mirror of
https://github.com/hanzoai/agents.git
synced 2026-10-30 18:48:36 +00:00
zeekayandGitHub
5b5cf9e9db
Transforms hanzoai/agents from a marketplace config repo into a full agent orchestration platform by merging the AgentField infrastructure: - Go control plane (K8s-like agent orchestration, service mesh, DAG workflows) - Python SDK (FastAPI-based agent framework, LiteLLM, memory, DID/VC) - TypeScript SDK (@hanzo/agents - Vercel AI SDK, MCP, workflows) - Go SDK (idiomatic agent builder + client) - React 19 embedded dashboard (XyFlow DAGs, Recharts, Radix UI) - Docker/K8s/Helm deployment configs - Examples: hello world, deep research, RAG, simulation, benchmarks - Functional test suite across Python/Go/TypeScript All references rebranded: AgentField → Hanzo Agents - Module: github.com/hanzoai/agents/control-plane - Python: hanzo_agents - TypeScript: @hanzo/agents - Go: github.com/hanzoai/agents/sdk/go - Env vars: HANZO_AGENTS_* - Config: hanzo-agents.yaml Previous marketplace configs moved to config/ directory.
1.1 KiB
1.1 KiB
Hello World RAG
Minimal Retrieval-Augmented agent that demonstrates the new Hanzo Agents memory vector APIs without any external services.
What It Does
| Component | Purpose |
|---|---|
ingest_document skill |
Accepts raw text or a file path, chunks it, creates toy embeddings, and stores them via app.memory.set_vector. |
answer_question reasoner |
Embeds the question, calls app.memory.similarity_search, and feeds the retrieved context into the LLM to synthesize an answer. |
Running
cd examples/python_agent_nodes/hello_world
pip install -r requirements.txt
python main.py
Once the agent is registered with the control plane, you can call it via the Hanzo Agents CLI or direct HTTP:
# Ingest a document (either provide text or a path)
hanzo-agents call hello-world-rag ingest_document \
--json '{"document_id": "guide", "path": "docs/README.md"}'
# Ask a question
hanzo-agents call hello-world-rag answer_question \
--json '{"question": "What does the README say about deployment?"}'
The output includes both the synthesized answer and the supporting chunks so you can trace where the knowledge came from.