Custom model is not working in langsmith playground

[muhammedhishamc]

I setup the langserve with custom model and the server is working fine. but the langsmith playground is not sending request to the local server

code in local server:

from fastapi import FastAPI
from langchain_openai import ChatOpenAI
from langserve import add_routes
import os
from fastapi.middleware.cors import CORSMiddleware
import uvicorn

client = ChatOpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ['LLM_API_KEY'],
    model="openai/gpt-4o-mini",
).configurable_fields()

app = FastAPI(
    title="LangChain Server",
    version="1.0",
    description="A simple api server using Langchain's Runnable interfaces",
)
add_routes(
    app,
    client,
    path="/openai",
)

# Set all CORS enabled origins
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
    expose_headers=["*"],
)

if _name_ == "_main_":
    uvicorn.run(app, host="0.0.0.0", port=8000)

Idea or request for content:

No response

[langchain-infra]

Hi @muhammedhishamc , you will need to host this to an external URL as our playground service has no way to reach your model server today. We do not send requests to the custom model directly from the browser.