https://github.com/armandfs/langchain_pdf_rag
This project is development of a Large Language Model using Python, Streamlit, and the O-Llama LLM open source tool for the built in model.
https://github.com/armandfs/langchain_pdf_rag
Last synced: about 1 month ago
JSON representation
This project is development of a Large Language Model using Python, Streamlit, and the O-Llama LLM open source tool for the built in model.
- Host: GitHub
- URL: https://github.com/armandfs/langchain_pdf_rag
- Owner: ArmandFS
- License: mit
- Created: 2024-11-21T05:47:12.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-17T15:27:16.000Z (over 1 year ago)
- Last Synced: 2025-06-13T07:46:37.236Z (12 months ago)
- Language: Jupyter Notebook
- Size: 1.12 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🤖 Chat with PDF locally using Ollama + LangChain 🤖
#### Original Project Idea by @Tony Kimpkemboi on Youtube
This project demonstrates an implemention of a local RAG (Retrieval Augmented Generation) that lets you chat with your PDF documents using Ollama and LangChain. For experimentation purposes, this project is tested in a Jupyter Notebook Environment.
## ✨ Features ✨
- 🔒 Fully local processing - no data leaves your machine
- 📄 PDF processing with intelligent chunking
- 🧠 Multi-query retrieval for better context understanding
- 🎯 Advanced RAG implementation using LangChain
- 📓 Jupyter notebook for personal experimentation
## 🚀 Implementation 🚀
If you want to use this on your own local setup, you can either watch Tony's video, or follow these simple steps below:
1. You will need to create a virtual environment first on so python dependencies and libraries don't clash
```
# On Windows
python -m venv venv
venv\Scripts\activate
# On macOS/Linux
python3 -m venv venv
source venv/bin/activate
```
2. Install the requirementss
```
pip install -r requirements.txt
```
3. Ensure you have the Ollama package installed
```
pip install ollama
```
4. Update to Ollama 0.4.1 to prevent TypeError issues
```
pip install --upgrade ollama==0.4.1
```
Note: The application will run slower on CPU-only systems, but it will still work effectively.
## 📝 License
This project is open source and available under the MIT License.
---