Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/aneeshpatne/resume.ai
AI Assistant using LoRA-fine-tuned LLAMA 3.2, trained on my resume to answer questions about my professional background and experience.
https://github.com/aneeshpatne/resume.ai
ai chatbot llama3 llm lora nlp
Last synced: 10 days ago
JSON representation
AI Assistant using LoRA-fine-tuned LLAMA 3.2, trained on my resume to answer questions about my professional background and experience.
- Host: GitHub
- URL: https://github.com/aneeshpatne/resume.ai
- Owner: aneeshpatne
- Created: 2024-12-11T11:04:13.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2025-01-12T15:28:18.000Z (18 days ago)
- Last Synced: 2025-01-12T15:28:30.192Z (18 days ago)
- Topics: ai, chatbot, llama3, llm, lora, nlp
- Language: Python
- Homepage:
- Size: 63.1 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Resume.AI
A chatbot system that uses Retrieval-Augmented Generation (RAG) and LLAMA 3.2 1B model to create an interactive resume experience.
## Overview
Resume.AI is an intelligent chatbot that provides accurate, contextual responses about professional experience by combining:
- LLAMA 3.2 1B language model and Mistral:Latest 8B.
- RAG (Retrieval-Augmented Generation) for grounding responses in actual resume data
- Natural language processing for human-like interactions
## Features
- Interactive Q&A about professional experience
- Context-aware responses using RAG
- Accurate information retrieval from resume data
- Natural conversational interface
- Support for diverse professional queries
## Project Structure
```
.
├── Chat/ # Main chat implementation
│ └── Vector Database/ # Vector DB for RAG
├── Extraction and Upserting/ # Data processing scripts
│ ├── extraction.ipynb
│ └── conversion.ipynb
└── README.md
```
## Setup and Installation
1. Clone the repository
```bash
git clone https://github.com/username/Resume.AI.git
```
2. Install dependencies
```bash
pip install -r requirements.txt
```
3. Configure environment variables in `.env`
4. Run the chat interface
```bash
python chat/main.py
```
## Data Preparation
Training data includes prompt-response pairs covering:
- Work history and experience
- Technical skills and competencies
- Educational background
- Project details and achievements
- Professional certifications
## Development
- Uses LLAMA 3.2 1B model fine-tuned on resume data
- Implements RAG for retrieval-augmented generation
- Indexes resume content in vector database
- Processes natural language queries