# xusenlinzy/api-for-open-llm

Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc. 开源大模型的统一后端接口

Repository: https://github.com/xusenlinzy/api-for-open-llm
Canonical: https://ross.abutalabs.com/products/api-for-open-llm
Language: Python
License: Apache-2.0
License Family: permissive
Topics: docker, langchain, llms, nlp, openai, chatglm, llama, baichuan, internlm, llama2, qwen, xverse, sqlcoder, code-llama
Last push: 2024-09-26T07:47:57+00:00

## Health v2 (maintenance only)
Score: 20/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 85
- inputs: {"age_days": 1198, "days_push": 706, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2460, forks 271 (observed 2026-08-28T04:06:53.423928+00:00)

## What it is
A Python server that exposes open-source large language models (LLaMA, ChatGLM, Qwen, Baichuan, Falcon, etc.) behind an OpenAI-compatible API. It supports streaming responses, embeddings, reranking, LoRA adapters, and vLLM-accelerated inference so open models can drop in as ChatGPT replacements.

## Use cases
- serve open-source llm with openai compatible api
- self-host chatgpt alternative backend
- use langchain with local open llm
- run chatglm or qwen behind openai api
- deploy llm server with streaming responses
- expose embeddings endpoint for rag knowledge base

## When to choose
- you want existing OpenAI SDK clients to work with open models
- you need LangChain compatibility and embeddings for RAG
- you want one unified backend for many open LLM families
- you want vLLM-accelerated serving with concurrency

## When to avoid
- you only need OpenAI's hosted models
- you need a production-grade inference server with broad model coverage like vLLM or TGI directly
- you need non-OpenAI API styles or heavy enterprise features

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, api-framework, http-server, rag
- domain: large-language-models, artificial-intelligence, self-hosted, apis
- platform: python, self-hosted
- tags: openai-compatible-api, chatglm, llama, qwen, vllm, langchain, streaming, embeddings, docker, gpu, linux

## Member repositories
- xusenlinzy/api-for-open-llm (main) score 20

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:53.423928+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:29:20.761140+00:00, confidence not recorded.
  - readme: https://github.com/xusenlinzy/api-for-open-llm (fetched 2026-08-28T04:06:53.423928+00:00, sha 9e7199ff6b3a)
- Data as of 2026-08-30T08:39:29.467469+00:00.