ksmin23/rag-with-postgresql-pgvector-and-sagemaker
Question Answering application with Large Language Models (LLMs) and Amazon Aurora Postgresql using pgvector
This project helps developers build question-answering applications using large language models (LLMs) to answer questions based on a vast trove of your company's documents. You provide your enterprise knowledge base as input, and the application generates accurate answers to user queries, even from very large document collections. This is for developers building intelligent assistants or knowledge retrieval systems for their organizations.
No commits in the last 6 months.
Use this if you are a developer looking to implement a question-answering system that can accurately retrieve and synthesize information from a large, proprietary document collection using LLMs and Amazon Aurora PostgreSQL.
Not ideal if you need a fully managed, ready-to-use end-user application without any development work or if your knowledge base isn't hosted on Amazon Aurora PostgreSQL.
Stars
11
Forks
1
Language
Python
License
—
Category
Last pushed
Jun 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ksmin23/rag-with-postgresql-pgvector-and-sagemaker"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
raphaelmansuy/edgequake
High-performance GraphRAG inspired from LightRag written in Rust
bosun-ai/swiftide
Fast, streaming indexing, query, and agentic LLM applications in Rust
AlphaCorp-AI/RustyRAG
⚡ Sub-200ms RAG API built in Rust — document ingestion, Milvus vector search, Jina AI local...
cool-japan/oxirag
A four-layer Retrieval-Augmented Generation (RAG) engine in Rust with SMT-based logic...
kkollsga/kglite
Lightweight in-memory knowledge graph with Cypher query support