microsoft/rag-experiment-accelerator
The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.
Driven by YAML configuration, it orchestrates experiments across multiple search types (hybrid, vector, semantic) and document loaders including Azure Document Intelligence with custom table-to-KV transformation. The tool integrates Azure AI Search, Azure OpenAI, MLflow, and Azure ML to automate hyperparameter tuning, evaluation via LLM-as-judge metrics (context recall, answer relevance, MAP@k), and report generation with stratified dataset sampling for representative results.
298 stars. No commits in the last 6 months.
Stars
298
Forks
106
Language
Python
License
—
Category
Last pushed
Apr 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/microsoft/rag-experiment-accelerator"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
OpenBMB/UltraRAG
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
Quansight/ragna
RAG orchestration framework ⛵️
microsoft/rag-time
RAG Time: A 5-week Learning Journey to Mastering RAG
AnkitNayak-eth/EpsteinFiles-RAG
A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).
deepset-ai/haystack-rag-app
An example of a RAG backend plus UI