Hi everyone,

I'm currently working on optimizing a function calling prompt for better performance with GPT, but I'm hitting a snag with obtaining accurate results. Despite reviewing available materials, I've found limited guidance on enhancing this specific aspect. Here's a succinct overview:

Goal: Improve function selection based on user queries and context, acknowledging that multiple functions may need to be called for a comprehensive answer.

Available Tools:

GetColumnsConfigTool - Fetches board columns' IDs and names.
GetWorkItemsDeliveryStatusTool - Retrieves work items' delivery status.
GetWorkItensTool - Acquires work items by keys or IDs.
Issue: For the question, "What are the delivery dates for tasks that are in progress?", I anticipated calls to both GetWorkItensTool and GetDeliveryStatusForWorkItems. However, only GetWorkItensTool is being selected.

Query: Does anyone have insights on refining function selection within prompts? Are there models superior to GPT-4-turbo for this use case, or techniques to ensure broader coverage and accuracy?

Appreciate any advice or resources that could shed light on this challenge.

Good morning people, everything fine?

I have some questions related to how to work with unstructured data.

I'm hitting the Github API, getting data from several endpoints and saving it to a Vector database.

Then I'm connected via langchain, to talk to this data.

But the result is pretty bad, anyone doing something similar?

Searching I saw that I will need to transform this data using some entity extraction techniques, training pairs and narrative format.

But I'm in doubt if I'm on the right path, if someone who has knowledge about can help.