552 views
???? Launching a fully local assistant using RAG technology with an agent scheme. We use: ✨ Ollama. ✨ llama3.2:3b-instruct-fp16. ✨ LangChain and LangGraph ✨Embeddings: intfloat/multilingual-e5-large model with HuggingFace. ✨ Tavily: A search engine for Web search, optimized for LLM and RAG. ???? See the source here: https://github.com/kvoloshenko/Local_... ✨ What else to study and see: AI Agents: • AutoGen. Multi-agent framework. Created... · LlamaIndex: • Creating an agent RAG with Llamaindex.... · OpenAI API (ChatGPT API): • OpenAI API (API) usage concepts... · RAG (Retrieval-Augmented Generation): • Using the ChatGPT API in an a... · Ollama: • Ollama: Command line server for running ... · Flowise: • Creating a neural assistant without prog... · LM Studio: • LM Studio Running Open S... · TextGen WebUI: • TextGen WebUI. How to automate ... ✨Attention: 1. If you are experiencing problems viewing a previously published video due to YouTube slowdown, write in the comets under the desired post in Telegram - and I will upload this video there. 2. I invite you to chat on this topic in Telegram: https://t.me/AiExp01 3. The chat is here: https://t.me/AiExp02