LangChain LLM Applications

A collection of hands-on experiments demonstrating the use of LangChain for building Large Language Model (LLM) applications. This project explores prompt engineering, conversation memory, agents, retrieval, and external knowledge integration.

---

Features

• Prompt Templates
• LLM Chains
• Sequential Chains
• Conversation Memory
• LangChain Agents
• Wikipedia Integration
• Document Loading
• Text Chunking
• Vector Embeddings
• FAISS Vector Store
• ChatGroq Integration

---

Technologies

• Python
• LangChain
• ChatGroq
• Hugging Face Embeddings
• FAISS
• Wikipedia API
• python-dotenv

---

Project Structure

LangChain.ipynb
README.md
requirements.txt

---

Installation

Clone the repository

git clone https://github.com/<your-username>/langchain-llm-applications.git
cd langchain-llm-applications

Install dependencies

pip install -r requirements.txt

Create a .env file

GROQ_API_KEY=your_api_key

Run the notebook.

---

Learning Outcomes

• Understanding LangChain architecture
• Prompt engineering techniques
• Building conversational AI
• Agent-based workflows
• Retrieval-Augmented Generation (RAG)
• Working with vector databases

---

Future Improvements

• Streamlit Web Interface
• Multi-document RAG
• Persistent Vector Database
• Chat History Storage