Crew Details
This project provides an in-depth guide on using CrewAI with Retrieval-Augmented Generation (RAG) techniques for processing PDFs and YouTube channels. It includes tools for content scraping, embedding in vector databases, and querying data.
Install
Clone the repo, install dependencies with Poetry, set up API keys in .env, and run the scripts for PDF or YouTube processing.
Input & Output
Input
- The project processes PDFs and YouTube content using agents for scraping and embedding.
Output
- Extracted data is embedded in vector databases, with structured outputs generated by agents.