https://github.com/azeemk210/pdf-rag-chatbot

This repository contains a Retrieval-Augmented Generation (RAG) chatbot powered by DeepSeek and Ollama, designed to process PDF documents and provide intelligent answers based on uploaded content.

https://github.com/azeemk210/pdf-rag-chatbot

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (11.5%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

This repository contains a Retrieval-Augmented Generation (RAG) chatbot powered by DeepSeek and Ollama, designed to process PDF documents and provide intelligent answers based on uploaded content.

Basic Info
  • Host: GitHub
  • Owner: azeemk210
  • Language: Python
  • Default Branch: master
  • Size: 6.84 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

📚 Local DeepSeek RAG

🚀 Installation & Setup Guide

This guide explains how to install, set up, and use the Local DeepSeek RAG system on your machine.


📌 1. Prerequisites

  • Python 3.10+
  • Git
  • Conda (Optional but recommended)

🔧 2. Clone the Repository

```bash

Clone the repo

git clone https://github.com/azeemk210/pdf-rag-chatbot.git cd pdf-rag-chatbot ```


🛠 3. Create and Activate Virtual Environment

Using Conda (Recommended)

bash conda create --name deepseek_rag python=3.10 -y conda activate deepseek_rag

Using Virtualenv (Alternative)

bash python -m venv deepseek_rag source deepseek_rag/bin/activate # On macOS/Linux deepseek_rag\Scripts\activate # On Windows


🔽 4. Install Dependencies

bash pip install -r requirements.txt


🏗 5. Install & Set Up Ollama

Step 1: Download & Install Ollama

Step 2: Download llama2 model

bash ollama run llama2

Step 3: Start Ollama Server in Terminal 1

bash ollama serve


6. Run the Application in Terminal 2

bash python localrag.py

  • Open the Gradio UI in your browser: http://127.0.0.1:7860
  • Upload PDFs and start asking questions!

📝 7. Usage

Uploading Documents

  • Click on "📂 Upload PDF Documents" and select your files.
  • Click Initialize System to process the documents.

Asking Questions

  • Enter a question related to the document in the text box.
  • Click Ask 🤖 and view the response in the chat.

Downloading Conversation History

  • Click 💾 Download Chat History to save your Q&A session.

8. Troubleshooting

Ollama Not Connecting?

bash $env:OLLAMA_HOST="http://127.0.0.1:11436" ollama serve Ensure it's running and accessible at http://127.0.0.1:11436 or update: ```python uncomment this line in localrag.py

os.environ["OLLAMA_HOST"] = "http://127.0.0.1:11436"

```

Wrong Document Answers?

  • Delete old embeddings: bash rm -r chroma_db
  • Restart the system and re-upload PDFs.

🤝 Contributing

Feel free to fork this repository and submit pull requests!

Owner

  • Name: azeemk210
  • Login: azeemk210
  • Kind: user

GitHub Events

Total
  • Push event: 3
  • Fork event: 1
  • Create event: 2
Last Year
  • Push event: 3
  • Fork event: 1
  • Create event: 2

Dependencies

requirements.txt pypi
  • chroma-hnswlib ==0.7.6
  • chromadb ==0.6.3
  • fastapi ==0.115.8
  • gradio ==5.15.0
  • langchain ==0.3.17
  • langchain-community ==0.3.16
  • langchain-ollama ==0.2.3
  • numpy >=1.22.5,<2.0
  • ollama ==0.4.7
  • pandas ==2.2.3
  • pypdf ==5.2.0
  • python-dotenv ==1.0.1
  • requests ==2.32.3
  • rich ==13.9.4
  • tenacity ==9.0.0
  • typing-extensions ==4.12.2
  • uvicorn ==0.34.0