ContextGem

ContextGem is an open-source Python framework by Sergii Shcherbak (Shcherbak AI AS). The README says it lets you "extract structured data and insights from documents using LLMs and decision models." You define the facts you're looking for, and it pulls them out of your files with a note of where each one came from. It's a library developers call from their own code, installed with pip or uv. What sets it apart is that extracted facts come with their sources, so they're easy to check.

Who it's for:Developers who need to pull information out of large numbers of files. Readers who don't write code won't get much use from it.

Before you start: You need Python 3.11 or later; version 1.x no longer supports Python 3.10. File contents go to the LLM service you configure, which means uploads and usage costs if you use an outside provider. How well it handles other languages depends on the model; we haven't tested it. Use non-sensitive documents you're allowed to process, and have a person check the extracted facts. The code is free under the Apache-2.0 license. The docs are in English.

Based on the project's public documentation. Not tested by AI Inspiration World.