Inconsistent File Access Behavior in Assistant API Between Playground and Programmatic Calls

Description: I’ve encountered an issue with the Assistant API related to file handling. When using the Assistant API’s playground, it appears to have access to files uploaded to the assistant. However, when the API is called programmatically, its behavior is inconsistent.

Steps to Reproduce:

  1. Upload files to the Assistant.
  2. Test file access in the API playground - files are accessible.
  3. Make an API call to query the files (e.g., “What files do you have?”).
  4. Attempt to perform operations on these files through the API (e.g., summarizing content or answering questions based on the file contents).

Expected Behavior: The API should be able to access and interact with the files consistently, both in the playground and when called programmatically. This includes performing tasks like summarizing content or answering questions based on these files.

Actual Behavior: The API successfully acknowledges and lists the files when queried. However, when asked to perform tasks involving the content of these files, it fails to access them, despite the fact that file IDs are attached and visible in the API response.


I’m facing same issue. Are there any solution that you can found?

I’m also facing same issue and hoping for a workaround or response from the team!

in my experience right now with v2 playground, playground retrieval is not correctly retrieving information uploaded when my prompts (one-shot long prompt) asks for reminding me about previous sessions, the system retrieves “previous” info but that is not stored anymore (any cache issue?), but retrieval is correctly activated in chat and work well when I trigger it in conversation as a user. did you get similar issues?