aws-samples/text-embeddings-pipeline-for-rag

A pipeline to convert contextual knowledge stored in documents and databases into text embeddings, and store them in a vector store

33
/ 100
Emerging

This solution helps developers working with Large Language Models (LLMs) to create a system that can understand and respond to user queries more accurately using their own private data. It takes your existing documents (like text files) or data from databases and converts them into a specialized format called text embeddings. These embeddings are then stored in a way that LLMs can quickly search through to find relevant information before generating a response. This is for software engineers or data scientists building LLM-powered applications.

No commits in the last 6 months.

Use this if you are a developer building a Retrieval Augmented Generation (RAG) system and need a pipeline to efficiently convert your organizational knowledge base into searchable embeddings for your LLMs.

Not ideal if you are not a developer or if you need a production-ready, fully-hardened RAG solution without needing to review and adapt configurations for security and cost.

LLM application development Generative AI data pipeline knowledge retrieval vector database
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

TypeScript

License

MIT-0

Last pushed

Apr 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/aws-samples/text-embeddings-pipeline-for-rag"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.