{"categories":[{"label":"Text Processing","url":"https://skillfed.io/packages/category/text-processing"}],"enrichment":{"capability":"A Python client for the Chunkr document intelligence API that uploads files and images for processing, supporting both synchronous and asynchronous workflows.","skillfed_tags":["document-extraction","async-http-client","api-wrapper"],"use_cases":["Batch extract text, tables, and metadata from a folder of PDFs using async concurrency.","Build a document ingestion pipeline that converts images and scans into structured JSON matching a custom schema.","Integrate document processing into a web service that accepts file uploads and returns parsed results.","Automate OCR and layout analysis on high-resolution scans with configurable segmentation strategies.","Process documents across multiple worker processes to parallelize I/O-bound uploads and polling."],"what_it_does":"Chunkr-ai is a Python client library for the Chunkr document intelligence API. It wraps HTTP calls to a remote Chunkr service (hosted or self-deployed) to upload documents and images, then retrieve processed results with configurable extraction strategies. The client handles both synchronous and asynchronous I/O, supports file paths, file objects, and PIL images as input, and allows fine-grained control over processing via Configuration objects (OCR strategy, segmentation approach, chunk sizing, JSON schema extraction, and result expiration).\n\nThe package is built on httpx, pydantic, and python-dotenv, making it lightweight and straightforward to integrate into existing Python workflows. It supports concurrent processing via asyncio or multiprocessing, and manages resource cleanup through context-aware close methods. The primary use case is extracting structured or semi-structured data from unstructured documents at scale, with the actual intelligence work delegated to the Chunkr backend.","worth_installing":"Yes, if you need to integrate Chunkr's document processing service into a Python application. The client is straightforward to use, supports both sync and async patterns, and has no known vulnerabilities. Install friction is low. However, you depend entirely on the Chunkr backend's availability and the package's aging maintenance status suggests reduced active development\u2014verify that the service meets your reliability and support expectations before committing."},"id":"chunkr-ai","links":{"html":"https://skillfed.io/packages/chunkr-ai","md":"https://skillfed.io/packages/chunkr-ai.md","pypi":"https://pypi.org/project/chunkr-ai/"},"maintenance":{"status":"aging"},"meta":{"latest_release":"2025-08-06","license_spdx":null,"license_treatment":"permissive","name":"chunkr-ai","python_support":"supports_current","summary":"Python client for Chunkr: open source document intelligence"},"popularity":{"monthly_downloads":3834366,"position":2486,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"0.3.7"}