Get the latest tech news
RAG, fine-tuning, API calling and gptscript for Llama 3 running locally
RAG support in Helix Patch fix - 0.9.1 fixes streaming in the UI for plain inference sessions. 0.9 release notes We now support RAG in Helix. You can upload documents and perform RAG over them fr...
We have also switched "inference" and "finetune" to the more generic and user friendly "chat" and "learn": RAG is better at retrieving specific facts, whereas fine-tuning is better at answering general questions about the documents uploaded. You can still fine-tune, either choose fine tuning from the app homepage, or use the settings button:
Or read this on Hacker News
