LangGraph OpenAI Serve
Serve LangGraph graphs through an OpenAI-compatible /v1 API so existing
OpenAI SDKs, Chainlit, Open WebUI, and similar clients can call them without a
project-specific protocol.
Install
Use uv for project dependency management:
uv add langgraph-openai-serve
The equivalent pip command is:
pip install langgraph-openai-serve
For deployments that use PostgreSQL for LangGraph checkpoints, Store data, or cross-worker interrupt coordination, install the optional integration:
uv add "langgraph-openai-serve[postgres]"
For built-in Langfuse tracing, install the tracing integration:
uv add "langgraph-openai-serve[tracing]"
Set LGOS_ENABLE_LANGFUSE=true together with LANGFUSE_PUBLIC_KEY and
LANGFUSE_SECRET_KEY. LGOS creates the callback lazily on the first graph run;
importing the package never initializes Langfuse.
The package contains the OpenAI-compatible server integration, not a built-in
LLM graph. Applications register their own graphs. The demo/ checkout keeps
each deployable application in an independent uv project with its own lockfile.
Its lgos-rag example indexes a small corpus packaged with the demo API, so the
entire directory can be copied and run without files from this repository.
Quick Demo
From this repository, prepare the demo environment and PostgreSQL:
cd demo
cp .env.example .env
docker compose -f docker/compose/demo.yml up -d lgos-db
uv run --directory api --env-file ../.env \
--locked --with-editable ../.. lgos-demo-api-setup
uv run --directory api --env-file ../.env \
--locked --with-editable ../.. lgos-demo-api
Then call the demo with the OpenAI Python client:
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="DUMMY")
response = client.chat.completions.create(
model="custom-input-output-context",
messages=[{"role": "user", "content": "Show me custom schemas."}],
user="demo-user",
)
print(response.choices[0].message.content)
Use curl http://localhost:8000/v1/models only as a diagnostic to inspect the
registered demo graph names.
The optional editable overlay tests this checkout without changing the self-contained demo project or its lockfile. The demo publishes independent API and Chainlit images and uses official images for third-party services such as Open WebUI. See the demo Docker Compose guide.
The demo also includes a PostgreSQL-persistent Chainlit client. It uses a shared mock login by default, with PocketID OAuth available as an opt-in mode. See the Chainlit demo.
Use In FastAPI
from fastapi import FastAPI
from langgraph_openai_serve import GraphConfig, GraphRegistry, LanggraphOpenaiServe
from your_graphs import my_graph
app = FastAPI()
graphs = GraphRegistry(
registry={
"my-graph": GraphConfig(
graph=my_graph,
description="Answer questions with my LangGraph workflow.",
streamable_node_names=["generate"],
)
}
)
LanggraphOpenaiServe(app=app, graphs=graphs).bind_openai_api()
The default base URL is {host}/v1. Registered graph names become OpenAI model
values.
Docs
- Documentation home: docs/index.md
- Package getting started: docs/getting-started.md
- Architecture and state ownership: docs/explanation/architecture.md
- Self-contained demo stack: docs/demo/index.md
- Runnable demo API: docs/demo/api.md
- Demo graph catalog: docs/demo/graphs/
- OpenAI clients: docs/tutorials/openai-clients.md
- Custom graphs: docs/tutorials/custom-graphs.md
- LangGraph runtime settings: docs/how-to-guides/langgraph-runtime-settings.md
- OpenAI-compatible proxies: docs/how-to-guides/openai-proxies.md
- API and configuration: docs/reference.md
- Compatibility contract: docs/explanation/openai-compatibility.md
1 maintainer
Release files for langgraph_openai_serve 0.14.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| langgraph_openai_serve-0.14.0.tar.gz | 37.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langgraph_openai_serve-0.14.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 90.9 kB
Release files / langgraph_openai_serve-0.14.0.tar.gz
| Download URL | langgraph_openai_serve-0.14.0.tar.gz |
|---|---|
| Size | 37.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ff2b0434b6baabd2b755801cb1501c94eb0b26f290c0ee62cfd1d6f78ccae3a8
|
|
BLAKE2b-256 checksum How to use checksums |
550f6fcb471af6f7c038b9426f9ea2b8bea3f9c3c4fa8016b5b6e535862749ee
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / langgraph_openai_serve-0.14.0-py3-none-any.whl
| Download URL | langgraph_openai_serve-0.14.0-py3-none-any.whl |
|---|---|
| Size | 53.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8774eacea8e6cb37f87b4513bf6d73754aef350c42d71a323fb3a2764a57fcab
|
|
BLAKE2b-256 checksum How to use checksums |
d5407f549a3a9e1c2f7cd574173e424e32b9724899c7caf77c04ae0992a4e97a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
