A comprehensive collection of Generative AI implementations using LangChain, Groq, and Google Gemini Pro
This repository showcases various implementations of Generative AI applications using modern frameworks and models. From job application generators to multi-RAG agents, this toolkit demonstrates the practical applications of AI in solving real-world problems.
- Generates tailored skill sets based on job descriptions
- Creates custom cover letters using job descriptions and resumes
- Built with LangChain and Groq API
- Frontend:
client.py
, Backend:api.py
- Implements multiple retrieval tools:
- 📚 Wikipedia Retriever
- 📖 Arxiv Retriever
- 🌐 Custom LangChain Documentation Retriever
- Powered by Google's Gemini Pro
- Uses Google Generative AI embeddings
- FAISS vector database integration
- Comprehensive RAG pipeline demonstration
- Multiple loader implementations:
- Text-based loader
- Web-based loader
- PDF loader
- Vector database integration (FAISS)
- Custom chat prompt templates
- Streamlit-based interactive interface
- Web-based document loader
- LangChain documentation integration
- Create and activate a Conda environment
conda create -n chat_assist python=3.10 anaconda
conda activate chat_assist
- Install dependencies
pip install -r requirements.txt
- Configure Environment Variables
LANGCHAIN_API_KEY=xxx
LANGCHAIN_PROJECT=ProjectName
GOOGLE_API_KEY=xxx
GROQ_API_KEY=xxx
.
├── api/
│ ├── api.py # Backend implementation
│ └── client.py # Frontend implementation
├── agents.py # Multi-RAG agent implementation
├── rag/
│ └── advanced_rag.ipynb # RAG pipeline demonstration
├── groq/ # Groq-specific implementations
└── requirements.txt
- LangChain Framework
- Groq API
- Google Gemini Pro
- FAISS and ChromaDB Vector Database
- Streamlit
- Google Generative AI
- Wikipedia Wrapper by Langchain
- Arxiv API Wrapper by Langchain