Skip to main content
Based on the refreshed ai-agent-crew-ai-examples codebase, here’s how to run the knowledge_agent FastAPI service, ingest docs, and stream answers into CometChat.

​
What you’ll build

  • A CrewAI agent that grounds replies in your ingested docs (per namespace).
  • A FastAPI service with ingest/search/generate endpoints plus a /stream SSE.
  • CometChat AI Agent wiring that consumes newline-delimited JSON chunks (text_delta, text_done, done).

​
Prerequisites

  • Python 3.10+ with pip (or uv)
  • OPENAI_API_KEY (optionally OPENAI_BASE_URL, KNOWLEDGE_OPENAI_MODEL, KNOWLEDGE_EMBEDDING_MODEL)
  • A CometChat app + AI Agent entry

​
Run the updated sample

1

Install & start

In ai-agent-crew-ai-examples/: 
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
uvicorn knowledge_agent.main:app —host 0.0.0.0 —port 8000 —reload
Env supports .env at repo root or inside knowledge_agent/.env.
2

Set env

OPENAI_API_KEY is required. Optional: OPENAI_BASE_URL, KNOWLEDGE_OPENAI_MODEL (default gpt-4o-mini), KNOWLEDGE_EMBEDDING_MODEL (default text-embedding-3-small).
3

Storage

Ingested files land in knowledge_agent/data/knowledge/<namespace>/ and embeddings persist to knowledge_agent/data/chroma/<namespace>/. Duplicate hashes are skipped automatically.

​
API surface (FastAPI)

  • POST /api/tools/ingest — accept JSON or multipart/form-data with sources (text/markdown/url) and optional file uploads; returns saved, skipped, errors.
  • POST /api/tools/searchDocs — semantic search via Chroma; accepts namespace, query, max_results.
  • POST /api/agents/knowledge/generate — single, non-streaming completion.
  • POST /stream — newline-delimited JSON over SSE (text_delta, text_done, done) ready for CometChat BYOA.

​
Ingest examples

curl -X POST http://localhost:8000/api/tools/ingest \
  -H "Content-Type: application/json" \
  -d '{
        "namespace": "default",
        "sources": [
          { "type": "url", "value": "https://docs.crewai.com/" },
          { "type": "markdown", "title": "Notes", "value": "# CrewAI Rocks" }
        ]
      }'
Multipart uploads are also supported: 
curl -X POST http://localhost:8000/api/tools/ingest \
  -H "Accept: application/json" \
  -F "namespace=default" \
  -F "sources=[{\"type\":\"text\",\"value\":\"Hello\"}]" \
  -F "files=@/path/to/file.pdf"

​
Search + answer

curl -X POST http://localhost:8000/api/tools/searchDocs \
  -H "Content-Type: application/json" \
  -d '{"namespace":"default","query":"CrewAI agent lifecycle","max_results":4}'

curl -N http://localhost:8000/stream \
  -H "Content-Type: application/json" \
  -d '{
        "thread_id": "thread_1",
        "run_id": "run_001",
        "messages": [
          { "role": "user", "content": "Summarize the CrewAI agent lifecycle." }
        ]
      }'
Streaming payload shape: 
{"type":"text_delta","content":"...","thread_id":"...","run_id":"..."}
{"type":"text_done","thread_id":"...","run_id":"..."}
{"type":"done","thread_id":"...","run_id":"..."}

​
Crew internals (for reference)

knowledge_agent/knowledge_manager.py builds a search tool per namespace, wired into a CrewAI agent: 
search_tool = self._create_search_tool(normalised)
agent = Agent(
    role="Knowledge Librarian",
    goal="Answer user questions with relevant citations from the knowledge base.",
    tools=[search_tool],
    llm=model,
)
task = Task(
    description="Use search_knowledge_base before answering.\nConversation: {conversation}\nLatest: {question}",
    expected_output="A concise, cited answer grounded in ingested docs.",
    agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], process=Process.sequential)

​
Wire it to CometChat

  • Dashboard → AI Agents → Provider: CrewAI → Agent ID (e.g., knowledge) → Deployment URL = your public /stream.
  • The SSE stream is newline-delimited JSON; CometChat AG-UI adapters can parse text_delta/text_done to render partials and stop on done.
  • Use namespaces to keep customer/workspace data separate; pass namespace in the payload or inside tool_params.namespace.
  • Keep secrets server-side; add auth headers on the FastAPI route if needed.