Azure-Samples/rag-as-a-service-with-vision
This repository offers a Python framework for a retrieval-augmented generation (RAG) pipeline using text and images from MHTML documents, leveraging Azure AI and OpenAI services. It includes ingestion and enrichment flows, a RAG with Vision pipeline, and evaluation tools.
This framework helps knowledge workers like researchers or analysts quickly get answers from complex documents that mix text and images, such as web archives or reports. You feed it MHTML files, and it uses AI to understand both the words and pictures, then provides precise answers to your questions. It's designed for anyone needing to extract insights from rich, multi-modal content.
Use this if you need to build a system that can accurately answer questions by searching and understanding both text and images within archived web pages or other MHTML documents.
Not ideal if your documents are purely text-based or if you don't need to incorporate visual information from images into your search and answer generation.
Stars
34
Forks
7
Language
Python
License
MIT
Category
Last pushed
Nov 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Azure-Samples/rag-as-a-service-with-vision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pguso/rag-from-scratch
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of...
microsoft/RAG_Hack
Hack Together: RAG Hack | Register, Learn, Hack
intersystems-community/iris-vector-rag
Enterprise RAG pipelines with native IRIS vector search. 6 production implementations with RAGAS...
huangjia2019/rag-project01-framework
[RAG训练营] u.geekbang.org/subject/airag/1009927 这是我用Cursor自行制作的RAG Framework，好处是可以掌控RAG每一个环节的教学细节。
fivetran/dbt_unified_rag
Fivetran dbt package designed to generate an end model and Cortex Search Service (for Snowflake...