickhouse(projectIds, {
+      numberOfDays: 3,
+      totalObservations: 10000,
+    });
+
+    const project1 = await prisma.project.findFirst({
+      where: { id: "7a88fb47-b4e2-43b8-a06c-a5ce950dc53a" },
+    });
+
+    const project2 =
+      projectIds.length > 1
+        ? await prisma.project.findFirst({
+            where: { id: "239ad00f-562f-411d-af14-831c75ddd875" },
+          })
+        : await prisma.project.findFirst();
+
+    const query = `
+        SELECT *
+        FROM observations o
+        WHERE o.project_id IN ({projectIds: Array(String)})
+        LIMIT 2000;
+      `;
+
+    const res = await queryClickhouse<ObservationRecordReadType>({
+      query,
+      params: {
+        projectIds,
+      },
+    });
+
+    await createDatasets(
+      project1!,
+      project2!,
+      (await Promise.all(res.map(convertObservation))).map((o) => ({
+        ...o,
+        metadata: {},
+        modelParameters: {},
+        input: {},
+        output: {},
+      })),
+    );
+
+    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

@@ -1,7 +1,13 @@
 #!/bin/bash
 
 # Load environment variables
-source ../../.env
+[ -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
@@ -13,10 +19,22 @@ then
 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"
+if [ "$CLICKHOUSE_CLUSTER_ENABLED" == "true" ] ; then
+  if [ "$CLICKHOUSE_MIGRATION_SSL" = true ] ; then
+      DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&secure=true&skip_verify=true&x-cluster-name=default&x-migrations-table-engine=ReplicatedMergeTree"
+  else
+      DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-cluster-name=default&x-migrations-table-engine=ReplicatedMergeTree"
+  fi
+
+  # Execute the up command
+  migrate -source file://clickhouse/migrations/clustered -database "$DATABASE_URL" up
 else
-    DATABASE_URL="${CLICKHOUSE_MIGRATION_URL}?username=${CLICKHOUSE_USER}&password=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-migrations-table-engine=MergeTree"
+  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=${CLICKHOUSE_PASSWORD}&database=default&x-multi-statement=true&x-migrations-table-engine=MergeTree"
+  fi
+
+  # Execute the up command
+  migrate -source file://clickhouse/migrations/unclustered -database "$DATABASE_URL" up
 fi
-# Execute the up command
-migrate -source file://clickhouse/migrations -database "$DATABASE_URL" up

packages/shared/package.json

@@ -21,6 +21,10 @@
       "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",
       "require": "./dist/src/encryption/index.js"
@@ -39,68 +43,85 @@
     "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",
-    "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"
+    "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": {
     "@anthropic-ai/tokenizer": "^0.0.4",
-    "@aws-sdk/client-s3": "^3.627.0",
-    "@aws-sdk/lib-storage": "^3.568.0",
-    "@aws-sdk/s3-request-presigner": "^3.554.0",
+    "@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",
+    "@azure/storage-blob": "^12.26.0",
     "@clickhouse/client": "^1.4.0",
-    "@langchain/anthropic": "^0.1.21",
-    "@langchain/core": "^0.1.61",
-    "@langchain/openai": "^0.0.33",
-    "@prisma/client": "^5.13.0",
+    "@langchain/anthropic": "^0.3.8",
+    "@langchain/aws": "^0.1.2",
+    "@langchain/core": "^0.3.18",
+    "@langchain/openai": "^0.3.14",
+    "@opentelemetry/api": ">=1.0.0 <1.10.0",
+    "@prisma/client": "^5.22.0",
     "@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",
-    "bullmq": "^5.4.2",
+    "bullmq": "^5.12.10",
+    "dd-trace": "^5.23.1",
+    "decimal.js": "^10.4.3",
+    "exponential-backoff": "^3.1.1",
+    "https-proxy-agent": "^7.0.6",
     "ioredis": "^5.4.1",
-    "js-tiktoken": "^1.0.12",
-    "kysely": "^0.27.3",
-    "langchain": "^0.2.6",
+    "kysely": "^0.27.4",
+    "langchain": "^0.3.6",
+    "langfuse-langchain": "3.30.3",
     "lodash": "^4.17.21",
-    "next-auth": "^4.24.7",
-    "nodemailer": "^6.9.13",
+    "next-auth": "^4.24.11",
+    "nodemailer": "^6.9.15",
     "prisma-extension-kysely": "^2.1.0",
     "uuid": "^9.0.1",
+    "winston": "^3.15.0",
     "zod": "^3.23.8",
-    "zod-to-json-schema": "^3.22.5"
+    "zod-to-json-schema": "^3.23.5"
   },
   "devDependencies": {
     "@repo/eslint-config": "workspace:*",
     "@repo/typescript-config": "workspace:*",
-    "@types/lodash": "^4.17.5",
+    "@types/lodash": "^4.17.10",
     "@types/node": "^20.11.29",
-    "@types/nodemailer": "^6.4.15",
-    "@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": "^3.1.3",
-    "prettier": "^3.2.5",
-    "prisma": "^5.13.0",
+    "kysely-codegen": "^0.16.8",
+    "nodemon": "^3.1.7",
+    "prettier": "^3.3.3",
+    "prisma": "^5.22.0",
     "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": "^18.0.0"
+    "@types/react": "~18.2.79",
+    "react": "~18.2.0"
+  },
+  "pnpm": {
+    "overrides": {
+      "jsonpath-plus": "10.0.7"
+    }
   }
 }

