Local RAG agent with LLaMA3 and Langchain

We will take a look at how to do RAG with LLama3
github.com/lan...
#python #pythonprogramming #llm #ml #ai #aritificialintelligence #largelanguagemodels #tutorial #deeplearning

[@proterotype]

Do you like using ChatOllama(model=local_model) better than just Ollama(model=local_model)?
Also have you seen a difference between using Llama3:instruct as opposed to just Llama3 70b:latest

[@tintintintin576]

very nice!

[@DLExplorers-lg7dt]

Thanks for the visit

[@MosheRecanati]

Any option to use local embedding rather than gpt?

[@DLExplorers-lg7dt]

GPT4AllEmbeddings is a local embedding, you can use sentence transformers too
python.langchain.com/docs/integrations/platforms/huggingface/