DataFog/vlm-api

REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model

29
/ 100
Experimental

This API helps document analysts, researchers, and knowledge managers improve information retrieval from visually rich documents like reports, infographics, or manuals. You input a document (image or PDF) and a text query, and it outputs a highlighted document showing where your query relates visually, along with a detailed similarity score. It helps you understand which parts of a document's images or layouts are most relevant to your search.

No commits in the last 6 months.

Use this if you need to find specific information within documents that heavily rely on visual elements like charts, diagrams, or complex layouts, and traditional text-based search tools often miss the context.

Not ideal if your documents are primarily text-based with minimal visual content, as standard text retrieval methods might be more efficient.

document-analysis information-retrieval research-analytics visual-search knowledge-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

MIT

Last pushed

Nov 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/DataFog/vlm-api"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.