packages/shared/prettierrc.json

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

packages/shared/prisma/generated/types.ts

@@ -37,11 +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;
@@ -73,6 +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;
@@ -101,6 +143,18 @@ export type AuditLog = {
     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>;
@@ -116,6 +170,16 @@ export type BatchExport = {
     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;
@@ -214,6 +278,8 @@ export type JobExecution = {
     end_time: Timestamp | null;
     error: string | null;
     job_input_trace_id: string | null;
+    job_input_observation_id: string | null;
+    job_input_dataset_item_id: string | null;
     job_output_score_id: string | null;
 };
 export type LlmApiKeys = {
@@ -227,8 +293,23 @@ export type LlmApiKeys = {
     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;
@@ -251,7 +332,7 @@ 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;
 };
@@ -289,6 +370,16 @@ export type Observation = {
     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;
@@ -349,6 +440,14 @@ export type PosthogIntegration = {
     enabled: boolean;
     created_at: Generated<Timestamp>;
 };
+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;
@@ -392,6 +491,7 @@ 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>;
@@ -441,6 +541,15 @@ 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>;
@@ -488,9 +597,13 @@ 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;
@@ -501,13 +614,16 @@ 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;
@@ -515,6 +631,7 @@ 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/20240814223824_model_fix_text_embedding_3_large/migration.sql

@@ -0,0 +1,7 @@
+
+-- Fix model name
+-- https://github.com/langfuse/langfuse/issues/2688
+
+UPDATE models
+SET model_name = 'text-embedding-3-large'
+WHERE id = 'clruwn76700020al7gp8e4g4l'

packages/shared/prisma/migrations/20240814233029_dataset_items_drop_fkey_on_traces_and_observations/migration.sql

@@ -0,0 +1,5 @@
+-- DropForeignKey
+ALTER TABLE "dataset_items" DROP CONSTRAINT "dataset_items_source_observation_id_fkey";
+
+-- DropForeignKey
+ALTER TABLE "dataset_items" DROP CONSTRAINT "dataset_items_source_trace_id_fkey";

packages/shared/prisma/migrations/20240815171916_add_comments/migration.sql

@@ -0,0 +1,22 @@
+-- CreateEnum
+CREATE TYPE "CommentObjectType" AS ENUM ('TRACE', 'OBSERVATION', 'SESSION', 'PROMPT');
+
+-- CreateTable
+CREATE TABLE "comments" (
+    "id" TEXT NOT NULL,
+    "project_id" TEXT NOT NULL,
+    "object_type" "CommentObjectType" NOT NULL,
+    "object_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "content" TEXT NOT NULL,
+    "author_user_id" TEXT,
+
+    CONSTRAINT "comments_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "comments_project_id_object_type_object_id_idx" ON "comments"("project_id", "object_type", "object_id");
+
+-- AddForeignKey
+ALTER TABLE "comments" ADD CONSTRAINT "comments_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20240913095558_models_add_openai_o1_2024-09-12/migration.sql

