Fully Local RAG for Your PDF Docs (Private ChatGPT Tutorial with LangChain, Ollama, Chroma)

Показать описание

Fully Local RAG for Your PDF Docs (Private ChatGPT with LangChain, RAG, Ollama, Chroma)

Teach your local Ollama new tricks with your own data in less than 10 minutes, using RAG with LangChain and Chroma. Completely private and FREE! Upload multiple PDFs into your vector store and create embeddings so you can query the database and provide the LLM the context it needs. This is a beginner tutorial that includes multiple examples of using PDFs in your RAG and features PyPDFLoader, RecursiveCharacterTextSplitter, Chroma, OllamaEmbeddings, and ChatOllama. Models used mxbai-embed-large and llama3.2, along with OpenAI text-embedding-3-large and gpt-4o.

Included is a bonus web scraper Python script that uses pypeteer and downloads any web page into a local PDF. Once added to the vector store you can start chatting with your entire website!

Ever wanted to chat with your PDFs or train ChatGPT on your own data? This video will show you how!

Timestamps:
0:00 - Intro
0:52 - GitHub walkthrough
3:40 - RAG
6:15 - Models
7:35 - Ingestion
10:25 - Chatbot
14:25 - Chroma
18:30 - Scraper
20:05 - QA
22:30 - Conclusion

Рекомендации по теме

Комментарии

Very nice tutorial. Gonna be super useful for all those super long PDF:s

mentos.

Great explanation of all the processes. I like how you broke out the two processes of ingestion and chat, which most tutorials on the topic don't do.

justthefactsplease

It’s fantastic! your tutorial on creating a local RAG setup with LangChain, Ollama, and Chroma for PDF docs. Amazing 😮
I was wondering if you could consider making a video that goes a bit deeper, specifically focusing on building an offline RAG UI system for PDF files.

The idea would be to create an interface where non-technical users could upload PDF files directly through the UI and then interact with ChatBolt to ask questions about the content. It would be awesome if this system could run locally without relying on OpenAI or any external APIs, using a setup with Ollama (like the llama 3 model) and Chroma for the vector database.

This would really help people who want a secure, fully offline solution without needing coding knowledge.

Have a nice one 😊

samiurrehman

obrigado pelo seu video e pelo ensino 👏👏👏👏👏👏👏👏👏👏👏

sr.modanez

Fully Local RAG for Your PDF Docs (Private ChatGPT Tutorial with LangChain, Ollama, Chroma)

Easy 100% Local RAG Tutorial (Ollama) + Full Code

Fully Local RAG for Your PDF Docs (Private ChatGPT Tutorial with LangChain, Ollama, Chroma)

Fully local RAG agents with Llama 3.1

Reliable, fully local RAG agents with LLaMA3.2-3b

Reliable, fully local RAG agents with LLaMA3

Build a Talking Fully Local RAG with Llama 3, Ollama, LangChain, ChromaDB & ElevenLabs: Nvidia S...

Llama-OCR + Multimodal RAG + Local LLM Python Project: Easy AI/Chat for your Docs

Fully Local RAG AI App using OpenHermes and Ollama

Build a RAG Based LLM App in 20 Minutes! | Full Langflow Tutorial

Llama3 Full Rag - API with Ollama, LangChain and ChromaDB with Flask API and PDF upload

Chat with Docs using LLAMA3 & Ollama| FULLY LOCAL| Ollama RAG|Chainlit #ai #llm #localllms

Retrieval-Augmented Generation (RAG) with .NET 8: A Full Local Resource Guide

Build Fully Local RAG AI Application

Complete Guide to Build RAG App using Ollama Python Lib | Local LLM RAG

Full-Text Search vs Vector Search (RAG with DuckDB)

Ollama and LangChain.js for RAG | Complete code example

RAG with Langchain, Ollama Llama3, and HuggingFace Embedding | Complete Guide

Build your own RAG based LLM Application (Completely Offline!): AI for your documents

Chatbots with RAG: LangChain Full Walkthrough

How I Built the Fastest FULLY LOCAL RAG PDF Chatbot Using GroqChat|Chainlit|Ollama #ai #llm

Google Gemma Fully LOCAL RAG ChatBot using Ollama|LangChain|Chainlit|Chat with Docs #ai #ollama #llm

Build high-performance RAG using just PostgreSQL (Full Tutorial)

Build a Full Stack RAG App With TypeScript

Create Complete RAG Pipeline Locally and Free with FastRAG and HayStack