Gemma 2 - RAG with LangChain and HuggingFace and Groq (text ,pdfs)
Support Me on Petron ⚡: / codewello
Building a very fast RAG app using Gemma 2 9B as the main LLM model, with speed optimized for Groq, Hugging Face embeddings, and LangChain, makes all of this super easy to do
Collab : colab.research.google.com/dri...
00:00 - What is Gemma 2
01:37 - Gemma 2 Quality and performance analysis
03:12 - Where to find Gemma 2
03:55 - What will we build
04:30 - Text Doc Rag (Splitting Text )
05:00 - Open source Embeddings
05:47 - Create the RAG
06:12 - Text Similarity vs llm Results
07:53 - PDF Rag
09:03 - PDF Rag Results Q&A
11:40 - Outro
_______________________________________________________________
🤖 Open AI Template Alima : codewello.gumroad.com/l/kjlzw
💷 50% Discount Code : A2LH6LZ
👉 Linkedin : / hossam-eldin
_______________________________________________________________
📕 Mastering Yolo V8 Object Detection : • Mastering YOLO V8: Obj...
📙 Supervision : • Supervision with Yolo ...
📗 Mastering Yolo NAS : • Mastering YOLO NAS: Ob...
🧑🏻💻 Build Ai Assistant : • OpenAI Assistant: From...
#gemma #groq #langchain #rag #llms #aiapps
31 июл 2024