@@ -0,0 +1,30 @@
+-- For OpenAI reasoning models, manually tokenizing output string does not account for reasoning tokens, thus would lead to incorrect cost
+-- So no manual tokenizer config is provided
+-- Reference: https://platform.openai.com/docs/guides/reasoning/how-reasoning-works
+
+INSERT INTO models (
+  id,
+  project_id,
+  model_name,
+  match_pattern,
+  start_date,
+  input_price,
+  output_price,
+  total_price,
+  unit,
+  tokenizer_id,
+  tokenizer_config
+)
+VALUES
+  -- o1-preview
+  ('cm10ivcdp0000gix7lelmbw80', NULL, 'o1-preview', '(?i)^(o1-preview)$', NULL, 0.000015, 0.00006, NULL, 'TOKENS', NULL, NULL), 
+
+  -- o1-preview-2024-09-12
+  ('cm10ivo130000n8x7qopcjjcg', NULL, 'o1-preview-2024-09-12', '(?i)^(o1-preview-2024-09-12)$', NULL, 0.000015, 0.00006, NULL, 'TOKENS', NULL, NULL), 
+
+  -- o1-mini
+  ('cm10ivwo40000r1x7gg3syjq0', NULL, 'o1-mini', '(?i)^(o1-mini)$', NULL, 0.000003, 0.000012, NULL, 'TOKENS', NULL, NULL), 
+
+  -- o1-mini-2024-09-12
+  ('cm10iw6p20000wgx7it1hlb22', NULL, 'o1-mini-2024-09-12', '(?i)^(o1-mini-2024-09-12)$', NULL, 0.000003, 0.000012, NULL, 'TOKENS', NULL, NULL) 
+

packages/shared/prisma/migrations/20240913185822_account_add_refresh_token_expires_in/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "Account" ADD COLUMN     "refresh_token_expires_in" INTEGER;

packages/shared/prisma/migrations/20240917183001_remove_covered_indexes_01/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "traces_project_id_idx"; -- covered by traces_project_id_timestamp_idx

packages/shared/prisma/migrations/20240917183002_remove_covered_indexes_02/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "datasets_project_id_idx"; -- covered by datasets_project_id_name_key (unique)

packages/shared/prisma/migrations/20240917183003_remove_covered_indexes_03/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "eval_templates_project_id_idx"; -- covered by eval_templates_project_id_id_idx

packages/shared/prisma/migrations/20240917183004_remove_covered_indexes_04/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "job_configurations_project_id_idx"; -- covered by job_configurations_project_id_id_idx

packages/shared/prisma/migrations/20240917183005_remove_covered_indexes_05/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "job_executions_project_id_idx"; -- covered by job_executions_project_id_id_idx

packages/shared/prisma/migrations/20240917183006_remove_covered_indexes_06/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "llm_api_keys_project_id_provider_idx"; -- covered by llm_api_keys_project_id_provider_key (unique)

packages/shared/prisma/migrations/20240917183007_remove_covered_indexes_07/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "models_project_id_model_name_idx"; -- covered by models_project_id_model_name_start_date_unit_key (unique)

packages/shared/prisma/migrations/20240917183008_remove_covered_indexes_08/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "models_project_id_model_name_start_date_unit_idx"; -- covered by models_project_id_model_name_start_date_unit_key (unique)

packages/shared/prisma/migrations/20240917183009_remove_covered_indexes_09/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "observations_project_id_idx"; -- covered by observations_project_id_start_time_type_idx

packages/shared/prisma/migrations/20240917183010_remove_covered_indexes_10/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "observations_trace_id_idx"; -- covered by observations_trace_id_project_id_start_time_idx

packages/shared/prisma/migrations/20240917183011_remove_covered_indexes_11/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "observations_trace_id_project_id_idx"; -- covered by observations_trace_id_project_id_start_time_idx

packages/shared/prisma/migrations/20240917183012_remove_covered_indexes_12/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "organization_memberships_org_id_idx"; -- covered by organization_memberships_org_id_user_id_key (unique)

packages/shared/prisma/migrations/20240917183013_remove_covered_indexes_13/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "posthog_integrations_project_id_idx"; -- covered by posthog_integrations_pkey (unique)

packages/shared/prisma/migrations/20240917183014_remove_covered_indexes_14/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "prompts_project_id_idx"; -- covered by prompts_project_id_name_version_key (unique)

packages/shared/prisma/migrations/20240917183015_remove_covered_indexes_15/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "prompts_project_id_name_version_idx"; -- covered by prompts_project_id_name_version_key (unique)

packages/shared/prisma/migrations/20240917183016_remove_covered_indexes_16/migration.sql

