Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/MIBlue119/awesome-rag

Some collections about Retrieval Augmented Generation resources
https://github.com/MIBlue119/awesome-rag

List: awesome-rag

Last synced: about 1 month ago
JSON representation

Some collections about Retrieval Augmented Generation resources

Awesome Lists containing this project

README 

        
# AWESOME-RAG(Retrieval Augmented Generation)

Some collections about Retrieval Augmented Generation resources



- [AWESOME-RAG(Retrieval Augmented Generation)](#awesome-ragretrieval-augmented-generation)

  - [RAG](#rag)

    - [Tutorials](#tutorials)

  - [Vector Store](#vector-store)

    - [How to choose Vector Store](#how-to-choose-vector-store)

    - [Paid vector stores](#paid-vector-stores)

    - [OpenSource vector store](#opensource-vector-store)

  - [Example App](#example-app)

    - [101 example](#101-example)

    - [Production Level Examples](#production-level-examples)



## RAG 

### Tutorials

- [Demystifying Advanced RAG Pipelines](https://github.com/pchunduri6/rag-demystified#demystifying-advanced-rag-pipelines): An LLM-powered advanced RAG pipeline built from scratch 

- [Anaconda's Sophiam Yang's slides about langchain RAG](https://sophiamyang.github.io/slides-langchain-rag-panel/)

- [Sahota, Harpreet. “RAG with LlamaIndex and DeciLM: A Step-by-Step Tutorial.” Deci, October 20, 2023](https://deci.ai/blog/rag-with-llamaindex-and-decilm-a-step-by-step-tutorial/)

- [llamaindex_Semi_Structured_RAG](https://github.com/sudarshan-koirala/youtube-stuffs/blob/main/llamaindex/llamaindex_Semi_Structured_RAG.ipynb)

- [RAG with LlamaIndex and DeciLM: A Step-by-Step Tutorial](https://deci.ai/blog/rag-with-llamaindex-and-decilm-a-step-by-step-tutorial/)

- [202310 A Complete LlamaIndex Guide](https://nanonets.com/blog/llamaindex/)

- [AI-engineer-workshop](https://github.com/run-llama/ai-engineer-workshop):Building, Evaluating, and Optimizing your RAG App for Production



## Vector Store



### How to choose Vector Store

- [Vector Store Benchmark](https://qdrant.tech/benchmarks/?gad=1&gclid=Cj0KCQjwhfipBhCqARIsAH9msbmjuZsDxTXSSk2P8vXTmhl-HHwsylkH-IqSeMzXWHz6sDbOoYWe-VQaAhvlEALw_wcB)

- [awesome-vector-database](https://github.com/dangkhoasdc/awesome-vector-database)

- [Vector Databases: A First-Principles Approach](https://docs.google.com/presentation/d/1qRv2nGVHjbFHXyUeUKK7bbvboj7Yal8UYcu_POEfWOQ/edit#slide=id.p)

- [How to choose your vector database in 2023?](https://www.sicara.fr/blog-technique/how-to-choose-your-vector-database-in-2023)

- [Comparison Vector Database](https://zilliz.com.cn/comparison/qdrant-vs-milvus)

- [Getting started with Vector DBs in Python](https://code.dblock.org/2023/06/16/getting-started-with-vector-dbs-in-python.html)

- [202304 The Best Vector Database for Stablecog's Semantic Search](https://stablecog.com/blog/the-best-vector-database-for-stablecogs-semantic-search)

### Paid vector stores

- [Milvus](https://milvus.io/)

- [Qdrant](https://qdrant.tech/)

- [Weaviate](https://weaviate.io/)

- [Chroma](https://www.trychroma.com/)

- [Pinecone](https://www.pinecone.io/)



### OpenSource vector store

- [Qdrant](https://github.com/qdrant/qdrant)

- [Chroma](https://docs.trychroma.com/about)

- [Milvus](https://github.com/milvus-io/milvus)

- [Weaviate](https://github.com/weaviate/weaviate)

- [Pgvector](https://github.com/pgvector/pgvector)



## Example App



### 101 example

- [Weaviate's demo for health search](https://weaviate.io/blog/healthsearch-demo)

- [Pinecone's example](https://docs.pinecone.io/page/examples)

- [Weaviate's RAG chatbot](https://github.com/weaviate/Verba)

- [llamaindex-chat-with-streamlit-docs](https://github.com/carolinedlu/llamaindex-chat-with-streamlit-docs)

- [Biblos - Bible Exploration with Vector Search and Summarization](https://github.com/dssjon/biblos)



### Production Level Examples

- [W&B's QAbot based on langchain](https://github.com/wandb/wandbot/)

    - [QAbot's prompt](https://github.com/wandb/wandbot/blob/main/data/prompts/chat_prompt.json)

    - Provide a script about sythetic hypothesis question from user

- [Anyscale's Goku awesome tutorial "Building RAG-based LLM Applications for Production"](https://www.anyscale.com/blog/a-comprehensive-guide-for-building-rag-based-llm-applications-part-1)

    - github: https://github.com/ray-project/llm-applications

- [Llamaindex: chat-llamaindex](https://github.com/run-llama/chat-llamaindex): create and share LLM chatbots that know your data (PDF or text documents).

- [Llamaindex: sec-insights](https://github.com/run-llama/sec-insights): A real world full-stack application using LlamaIndex for 10-k/10-q report