--- id: reductoai version: "0.22.0" license: Apache-2.0 license_treatment: permissive maintenance: active --- # reductoai — The official Python library for the reducto API License: permissive · Maintenance: active · Downloads: 3.9M/mo ## What it is and what it does Reductoai is an official Python SDK for the Reducto document processing API. It provides a typed client interface to submit documents to Reducto's remote parsing service and retrieve structured results. The library includes full type hints for requests and responses via pydantic, making it suitable for IDE autocomplete and static type checking. The package supports both synchronous and asynchronous workflows, both powered by httpx. It handles authentication via API key, automatic retries on transient failures, configurable timeouts, and detailed error types for different HTTP status codes. Responses are pydantic models with helper methods for JSON serialization and dictionary conversion. Use it for: - Submit PDFs or images to Reducto's cloud service to extract structured data or enhanced content. - Build async workflows that submit multiple documents in parallel and collect results without blocking. - Integrate document parsing into a web service that needs typed, validated API responses. - Handle API errors gracefully with specific exception types for rate limits, authentication, and connection failures. - Use environment variables to manage API credentials securely across different deployment environments. ## Worth the install? AI-flagged interpretation of the facts above — verify before relying. A Python client library for the Reducto REST API that parses and processes documents through remote API calls, with both synchronous and asynchronous interfaces. Yes, if you need to call the Reducto API from Python. The library is actively maintained, has low install friction, permissive Apache-2.0 licensing, no known vulnerabilities, and provides a well-typed interface with both sync and async support. The main constraint is that it requires a valid Reducto API key and internet access to the service; it is not a standalone document processor. ## Install pip install reductoai uv add reductoai poetry add reductoai ## Installing reductoai Before you install: Low install friction with a pure-Python wheel and standard dependencies. Active maintenance with recent commits and support for current Python versions (3.9–3.14). License in practice: Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects. Quickstart: pip install reductoai import os from reductoai import Reducto client = Reducto(api_key=os.environ.get("REDUCTO_API_KEY")) response = client.parse.run(input="https://pdfobject.com/pdf/sample.pdf") Requires a valid REDUCTO_API_KEY environment variable or explicit api_key parameter to authenticate with the Reducto service. Verify before relying: - Whether the Reducto service itself is production-ready and has documented SLAs for availability and latency. - Cost structure and rate limits for API calls beyond the free tier, if any. - Whether aiohttp integration is stable and recommended for production async workloads. ## Package facts - License: Apache-2.0 (permissive) - Python support: supports_current - Install friction: low - Maintenance: active - Downloads: 3.9M/month (top 5,000 on PyPI) - Known vulnerabilities: none known ## Tags reducto api client, document parsing python, pdf processing api, async http client library, rest api python sdk, typed api wrapper, document extraction, rest-api-client, async-support, document-processing [View on SkillFed](https://skillfed.io/packages/reductoai) · [View on PyPI](https://pypi.org/project/reductoai/)