Posted by admin

Join us as we dive into the exciting world of AI with the new Google Gemma opensource model, powered by Ollama, to construct a cutting-edge rag application with memory capabilities. Utilizing Chainlit and Langchain. Our application allows you to seamlessly upload PDF docs and engage in conversations with them like never before. What sets this video apart is our exploration of Gemma, a lightweight open model developed by Google DeepMind and other Google teams. Born from the groundbreaking Gemini models, Gemma comes in two sizes: Gemma 2B and Gemma 7B, each offering pre-trained and instruction-tuned variants. But that's not all! We're harnessing the power of nomic-embed-text from Ollama as our embedding model. With an impressive 8192 token context window, nomic-embed-text outperforms other models like OpenAI text-embedding-ada-002 and text-embedding-3-small on both short and long context tasks. This makes it the perfect choice for embedding in our project. #opensource #localllms #googlegemini #gemini #langchain #model LINKS: Github Code: https://github.com/InsightEdge01/RAGGemmaModel/tree/main Gemma Docs:https://blog.google/technology/developers/gemma-open-models/ Ollama embedding:https://ollama.com/library/nomic-embed-text Chainlit:https://docs.chainlit.io/get-started/overview https://www.youtube.com/watch?v=E53hc-jcUeE&t=460s https://www.youtube.com/watch?v=7lP7fune0Gw&t=16s https://www.youtube.com/watch?v=vBC6Ym0cb0Y&t=2138s https://www.youtube.com/watch?v=cNsUTI3AJn4&t=24s