OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Contextgem

ContextGem is an open-source Python framework for extracting structured data and insights from documents with large language models. It provides document, concept, and aspect abstractions for building extraction workflows, including nested analyses and multi-document pipelines.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Contextgem — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use ContextGem when an application needs structured LLM extraction from documents, especially when results should include references to source passages or be organized into multi-stage analyses.

Who it is for

  • Python developers building document-intelligence applications
  • Teams extracting structured facts, concepts, or assessments from documents
  • Developers creating contract-analysis and other document-review pipelines

Documented uses

  • Extract defined information from document text or images
  • Identify topics, themes, categories, entities, facts, conclusions, or assessments
  • Associate extracted items with document passages and justifications
  • Compose nested or multi-LLM extraction workflows across documents
Before you choose

Requirements & limits

The project is open source under Apache-2.0 and distributed as a Python package. The README lists Python 3.10–3.14 and installation through uv or pip. Its extraction example requires an LLM provider model and API key.

  • The developer configures the model and provider credentials; ContextGem supplies the document-extraction framework.
  • The README demonstrates references at sentence level and brief justifications as configurable extraction options.
  • The framework supports nested aspects and concepts, as well as multi-LLM workflows across several documents.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a document extraction workflow

Install ContextGem and configure the elements shown in its legal-document extraction example.

Before you start

  • Python 3.10–3.14
  • An LLM provider and API key; the example uses OpenAI gpt-4o-mini
  • A document represented as text

Steps

  1. Install ContextGem using the command below or the command below.

    Documented command
    uv add contextgem
    Documented command
    pip install -U contextgem

  2. Create a Document with the document text and add a StringConcept describing the information to extract.

  3. Configure DocumentLLM with a model and provider API key.

  4. Call llm.extract_all(doc) and inspect the concept's extracted items.

Expected outcome

A document object containing extracted items; the example configures sentence-level references and brief justifications for anomaly findings.

Guide limitations

  • The example requires a configured LLM provider and API key.
  • The README example demonstrates legal-text anomaly extraction; it does not establish accuracy for other documents or tasks.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
11 October 2026
Original website title
shcherbak-ai/contextgem · Official homepage title · retained in its source language
How we review sourcesSuggest a correction