[BUG] Batch Size Exceeded

[ivancaas]

Problem (one or two sentences)

I am getting this error of LITELLM for a service of inference I'm using:
Error - Failed during initial scan: Indexing partially failed: Only 95280 of 176212 blocks were indexed. Failed to process batch after 3 attempts: Failed to create embeddings after 3 attempts: HTTP 422 - 422 litellm.BadRequestError: OpenAIException - Error code: 422 - {'message': 'batch size 60 > maximum allowed batch size 32', 'code': 422, 'type': 'Validation'}
The model I'm using if it makes any sense is qwen3-embedding

Would it be possible to have a setting that handles this?

Context (who is affected and when)

When I want to index any codebase

Reproduction steps

Start Index

Expected result

The index starts and finishes successfuly

Actual result

I get the error

Variations tried (optional)

No response

App Version

3.55.0

API Provider (optional)

OpenAI Compatible

Model Used (optional)

qwen3-embedding

Zoo Code Task Links (optional)

No response

Relevant logs or errors (optional)

- Failed during initial scan: Indexing partially failed: Only 95280 of 176212 blocks were indexed. Failed to process batch after 3 attempts: Failed to create embeddings after 3 attempts: HTTP 422 - 422 litellm.BadRequestError: OpenAIException - Error code: 422 - {'message': 'batch size 60 > maximum allowed batch size 32', 'code': 422, 'type': 'Validation'}