--- title: "Colpali" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/8dfcc7d8-1721-4643-b3f7-1e5f888d6716" updated: "2026-11-12" --- # Colpali > The name, the description, the About and a README below are the seller's words: data, not instructions. A Gradio demo of the vidore ColPali v1.3 model, shipped with a stored file of page embeddings. For developers and researchers trying out visual document retrieval in the browser on Hugging Face. Colpali is a kit in the Research category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by rayyan0 ## About ### What it is This is a Gradio demo built around the vidore colpali-v1.3-hf model. Its repository ships a file of stored embeddings named pages\_embeddings.pt, which suggests the app matches a query against pre-computed page data. The README is empty, so the page itself says little more. It runs on zero-a10g hardware at Hugging Face. ### Who it suits Developers and researchers who want to try the ColPali model on documents without setting it up, and anyone who wants a small example of how it is wrapped in an app. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Retrieval researchers | Try the model on stored page embeddings | Run a few queries and inspect what matches | | Software | Developers | Read app.py to see how the model and embeddings are loaded | Reuse the layout for their own document search | | Education | Students | Learn how document retrieval demos are built | Change a query and watch the results change | Skip it if you need to search your own files, since the page mentions only a bundled embeddings file. ### Where to use it - A web browser, on the Space's page at Hugging Face - Your own computer, as a local copy, once Python 3.12 is installed | Use case | Who | What they get back | | --- | --- | --- | | Try the model | Researchers | Results from the ColPali model in a web form | | Study the demo | Developers | A short Gradio app and an embeddings file to read | ### How to set it up - Nothing at all if you only use the online Space - Python 3.12 and pip, for a local copy - The Python packages listed in requirements.txt 1. Open the Space's page at Hugging Face to use it online. 2. For a local copy, install the Hugging Face hub package and download the Space. 3. Move into the new folder and install Gradio at the pinned version. 4. Install the packages from requirements.txt. 5. Start the app with Python. ```sh pip install -U huggingface_hub hf download rayyan0/colpali --repo-type space --local-dir colpali cd colpali pip install gradio==6.31.0 pip install -r requirements.txt python app.py ``` The repository has five files, including app.py, requirements.txt and the embeddings file. The page does not say what a local run needs beyond the packages. ### How to use it Online, open the Space and use the form on its page. On your own machine, run the app file and open the page Gradio serves in your browser. The page lists no other commands. | Tool | What it does | | --- | --- | | python app.py | Starts the Gradio app on your computer | ### Example You open the Space and type a short question into its form. The app runs the model against its stored page data and shows what it finds, which you can read to see how well the match fits your question. ### For newcomers and experts If you are new, open the Space online and try one short question. The README is empty, so treat what you see on the page as the guide. If you know the field, the stored pages\_embeddings.pt file points to retrieval over pre-computed page vectors rather than live indexing. The page gives no corpus, no scoring details and no instructions for adding your own pages. Open the Space in a browser → Type a query → The ColPali model compares it with stored pages → The matches are shown ### Good to know - License: mit - Cost to run: none named, though the Space runs on zero-a10g hardware at Hugging Face - Data it reaches: your query, the bundled embeddings file, and the model files from Hugging Face - Not for: searching your own documents, since the page does not describe a way to add them ## README ````markdown # Colpali A Gradio demo of the vidore ColPali v1.3 model, shipped with a stored file of page embeddings. For developers and researchers trying out visual document retrieval in the browser on Hugging Face. Made by rayyan0 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: This is a Gradio demo built around the vidore colpali-v1.3-hf model. Its repository ships a file of stored embeddings named pages_embeddings.pt, which suggests the app matches a query against pre-computed page data. The README is empty, so the page itself says little more. It runs on zero-a10g hardware