Open d3rp3tt3 opened 3 days ago
We'll use Langchain to give the LLM prompts to perform as a trivial chatbot. We must identify the workflows first and then create the Python code.
These workflows need to be specific for RAG since the template will need to callback to the vector store.
https://python.langchain.com/docs/how_to/qa_chat_history_how_to/
Overview
We'll use Langchain to give the LLM prompts to perform as a trivial chatbot. We must identify the workflows first and then create the Python code.