AgenticAI

# AgenticAI AgenticAI is a modular framework for building agentic and LLM-powered applications in Python. It provides tools, workflows, and examples for working with language models, vector databases, document loaders, and custom AI agents. ## Features - Modular agent and workflow design - Integration with LangChain, LangGraph, HuggingFace, Google Gemini, and more - Vector database support (FAISS, Chroma, Pinecone) - Document loading and text splitting utilities - Built-in and custom tools for Wikipedia, YouTube, and web search - Example notebooks for agentic workflows and LLM applications ## Getting Started 1. Clone the repository: ```bash git clone https://github.com/prayag001/AgenticAI.git cd AgenticAI ``` 2. Install dependencies: ```bash pip install -r requirements.txt ``` 3. Set up your environment variables (e.g., API keys) in a `.env` file. ## Usage - Explore the example notebooks in the `4-LangGraph/` and `2-Langchain_Basics/` folders - Run Jupyter notebooks for hands-on demos - Customize agent workflows and tools for your own use cases ## Folder Structure - `1-Pydantic/` - Pydantic examples - `2-Langchain_Basics/` - LangChain basics, document loaders, vector stores - `3-LangChain/` - LangChain tools and utilities - `4-LangGraph/` - LangGraph agentic workflows and demos - `6-MCP/` - Model Context Protocol experiments ## Contributing Pull requests and issues are welcome! Please open an issue for feature requests or bug reports. ## License This project is licensed under the MIT License.