Hacker News new | past | comments | ask | show | jobs | submit login

Does anyone know if this is just a "native" RAG implementation? Or if it's actually fine tuned models?



Native RAG, with likely some secret sauce to align the models a bit better: https://platform.openai.com/docs/assistants/tools/knowledge-...

> Retrieval augments the Assistant with knowledge from outside its model, such as proprietary product information or documents provided by your users. Once a file is uploaded and passed to the Assistant, OpenAI will automatically chunk your documents, index and store the embeddings, and implement vector search to retrieve relevant content to answer user queries.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: