Skip to main content

lfx-openai-compatible

Generic OpenAI-compatible endpoints as a first-class Langflow model provider, packaged as a standalone Extension Bundle.

Registers an OpenAI Compatible model provider that appears in Langflow's unified model picker alongside the built-in providers. Any service that speaks the OpenAI HTTP API shape can be configured through it — for example:

Provider Base URL
OpenRouter https://openrouter.ai/api/v1
Together AI https://api.together.xyz/v1
Groq https://api.groq.com/openai/v1
Fireworks AI https://api.fireworks.ai/inference/v1
Self-hosted vLLM / TGI / LM Studio http://localhost:8000/v1

The provider reuses the ChatOpenAI / OpenAIEmbeddings classes and discovers the served models live from the endpoint's /v1/models route — the same model is therefore offered in both the Language Model and Embedding Model contexts.

Unlike a component bundle, this ships no component: it contributes a provider through the providers[] block in extension.json, which Langflow's provider registry merges into the unified model system. It edits no Langflow core files.

Configure

Set the endpoint (and, if it requires one, an API key) under Settings → Model Providers → OpenAI Compatible, or via environment variables:

  • OPENAI_COMPATIBLE_BASE_URL — base URL of the endpoint, e.g. https://openrouter.ai/api or http://localhost:8000 (required). The bundle's provider manifest declares base_url_suffix: /v1, so Langflow appends /v1 when it is missing and preserves endpoints that already include it.
  • OPENAI_COMPATIBLE_API_KEY — bearer token, if the endpoint enforces one (optional; local servers without auth do not need it).

The provider holds one endpoint at a time. For a second concurrent custom endpoint, combine it with the built-in OpenAI provider's Base URL override or the vLLM provider (lfx-vllm).

Install

pip install lfx-openai-compatible

The bundle is registered automatically via the langflow.extensions entry-point. Restart your Langflow server and select OpenAI Compatible in any Language Model or Embedding Model field.

Develop

cd src/bundles/openai-compatible
pip install -e .
lfx extension validate src/lfx_openai_compatible

Credit

Resolves the feature request in #12839. Follows the provider-bundle pattern established by lfx-vllm (#13919).

Metadata

Release files for lfx-openai-compatible 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for lfx-openai-compatible 0.2.1
File Interpreter ABI Platform Actions
lfx_openai_compatible-0.2.1-py3-none-any.whl Python 3 none any Details for lfx_openai_compatible-0.2.1-py3-none-any.whl

Release files / lfx_openai_compatible-0.2.1-py3-none-any.whl

Download URL lfx_openai_compatible-0.2.1-py3-none-any.whl
Size 6.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7d58c4dde2301af6883564af2352629ee73c557f150b9cd48f152f48ac3b2950
BLAKE2b-256 checksum
How to use checksums
ee5a6e46dc80bd627514e98a0e0947e78d1d8503ac852bd0d46ed65aedd7a4b5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","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}

Security for lfx-openai-compatible 0.2.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page