rag-as-a-service-with-vision and rag-service
These are competitors—both provide complete RAG pipeline solutions, though the Azure-Samples offering emphasizes multimodal document processing while Leroll's focuses on a cloud-native service architecture, but each could independently serve as a production RAG system.
About rag-as-a-service-with-vision
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.
About rag-service
Leroll/rag-service
A cloud-native RAG (Retrieval Augmented Generation) service API built on LightRAG framework, offering plug-and-play knowledge-enhanced generation capabilities.
This is a cloud-native RAG (Retrieval Augmented Generation) service API built on LightRAG framework, offering plug-and-play knowledge-enhanced generation capabilities. It takes multi-format documents and generates enhanced responses with streaming support. The primary user for this project is a developer who needs to integrate advanced knowledge retrieval and generation features into their applications.
Scores updated daily from GitHub, PyPI, and npm data. How scores work