Building Generative AI application using Retrieval Augmented Generation(RAG) using Mistral 7B LLM, LangChain orchestration framework & In memory vector database FAISS (Facebook AI Similarity Search)
Step 5: Run Opensource LLM a per your choice example as below using mistral LLM
ollama run mistral
Step 5: Ask LLM question and get answer :)
Now you can ask question from LLM to get response at Windows powershell terminal.
Future work is where you can run that as API endpoint at Google Collab, VSCode and Ollama it's own chat interface.
About
Building Generative AI application using Retrieval Augmented Generation(RAG) using Mistral 7B LLM, LangChain orchestration framework & In memory vector database FAISS (Facebook AI Similarity Search)