Skip to content

Gather evidence fails gracefully on timeout #1103

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sidnarayanan merged 5 commits into from
Sep 25, 2025
Merged

Gather evidence fails gracefully on timeout #1103

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
bbaaf03
_map_fxn_summary fails gracefully on timeout
sidnarayanan Sep 24, 2025
6baf6e3
use %s in logger.exception
sidnarayanan Sep 24, 2025
83e5ff4
tweak exception messages; error_log->help_message
sidnarayanan Sep 24, 2025
45da950
propagate help_message
sidnarayanan Sep 24, 2025
75f85d7
rm skipif
sidnarayanan Sep 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
propagate help_message
  • Loading branch information
@sidnarayanan
sidnarayanan committed Sep 24, 2025
commit 45da950d39f4bbd7ad59a766f1c136d535f1eaec
4 changes: 2 additions & 2 deletions src/paperqa/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,7 @@ class LLMBadContextJSONError(LLMContextError):
"""Retryable exception for when the LLM gives back bad JSON."""

retryable = True
error_log = (
help_message = (
"Abandoning this context creation."
" Your model may not be capable of supporting JSON output"
" or our parsing technique could use some work. Try"
Expand All @@ -151,7 +151,7 @@ class LLMContextTimeoutError(LLMContextError):
"""Non-retryable exception for when the LLM call times out."""

retryable = False
error_log = (
help_message = (
"Timeout when creating a context, abandoning it."
" If you see this error frequently, consider increasing the timeout in"
" Settings(summary_llm_config=...). Or, feel free to just ignore this message,"
Expand Down