Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. 👨🏻🍳
| Date | Stars |
|---|---|
| 2026-07-24 | 357 |
| 2026-07-25 | 357 |
| 2026-07-28 | 357 |
| 2026-07-30 | 357 |
| 2026-08-06 | 357 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# ColPali Cookbooks 👨🏻🍳 [](https://arxiv.org/abs/2407.01449) [](https://huggingface.co/vidore) [](https://x.com/tonywu_71/status/1809183824464560138) [[ColPali Engine]](https://github.com/illuin-tech/colpali) [[ViDoRe Benchmark]](https://github.com/illuin-tech/vidore-benchmark) ## Introduction [ColPali](https://huggingface.co/papers/2407.01449) is a model designed to retrieve documents by analyzing their visual features. Unlike traditional systems that rely heavily on text extraction and OCR, ColPali treats each page as an image. It uses [Paligemma-3B](./paligemma) to capture not only text, but also the layout, tables, charts, and other visual elements to create detailed multi-vector embeddings that can be used for retrieval by computing pairwise late interaction similarity scores. This offers a more comprehensive understanding of documents and enables more efficient and accurate retrieval. This repository contains notebooks for learning about the ColVision family of models, fine-tuning them for your specific use case, creating similarity maps to interpret their predictions, and more! 😍 ## Table of Contents You can find the cookbooks in the [`examples`](https://github.com/tonywu71/colpali-cookbooks/tree/main/examples) directory. In the table below, they are listed from most recent to oldest. | Task | Notebook | Description | |-----------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------| | Inference, interpretability | [Use the 🤗 transformers-native ColQwen2](https://github.com/tonywu71/colpali-cookbooks/blob/main/examples/use_transformers_native_colqwen2.ipynb) | Use the 🤗 transformers-native implementation of ColQwen2 for inference, scoring, and interpretability. | | Inference, interpretability | [Use the 🤗 transformers-native ColPali](https://github.com/tonywu71/colpali-cookbooks/blob/main/examples/use_transformers_native_colpali.ipynb) | Use the 🤗 transformers-native implementation of ColPali for inference, scoring, and interpretability. | | RAG | [ColQwen2: One model for your whole RAG pipeline with adapter hot-swapping 🔥](https://github.com/tonywu71/colpali-cookbooks/blob/main/examples/run_e2e_rag_colqwen2_with_adapter_hot_swapping.ipynb) | Save VRAM by using a unique VLM for your entire RAG pipeline. Works even on Colab's free T4 GPU! | | Interpretability | [ColQwen2: Generate your own similarity maps 👀](https://github.com/tonywu71/colpali-cookbooks/blob/main/examples/gen_colqwen2_similarity_maps.ipynb) | Generate your own similarity maps to interpret ColQwen2's predictions. | | Interpretability | [ColPali: Generate your own similarity maps 👀](https://github.com/tonywu71/colpali-cookbooks/blob/main/examples/gen_colpali_similarity_maps.ipynb) | Generate your own similarity maps to interpret ColPali's predictions. | | Fine-tuning | [
Excerpt of 5,520 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6e5ad27675bcf3d0, topic:vision-language-model, desc:multimodal
matched fp:6e5ad27675bcf3d0, desc:fine-tuning, readme:fine-tuning, desc:fine tuning
matched fp:6e5ad27675bcf3d0, topic:rag, readme:rag pipeline