AI Apps. Understanding RAGs and VectorDB

By the end of this post, you will have few alternatives to: https://notebooklm.google/

F/OSS Vector DBs

• ChromaDB
• Vector Admin
• The ChromaDB Site
• The ChromaDB Source Code at Github
  • License: Apache v2 ✅

• The faiss Site
  • The faiss Source Code at Github
    • License: MIT ❤️

QDrant

• https://qdrant.tech/

• 👉 https://www.youtube.com/watch?v=VL6MAAgwSDM

docker pull qdrant/qdrant
docker run -p 6333:6333 qdrant/qdrant

version: '3'
services:
  qdrant:
    container_name: my_qdrant_container
    image: qdrant/qdrant
    ports:
      - "6333:6333"
    volumes:
      - qdrant_data:/path/to/qdrant_data

volumes:
  qdrant_data:

Check its UI at: http://localhost:6333/dashboard#

Vector Admin

F/OSS RAGs

• Python EmbedChain
• Dependencies for Python

RAG (Retrieval-Augmented Generation) frameworks are a type of natural language processing system that combines information retrieval and language generation techniques.

These frameworks aim to improve the quality and relevance of generated text by leveraging external knowledge sources.

In a RAG framework, when a user poses a question or provides a prompt, the system first retrieves relevant information from a large corpus of text data.

The retrieved information is then used to augment the input prompt, providing additional context and knowledge to the language generation model.

• LangChain
• LlamaIndex - This is the default RAG framework of PrivateGPT
• EmbedChain
• PandasAI
• MemGPT

LangChain

LLamaIndex

I got to know LlamaIndex RAG thanks to the PrivateGPT project, which uses it as default RAG.

What can I use LLamaIndex for?

• Together with Ollama

MemGPT

https://github.com/cpacker/MemGPT - Solving LLMs context Window

• The Site
• The Code at Github
  • License: MIT ❤️

  Create LLM agents with long-term memory and custom tools 📚🦙

Mem0 - exEmbedChain

PandasAI

• PandasAI

F/OSS No Code RAGs

LangFlow

It uses LangChain in the background

Conclusions

https://github.com/run-llama/chat-llamaindex

Create chat bots that know your data

Creating GenAI F/OSS

whatsap chat bot, but OSS

FAQ

How to Process Unstructured Data

• https://github.com/iterative/datachain
  • https://github.com/iterative/datachain?tab=Apache-2.0-1-ov-file#readme ✅
  • https://pypi.org/project/datachain/

DataChain 🔗 Process and curate unstructured data using local ML models and LLM calls

How to run LLMs Locally

https://www.youtube.com/watch?v=5WCvGyPpWwg

• Ollama
• Oobabooga - Text Gen Web UI
• GPT4All
• PrivateGPT
• GPT4All
• KoboldCpp

• LLamaCPP: you need to build it from source + use GGUF format

• AnythingLLM
• LocalAI

What are LangChains?

They allow to connect an LLM to our own sources of data. It will have referenced data. It can also take actions for us (like send email).

Document -> Document Chunks -> VectorStore

https://www.youtube.com/watch?v=aywZrzNaKjs

https://www.langchain.com/ You can use it from Python or JS.

• https://integrations.langchain.com/
• https://integrations.langchain.com/llms

Chat with Web - https://www.youtube.com/watch?v=bupx08ZgSFg

Get your LLM application from prototype to production.

A great YT List: https://www.youtube.com/playlist?list=PL4HikwTaYE0GEs7lvlYJQcvKhq0QZGRVn

Retrieval Chains

• https://www.youtube.com/watch?v=-Ueh5XBpcoY&list=PL4HikwTaYE0GEs7lvlYJQcvKhq0QZGRVn&index=4
  • https://python.langchain.com/docs/modules/data_connection/
    • https://python.langchain.com/docs/integrations/document_loaders/web_base
    • https://github.com/leonvanzyl/langchain-python-tutorial/tree/lesson-4

To explore vector DBs we have Vector Admin, but for regular DB’s we have WhoDB

https://github.com/clidey/whodb?ref=selfh.st https://github.com/clidey/whodb?tab=GPL-3.0-1-ov-file#readme

A lightweight next-gen database explorer - Postgres, MySQL, SQLite, MongoDB, Redis, MariaDB & Elastic Search

Welcome to WhoDB – a powerful, lightweight (~20Mi), and user-friendly database management tool that combines the simplicity of Adminer with superior UX and performance. WhoDB is written in GoLang f