fcakyon/autollm

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

1005 stars · 97 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AutoLLM is a Python library for rapidly building RAG-based LLM web apps and APIs, offering a unified API over 100+ LLM providers and 20+ vector databases with one-line query engine and FastAPI setup. It wraps LlamaIndex and LangChain to simplify shipping retrieval-augmented chat applications.

Use cases

• build a rag chatbot over my documents
• create an llm api server in one line
• query pdfs with a large language model
• unified interface for openai anthropic cohere llms
• ship a question answering web app fast
• connect multiple vector databases to an llm

When to choose

• you want a minimal-code RAG pipeline with FastAPI or Gradio deployment
• you need to swap between many LLM providers and vector stores behind one API
• you want built-in cost calculation across providers

When to avoid

• you need fine-grained control over retrieval and prompting that raw LlamaIndex gives
• you require a permissive license for closed-source use (AGPL-3.0)
• you need actively maintained software - releases stopped in early 2024

Facets

library · maturity maintenance

rag llm-inference web-framework vector-database api-framework large-language-models artificial-intelligence web-development python self-hosted llamaindex langchain fastapi gradio openai multi-provider-llm query-engine retrieval-augmented-generation docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="fcakyon/autollm")