AzizBenAli/YouTube-AI-Assistant
Develop a python application that allows you to extract valuable insights, engage in meaningful conversations, and explore video content in a whole new way.
Combines YouTube transcript extraction via the official API with a RAG pipeline using Hugging Face embeddings and Mistral LLM, enabling source-cited answers with conversation memory managed through LangChain. The Streamlit interface integrates Parent Document Retriever for relevant context retrieval, allowing users to trace chatbot responses back to specific transcript timestamps for verification.
No commits in the last 6 months.
Stars
12
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jan 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/AzizBenAli/YouTube-AI-Assistant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.