tomdyson/microllama
The smallest possible LLM API
This project helps you quickly create a custom question-and-answer system based on your own content. You provide your documents as a JSON file, and it generates an API and an optional web interface where users can ask questions and get answers drawn directly from your sources. This is ideal for technical writers, customer support teams, or anyone who needs to make internal documentation easily searchable and queryable.
Available on PyPI.
Use this if you want to make your own specific set of documents, like product manuals or company policies, instantly queryable with a natural language interface without needing to build complex AI systems from scratch.
Not ideal if you need a solution that works entirely offline, without relying on external API services for language processing, or if you need a very deep, conversational AI experience.
Stars
66
Forks
5
Language
Python
License
MIT
Category
Last pushed
Oct 22, 2025
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/tomdyson/microllama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thu-pacman/chitu
High-performance inference framework for large language models, focusing on efficiency,...
NotPunchnox/rkllama
Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning...
sophgo/LLM-TPU
Run generative AI models in sophgo BM1684X/BM1688
Deep-Spark/DeepSparkHub
DeepSparkHub selects hundreds of application algorithms and models, covering various fields of...
howard-hou/VisualRWKV
VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle...