ianhohoho/auto-hyde
🔎 A deep-dive into HyDE for Advanced LLM RAG + 💡 Introducing AutoHyDE, a semi-supervised framework to improve the effectiveness, coverage and applicability of HyDE
This project helps you improve how large language models (LLMs) find and retrieve information from your documents. It takes your existing documents and a set of example questions, then helps the LLM generate more relevant and comprehensive answers by creating better internal search queries. This is for data scientists, ML engineers, or AI practitioners who work with Retrieval Augmented Generation (RAG) systems.
No commits in the last 6 months.
Use this if you are working with RAG systems and want to enhance the quality and completeness of information retrieved by your LLM from a given document set.
Not ideal if you are looking for a general-purpose LLM or a tool for basic document search without the need for advanced RAG optimization.
Stars
34
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ianhohoho/auto-hyde"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents