issues
search
Future-House
/
paper-qa
High accuracy RAG for answering questions from scientific documents with citations
Apache License 2.0
6.44k
stars
617
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Adding assertion `gather_evidence` doesn't populate `session.answer`
#716
jamesbraza
opened
15 hours ago
0
Lock file maintenance
#715
renovate[bot]
opened
1 day ago
0
Fixes `gather_with_concurrency` typing
#714
maykcaldas
opened
1 day ago
0
Fixed settings `session` into `EnvironmentState`, and suppressing PyMuPDF derived `DeprecationWarning`
#713
jamesbraza
closed
1 day ago
0
How to control the count of relevant papers and the words of answer?
#712
CGH20171006
opened
1 day ago
1
Fixed mutably defaulted `NumpyVectorStore.texts`
#711
jamesbraza
closed
2 days ago
0
maybe_is_text() discards valid text due to spaces from titles and tables
#710
loesinghaus
opened
2 days ago
1
Failures to correct evaluate non-single letter answers
#709
jamesbraza
opened
2 days ago
0
Fixing `LitQAEvaluation` bugs: incorrect reward indices, not using LLM's native knowledge
#708
jamesbraza
closed
2 days ago
0
Adding filters to paper-qa Docs
#707
whitead
closed
2 days ago
0
`rate_limited` decorator doesn't pass type checker
#706
jamesbraza
opened
2 days ago
0
Update all non-major dependencies
#705
renovate[bot]
closed
2 days ago
1
Refactor to enable message parts
#704
whitead
opened
2 days ago
0
Fixing `PaperQAEnvironment.reset` respecting `mmr_lambda` and `text_hashes`
#703
jamesbraza
closed
2 days ago
0
Refactored `TestGradablePaperQAEnvironment` for DRY code
#702
jamesbraza
closed
2 days ago
0
`LLMModel` does not support tool calling
#701
jamesbraza
opened
3 days ago
0
JSON Schema
#700
cclark1e
opened
3 days ago
2
Lock file maintenance
#699
renovate[bot]
closed
3 days ago
0
Removed `"cannot answer"` literals and added `reset` tool
#698
jamesbraza
closed
2 days ago
0
Default to ordered tool calls, w env variable control
#697
mskarlin
closed
4 days ago
0
Added missing `test_from_question` cassette
#696
jamesbraza
closed
5 days ago
0
Moved `fake` agent to LLM propose `complete` tool
#695
jamesbraza
closed
5 days ago
0
Making sure we copy distractors
#694
sidnarayanan
closed
6 days ago
0
Evaluation bug when answer is not in option list
#693
sidnarayanan
closed
2 days ago
1
Fixing flaky test `test_gather_evidence_rejects_empty_docs`
#692
jamesbraza
closed
6 days ago
1
Removed `GenerateAnswer.FAILED_TO_ANSWER` as its unnecessary
#691
jamesbraza
closed
6 days ago
0
Fixed LDP runner's `TRUNCATED` not calling `gen_answer`, and documented `AgentStatus`
#690
jamesbraza
closed
6 days ago
0
Removed `gen_answer`'s dead argument `question`
#689
jamesbraza
closed
6 days ago
0
Allowing serialized `Settings` in `get_settings`
#688
jamesbraza
closed
6 days ago
0
Implement support to BatchAPIs to gather evidence
#687
maykcaldas
opened
1 week ago
0
Fixing `test_evaluation` logic bugs
#686
jamesbraza
closed
1 week ago
0
Removed `tool_names` validation for `gen_answer` being present
#685
jamesbraza
closed
1 week ago
0
Created `complete` tool to allow unsure answers
#684
jamesbraza
closed
6 days ago
2
Fixed agent prompt names and contents after #681 mess up
#683
jamesbraza
closed
1 week ago
0
Resolving `evidence_detailed_citations` and `Answer` deprecations
#682
jamesbraza
closed
1 week ago
0
Moved agent prompts to `prompts.py`
#681
jamesbraza
closed
1 week ago
0
Refactor to remove `skip_system` from `LLMModel.run_prompt`
#680
jamesbraza
closed
1 week ago
0
Deprecation cycle for `AgentSettings.should_pre_search`
#679
jamesbraza
closed
1 week ago
0
When the agent is initialized
#677
bytesculptors
closed
1 week ago
3
Using external vector DBs
#676
markokow
opened
1 week ago
1
Changed it to be debug for source quality
#675
whitead
closed
1 week ago
1
Allowing latest `pydantic-settings` and regenerated cassettes
#674
jamesbraza
closed
1 week ago
0
Optional `AnswerSetting.max_answer_attempts` to allow a new unsure branch
#673
jamesbraza
closed
1 week ago
0
`fake` agent allowing timeouts or exceptions,
#672
jamesbraza
closed
1 week ago
0
Empty tool calls leading to `done` condition
#671
jamesbraza
closed
1 week ago
1
Made it so you do not die on invalid tool
#670
whitead
closed
1 week ago
0
Made o1 temperature issue a warning, instead of valueerror
#669
whitead
closed
2 weeks ago
0
Catch edge case where externalIds field is None
#668
mskarlin
closed
2 weeks ago
0
Paper QA Settings for AWS Bedrock
#667
istranic
opened
2 weeks ago
6
Convert citation to formatted_citation usage where necessary
#666
mskarlin
closed
2 weeks ago
1
Next