ContextGem 1.0 launches on Product Hunt, adding decision models alongside LLMs for fast, low-cost document data extraction, plus Docling file support and tools for agents. The update introduces a model group feature that routes each question to the most suitable model.
<p>
Decision models join LLMs to extract data from documents
</p>
<p>
<a href="https://www.producthunt.com/products/contextgem?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a>
|
<a href="https://www.producthunt.com/r/p/1294110?app_id=339">Link</a>
</p>
# ContextGem: Extract data from documents using LLMs and decision models | Product Hunt
Source: [https://www.producthunt.com/products/contextgem](https://www.producthunt.com/products/contextgem)
This is the 2nd launch from ContextGem\.
[View more](https://www.producthunt.com/products/contextgem/launches)
## ContextGem 1\.0
Launching today
Decision models join LLMs to extract data from documents
New in 1\.0: decision models next to LLMs\. They answer closed questions with the probability of each answer, fast and at a low cost, and a model group sends each question to the model that suits it\. Also new: Docling for your files, and tools for agents\.
Free
Launch tags:
[Open Source](https://www.producthunt.com/topics/open-source)•[Developer Tools](https://www.producthunt.com/topics/developer-tools)•[Artificial Intelligence](https://www.producthunt.com/topics/artificial-intelligence)
Launch Team
/ Built With
[https://www.producthunt.com/@sergiishcherbak](https://www.producthunt.com/@sergiishcherbak)[](https://www.producthunt.com/products/omerta)
[](https://www.producthunt.com/products/litellm)
[](https://www.producthunt.com/products/pydantic)
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Gemma 4 introduces a new generation of open-weight, natively multimodal language models with dense and Mixture-of-Experts architectures, featuring thinking mode for advanced reasoning, improved efficiency, and long-context capabilities.
Google introduces Gemma 3, a collection of lightweight open models (1B, 4B, 12B, 27B) designed to run on single GPUs or TPUs, featuring support for 140+ languages, 128k context window, and multimodal capabilities. The models outperform larger competitors like Llama 3 and DeepSeek-V3 while maintaining efficiency for on-device deployment.
Google DeepMind releases Gemma 4, a frontier multimodal model family available on Hugging Face with Apache 2 licensing, optimized for on-device deployment and supported by various inference libraries.
Google released Gemma 4 12B, an Apache 2.0 open-source multimodal model supporting text, vision, and audio with a 256K context window. The article provides a guide for running it locally on Macs using Ollama, LM Studio, or llama.cpp.