6 views
-/https://github.com/berriai/litellm/issues/31061
GitHub · issue

#31061 timeout issue in long pdf

  • State: open
  • Author: @pvssrikanth

Hi

when loading big document 300+ pages

getting timeout error with local model return self.__pydantic_serializer__.to_python( toc found start detect_page_index index found process_toc_with_page_numbers start_index: 1 start toc_transformer

Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new LiteLLM.Info: If you need to debug this error, use `litellm._turn_on_debug()'.

Provider List: https://docs.litellm.ai/docs/providers

************* Retrying ************* ERROR:root:Error: litellm.Timeout: APITimeoutError - Request timed out. Error_str: Request timed out.

WILL THIS SURELY WORK FOR HUGE PDFS 1000+ pages ?

How to resolve these timesouts

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (1 events)
#0 of 0 · 31d18h20m16s ago — entered · #import:https:::github.com:berriai:litellm post #2604
The left issue is harder because it has an unclear root cause and may require profiling, timeout-policy changes, and validation across large-document processing paths. The right issue is a bounded protocol-state change with a clearer implementation surface and focused tests.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search