Llama3 Autonomous RAG
2024 ж. 23 Мам.
3 239 Рет қаралды
Lets build Autonomous RAG where Llama3 decides how to pull the data it needs.
Code: git.new/groq-autorag
⭐️ Phidata: git.new/phidata
Questions on Discord: phidata.link/discord
Here's the flow:
🦋 The user asks a question.
🤔 Llama3 decides whether to search its knowledge, memory, internet or make an API call.
✍️ Llama3 answers with the context.
Thanks for the video. Very helpful. I have a question: You mention openDB at 6:55. What is the concept? Can you share a link, please?
Thanks for your contribution. Making this open-source really help a lot. My question is "is it possible to customize the prompt for the tool?"
😮 thank
Your instruction is that "Either nomic-embed-text or OPENAI can be used for embedding", so I prefer nomic-embed-text. However, after I uploaded a pdf. file in localhost8501, why have I kept getting an error message for OPENAI API Key?
wha tsolution UI is that? is it better than Open. Web UI?
No, it is not better than open web UI. It’s actually quite poor. It’s just an off the shelf boiler plate UI
Can we use openwebui
Can I use AI other than OpenAI?
Yeah, you could use Llama3 🤣
you can use any llm :)
How can I make an API call to this assistant?
@DarrenAllatt we can serve the Assistant behind a FastApi server. Its a bit too much to type as a comment but drop by in our discord and im happy to help phidata.link/discord