Skip to content

Conversation

akashSharmaDev
Copy link

Resolved an issue where Azure Search was using the identifier field (typically id) as the search field. Since identifier fields are not marked as searchable in the index, this caused search requests to fail. The implementation now ensures that only valid searchable fields are used for query execution, preventing HttpResponseError related to non-searchable fields.

…rch field, But identifiers are mainly id which are not searchable
@pamelafox
Copy link
Collaborator

@akashSharmaDev Hm, the identifier_field is searchable in the index that's set up by the integrated vectorization script:
Screenshot 2025-08-18 at 12 16 52 PM

Are you using this with a different index?

# are generated, where chunk_id is searchable with a keyword tokenizer, not filterable
search_results = await search_client.search(search_text=list,
search_fields=[identifier_field],
search_fields=[content_field],
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This seems like a functional difference, to search the content field for the grounding sources, how does this work? It's sending in a query like "4c1968ac98f3_aHR0cHM6Ly9zdGVqN2o0ZzJ6cG96ZXMuYmxvYi5jb3JlLndpbmRvd3MubmV0L2NvbnRlbnQvcm9sZV9saWJyYXJ5LnBkZg2_pages_36" which wouldnt be in the content field.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants