Skip to content

Retrying Context creation once #1083

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
jamesbraza merged 8 commits into from
Sep 11, 2025
Merged

Retrying Context creation once #1083

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ab99395
Renamed success to successfully_has_score, for understandability
jamesbraza Sep 10, 2025
59f3f7c
Moved to map_fxn_summary giving 1+ LLM results
jamesbraza Sep 10, 2025
3ddb419
Removed unnecesssary annotations import
jamesbraza Sep 10, 2025
aa3388b
Fixed LLMResult import to be from LMI
jamesbraza Sep 10, 2025
54b3559
Retrying context creation once, and then abandoning if it fails twice
jamesbraza Sep 10, 2025
4758b0c
Beefed up test_custom_llm assertions to avoid IndexError
jamesbraza Sep 10, 2025
507293c
Fixed typo from 'other' to 'only'
jamesbraza Sep 10, 2025
c2175f7
Added retrying of bad Context creation, both in non-JSON mode and JSO…
jamesbraza Sep 10, 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
Fixed typo from 'other' to 'only' 
Co-authored-by: Andrew White <white.d.andrew@gmail.com>
  • Loading branch information
@jamesbraza @whitead
jamesbraza and whitead authored Sep 10, 2025
commit 507293cbb3a269ec949282e7bd99f1ecc21d1e9c
2 changes: 1 addition & 1 deletion src/paperqa/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,7 +292,7 @@ async def _map_fxn_summary( # noqa: PLR0912
context = cleaned_text
# If we don't assign scores, just default to 5.
# why 5? Because we filter out 0s in another place
# and 5/10 is the other default I could come up with
# and 5/10 is the only default I could come up with
score = 5
# remove citations that collide with our grounded citations (for the answer LLM)
if not skip_citation_strip:
Expand Down
Loading