sparrow
Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
What is sparrow?
Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
Overview of sparrow
What it is
Sparrow is an API-first platform for enterprise document intelligence. It combines structured data extraction from documents (invoices, statements, tables) with workflow agents and decision agents. The platform provides RESTful APIs for structured data extraction, instruction processing, and multi-agent workflow orchestration, all running on the user's own infrastructure with no external API calls or cloud dependencies.
Key features
- Universal Document Processing: Handles invoices, receipts, forms, bank statements, tables
- Pluggable Architecture: Mix and match different pipelines (Sparrow Parse, Instructor, Agents)
- Multiple Backends: MLX on Apple Silicon, vLLM on NVIDIA, Ollama, Hugging Face, Mistral OCR
- Schema Validation: JSON schema-based extraction with automatic validation
- API-First Design: RESTful APIs for easy integration
- Instruction Calling: Text processing, validation, decision making with Gemma, Mistral, Qwen 3.6, etc.
- Enterprise Ready: Rate limiting, usage analytics, commercial licensing available
Use cases
Document data extraction from invoices, receipts, bank statements, forms, and tables. Instruction processing for text validation and decision making. Multi-step workflow orchestration using custom agents with visual monitoring via Prefect.
Getting started
bash# 1. Install pyenv and Python 3.12.10pyenv install 3.12.10pyenv global 3.12.10# 2. Create virtual environmentpython -m venv .env_sparrow_parsesource .env_sparrow_parse/bin/activate # Linux/Mac# or .env_sparrow_parseScriptsactivate # Windows# 3. Install Sparrow Parse pipelinegit clone https://github.com/katanaml/sparrow.gitcd sparrow/sparrow-ml/llmpip install -r requirements_sparrow_parse.txt# 4. For macOS: Install poppler for PDF processingbrew install poppler# 5. Start the API serverpython api.pyFor complete installation instructions, see the repository README.
License and pricing
Licensed under GPL-3.0 (open source). Commercial licensing is also available as stated in the README.
Based on the project's public README and repository metadata.