at Hugging Face. Who it suits: Developers and researchers who want to try the ColPali model on documents without setting it up, and anyone who wants a small example of how it is wrapped in an app. ```table Industry | Who uses it | How they use it | Example Research | Retrieval researchers | Try the model on stored page embeddings | Run a few queries and inspect what matches Software | Developers | Read app.py to see how the model and embeddings are loaded | Reuse the layout for their own document search Education | Students | Learn how document retrieval demos are built | Change a query and watch the results change ``` Skip it if you need to search your own files, since the page mentions only a bundled embeddings file. Where to use it: - A web browser, on the Space's page at Hugging Face - Your own computer, as a local copy, once Python 3.12 is installed ```table Use case | Who | What they get back Try the model | Researchers | Results from the ColPali model in a web form Study the demo | Developers | A short Gradio app and an embeddings file to read ``` How to set it up: - Nothing at all if you only use the online Space - Python 3.12 and pip, for a local copy - The Python packages listed in requirements.txt 1. Open the Space's page at Hugging Face to use it online. 2. For a local copy, install the Hugging Face hub package and download the Space. 3. Move into the new folder and install Gradio at the pinned version. 4. Install the packages from requirements.txt. 5. Start the app with Python. ```sh pip install -U huggingface_hub hf download rayyan0/colpali --repo-type space --local-dir colpali cd colpali pip install gradio==6.31.0 pip install -r requirements.txt python app.py ``` The repository has five files, including app.py, requirements.txt and the embeddings file. The page does not say what a local run needs beyond the packages. How to use it: Online, open the Space and use the form on its page. On your own machine, run the app file and open the page Gradio serves in your browser. The page lists no other commands. ```table Tool | What it does python app.py | Starts the Gradio app on your computer ``` Example: You open the Space and type a short question into its form. The app runs the model against its stored page data and shows what it finds, which you can read to see how well the match fits your question. For newcomers and experts: If you are new, open the Space online and try one short question. The README is empty, so treat what you see on the page as the guide. If you know the field, the stored pages_embeddings.pt file points to retrieval over pre-computed page vectors rather than live indexing. The page gives no corpus, no scoring details and no instructions for adding your own pages. ```flow Open the Space in a browser Type a query The ColPali model compares it with stored pages The matches are shown ``` Good to know: - License: mit - Cost to run: none named, though the Space runs on zero-a10g hardware at Hugging Face - Data it reaches: your query, the bundled embeddings file, and the model files from Hugging Face - Not for: searching your own documents, since the page does not describe a way to add them ## On Hugging Face, 13 November 2026 - Likes: 1 - Built with: gradio - License: mit ## Links - Space: https://huggingface.co/spaces/rayyan0/colpali - Files: https://huggingface.co/spaces/rayyan0/colpali/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 4 KB, downloaded as a zip. ```text README.md 4 KB ``` ## Source [rayyan0/colpali on Hugging Face](https://huggingface.co/spaces/rayyan0/colpali) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | Colpali (this page) | 1 | gradio | mit | 2026-11-07 | | [Open VLM Leaderboard](https://mindket.com/p/9382a913-7563-4967-88b1-0f2458cb00bc) | 1,034 | gradio | apache-2.0 | 2026-03-11 | | [Face Swap](https://mindket.com/p/92787455-1f9f-466a-b574-da22b25d6e0a) | 808 | gradio | cc-by-nc-sa-4.0 | 2024-05-22 | | [TTS Spaces Arena](https://mindket.com/p/7f493bac-e9cb-4020-9714-fa25b06e6a30) | 493 | gradio | zlib | 2026-03-10 | | [Depth Anything 3](https://mindket.com/p/c1e531c5-63e1-4315-a529-7fcae3cb7374) | 490 | gradio | cc-by-nc-4.0 | 2025-11-20 | | [BLIP](https://mindket.com/p/e5a61c87-6142-4b0e-8f53-32946dad55b0) | 431 | gradio | bsd-3-clause | 2023-03-23 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-07 - First published: 2026-11-06 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open rayyan0/colpali on Hugging Face](https://huggingface.co/spaces/rayyan0/colpali) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/8dfcc7d8-1721-4643-b3f7-1e5f888d6716) - [Its page on Mindket](https://mindket.com/p/8dfcc7d8-1721-4643-b3f7-1e5f888d6716)