64 lines
1.6 KiB
Python
64 lines
1.6 KiB
Python
#!/usr/bin/env python
|
|
"""Example LangChain server exposes multiple runnables (LLMs in this case)."""
|
|
|
|
from fastapi import FastAPI
|
|
from fastapi.responses import RedirectResponse
|
|
from langchain_anthropic import ChatAnthropic
|
|
from langchain_openai import ChatOpenAI
|
|
from langchain_google_genai import ChatGoogleGenerativeAI
|
|
|
|
from langserve import add_routes
|
|
|
|
import mlflow
|
|
|
|
import getpass
|
|
import os
|
|
|
|
os.environ["OPENAI_API_KEY"] = "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"
|
|
os.environ["GOOGLE_API_KEY"] = "AIzaSyDIO5PFKRV-kVjNzpsrOcC-KodUMO-VGAo"
|
|
|
|
mlflow.set_tracking_uri("http://localhost:5000")
|
|
mlflow.langchain.autolog()
|
|
|
|
app = FastAPI(
|
|
title="LangChain Server",
|
|
version="1.0",
|
|
description="Spin up a simple api server using Langchain's Runnable interfaces",
|
|
)
|
|
|
|
llm = ChatGoogleGenerativeAI(
|
|
model="gemini-2.0-flash-001",
|
|
temperature=0,
|
|
max_tokens=None,
|
|
timeout=None,
|
|
max_retries=2,
|
|
# other params...
|
|
)
|
|
|
|
openai_llm = ChatOpenAI(
|
|
model="gpt-4o",
|
|
temperature=0,
|
|
max_tokens=None,
|
|
timeout=None,
|
|
max_retries=2,
|
|
# api_key="...", # if you prefer to pass api key in directly instaed of using env vars
|
|
# base_url="...",
|
|
# organization="...",
|
|
# other params...
|
|
)
|
|
|
|
add_routes(
|
|
app,
|
|
llm,
|
|
path="/gemeni",
|
|
)
|
|
|
|
@app.get("/")
|
|
async def redirect_root_to_docs():
|
|
return RedirectResponse("/gemeni/playground")
|
|
|
|
if __name__ == "__main__":
|
|
import uvicorn
|
|
|
|
uvicorn.run(app, host="0.0.0.0", port=9000)
|