Viewing profile — amitness

It's not enabled by default for their function calling API. So, hallucination is possible. You have to set 'strict' to True manually to use the same grammar-based sampling they use…

Try this trick that I learned from Cohere: - Fetch top 10*k (i.e. 100) results using the hamming distance - Rerank by taking dot product between query embedding (full precision) an…

OpenAI recommends using o1 to generate the verbose plan and then chain the verbose output to a cheaper model (e.g. gpt-4o-mini) to convert it into structured data / function calls …