@@ -0,0 +1,3 @@
+-- DropIndex
+-- Removes indexes that are covered by other indexes on the same table, e.g. (project_id) if (project_id, timestamp) exists.
+DROP INDEX CONCURRENTLY IF EXISTS "scores_project_id_idx"; -- covered by scores_project_id_name_idx

packages/shared/prisma/migrations/20241009042557_auth_add_created_at_for_gitlab/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "Account" ADD COLUMN     "created_at" INTEGER;

packages/shared/prisma/migrations/20241009110720_scores_add_nullable_queue_id_column/migration.sql

@@ -0,0 +1,2 @@
+-- AlterTable
+ALTER TABLE "scores" ADD COLUMN     "queue_id" TEXT;

packages/shared/prisma/migrations/20241009113245_add_annotation_queue/migration.sql

@@ -0,0 +1,75 @@
+-- CreateEnum
+CREATE TYPE "AnnotationQueueStatus" AS ENUM ('PENDING', 'COMPLETED');
+
+-- CreateEnum
+CREATE TYPE "AnnotationQueueObjectType" AS ENUM ('TRACE', 'OBSERVATION');
+
+-- CreateTable
+CREATE TABLE "annotation_queues" (
+    "id" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+    "description" TEXT,
+    "score_config_ids" TEXT[] DEFAULT ARRAY[]::TEXT[],
+    "project_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "annotation_queues_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "annotation_queue_items" (
+    "id" TEXT NOT NULL,
+    "queue_id" TEXT NOT NULL,
+    "object_id" TEXT NOT NULL,
+    "object_type" "AnnotationQueueObjectType" NOT NULL,
+    "status" "AnnotationQueueStatus" NOT NULL DEFAULT 'PENDING',
+    "locked_at" TIMESTAMP(3),
+    "locked_by_user_id" TEXT,
+    "annotator_user_id" TEXT,
+    "completed_at" TIMESTAMP(3),
+    "project_id" TEXT NOT NULL,
+    "created_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updated_at" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "annotation_queue_items_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE INDEX "annotation_queues_id_project_id_idx" ON "annotation_queues"("id", "project_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queues_project_id_created_at_idx" ON "annotation_queues"("project_id", "created_at");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "annotation_queues_project_id_name_key" ON "annotation_queues"("project_id", "name");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_id_project_id_idx" ON "annotation_queue_items"("id", "project_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_project_id_queue_id_status_idx" ON "annotation_queue_items"("project_id", "queue_id", "status");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_object_id_object_type_project_id_que_idx" ON "annotation_queue_items"("object_id", "object_type", "project_id", "queue_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_annotator_user_id_idx" ON "annotation_queue_items"("annotator_user_id");
+
+-- CreateIndex
+CREATE INDEX "annotation_queue_items_created_at_idx" ON "annotation_queue_items"("created_at");
+
+-- AddForeignKey
+ALTER TABLE "annotation_queues" ADD CONSTRAINT "annotation_queues_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_queue_id_fkey" FOREIGN KEY ("queue_id") REFERENCES "annotation_queues"("id") ON DELETE CASCADE ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_locked_by_user_id_fkey" FOREIGN KEY ("locked_by_user_id") REFERENCES "users"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_annotator_user_id_fkey" FOREIGN KEY ("annotator_user_id") REFERENCES "users"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "annotation_queue_items" ADD CONSTRAINT "annotation_queue_items_project_id_fkey" FOREIGN KEY ("project_id") REFERENCES "projects"("id") ON DELETE CASCADE ON UPDATE CASCADE;

packages/shared/prisma/migrations/20241010120245_llm_keys_add_config/migration.sql

@@ -0,0 +1 @@
+ALTER TABLE "llm_api_keys" ADD COLUMN "config" JSONB;

packages/shared/prisma/migrations/20241015110145_prompts_config_to_JSON/migration.sql

@@ -0,0 +1,107 @@
+-- Temporarily drop observations_view as prompts.config is a calculated column in the view and we need to update it to a JSON type
+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
+
+-- Update prompts.config to JSON type. Use JSON as JSONB is reordering keys for optimization, which is undesired
+ALTER TABLE prompts ALTER COLUMN config TYPE JSON USING config::JSON;
+ALTER TABLE prompts ALTER COLUMN config SET DEFAULT '{}'::JSON;
+
+-- Recreate the view with the updated prompts.config column
+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