v0.4.1

Sparrow UI Dashboard

Added dashboard to Sparrow UI to visualize system performance

v0.4.0

Free tier and new vision backend models

Sparrow is updated with new free tier functionality for https://sparrow.katanaml.io/. New vision backend models are integrated, such as Mistral Small 3.1 and Qwen 2.5 72B

v0.3.0

Sparrow Agent

Added Sparrow Agent functionality to orchestrate complex document processing tasks. This new component allows you to combine multiple data extraction operations into a single workflow with visual monitoring and tracking through Prefect integration. Users can now process documents through an intuitive API that handles classification, extraction, and validation in one seamless pipeline.

v0.2.4

Image Cropping and UI Shell updates

Implemented image cropping, this is useful for form pages, to reduce overall image size. Add various UI improvements to Sparrow UI Shell, enabled better logging

This release brings Sparrow deployment on local Mac Mini M4 Pro 64GB machine - https://sparrow.katanaml.io

v0.2.3

Table processing

Added support auto detect tables and send cropped table images for inference

v0.2.2

Multi-page PDF document support

Added support for multi-page PDF document through CMD and API

v0.2.1

Dependencies cleanup

Removed dependencies to LlamaIndex, Haystack, Unstructured and other libraries, as main Sparrow focus is on Sparrow Parse

v0.2.0

Sparrow Parse with Vision LLM support

This release starts new phase in Sparrow development - Vision LLM support for document data processing.

1. Sparrow Parse library supports Vision LLM
2. Sparrow Parse provides factory class implementation to run inference locally or on cloud GPU
3. Sparrow supports JSON as input query
4. JSON query validation and LLM response JSON validation is performed