katanaml/sparrow
Structured data extraction and instruction calling with ML, LLM and Vision LLM
Combines pluggable extraction pipelines (Sparrow Parse for vision, Instructor for text) with multi-backend support (MLX for Apple Silicon, Ollama, vLLM, HuggingFace Cloud) to handle diverse document types as JSON-validated schemas. Includes agent-based workflow orchestration for multi-step processing, OCR preprocessing, and a web UI with real-time visualization and bounding box annotations for extracted data.
5,129 stars. Actively maintained with 20 commits in the last 30 days.
Stars
5,129
Forks
511
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/katanaml/sparrow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
WangRongsheng/awesome-LLM-resources
🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the...
luhengshiwo/LLMForEverybody
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈
LazyAGI/LazyLLM
Easiest and laziest way for building multi-agent LLMs applications.
SylphAI-Inc/AdalFlow
AdalFlow: The library to build & auto-optimize LLM applications.
PacktPublishing/LLM-Engineers-Handbook
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS...