Skip to main content

​
Minimal server

# server.py
from langchat import LangChat
from langchat.api import create_app
from langchat.providers import OpenAI, Pinecone, Supabase
import uvicorn

LangChat.load_env()

app = create_app(
    llm=OpenAI("gpt-4o-mini"),
    vector_db=Pinecone("my-index"),
    db=Supabase(),
)

if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=8000)

python server.py

​
Endpoints

MethodPathDescription
GET/Redirects to /frontend/
GET/healthHealth check — returns status and version
GET/frontend/Built-in chat UI (served from Vite build)
POST/chatSend a message

​
POST /chat

Accepts multipart/form-data:
FieldTypeRequiredDescription
querystring✓User message
userIdstring✓User identifier
platformstring✓Platform namespace (e.g. "web")
imagefile—Optional image attachment
Example with curl: 
curl -X POST http://localhost:8000/chat \
  -F "query=What is our return policy?" \
  -F "userId=alice" \
  -F "platform=web"
Response: 
{
  "response": "You can return items within 30 days...",
  "user_id": "alice",
  "timestamp": "2025-01-15T10:30:00.123Z",
  "status": "success",
  "response_time": 1.23
}

​
GET /health

curl http://localhost:8000/health

{
  "status": "healthy",
  "timestamp": "2025-01-15T10:30:00.123Z",
  "version": "1.0.1"
}

​
Custom prompt in API server

app = create_app(
    llm=OpenAI("gpt-4o-mini"),
    vector_db=Pinecone("my-index"),
    db=Supabase(),
    prompt_template="""You are Aria, support agent for Acme Corp.

Context:
{context}

History:
{chat_history}

Customer: {question}
Aria:""",
)

​
Production server

For production, disable auto-reload and run multiple workers: 
# server.py
from langchat import LangChat
from langchat.api import create_app
from langchat.providers import OpenAI, Pinecone, Supabase

LangChat.load_env()

app = create_app(
    llm=OpenAI("gpt-4o-mini"),
    vector_db=Pinecone("my-index"),
    db=Supabase(),
    max_chat_history=20,
)

# Production: multiple workers, no reload
uvicorn server:app --host 0.0.0.0 --port 8000 --workers 4

​
Frontend build

The built-in UI is served from src/langchat/core/ui/dist/. Build it with: 
cd src/langchat/core/ui
npm install
npm run build
The UI is then available at http://localhost:8000/frontend/.

​
Docker

LangChat can auto-generate a Dockerfile: 
app = create_app(
    llm=OpenAI("gpt-4o-mini"),
    vector_db=Pinecone("my-index"),
    db=Supabase(),
    auto_generate_docker=True,   # generates Dockerfile + .dockerignore
)
Or write your own: 
FROM python:3.11-slim

WORKDIR /app
COPY . .

RUN pip install langchat uvicorn

ENV OPENAI_API_KEY=""
ENV PINECONE_API_KEY=""
ENV SUPABASE_URL=""
ENV SUPABASE_KEY=""

EXPOSE 8000
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8000"]

docker build -t my-chatbot .
docker run -p 8000:8000 \
  -e OPENAI_API_KEY=sk-... \
  -e PINECONE_API_KEY=pcsk-... \
  -e SUPABASE_URL=https://xxxx.supabase.co \
  -e SUPABASE_KEY=eyJ... \
  my-chatbot

​
Adding custom routes

Inject your own FastAPI routes alongside LangChat’s: 
from fastapi import APIRouter
from langchat.api import create_app

my_router = APIRouter()

@my_router.get("/status")
async def status():
    return {"my_service": "running"}

@my_router.post("/feedback")
async def feedback(message_id: str, rating: int):
    # save feedback to your DB
    return {"saved": True}

app = create_app(
    llm=OpenAI("gpt-4o-mini"),
    vector_db=Pinecone("my-index"),
    db=Supabase(),
    custom_routes=[my_router],
)