Future-House/paper-qa

Issues

• how to use AZURE_API_KEY

  #775 opened 5 days ago by zhendejuzi
  0

• Reactor: Overly Complicated Question Eval

  #761 opened 13 days ago by whitead
  0

• aiohttp issue, seemingly related to Crossref Search

  #759 opened 12 days ago by meefen
  2

• What's the difference between `context` and `contexts` in the response output?

  #755 opened 16 days ago by n400peanuts
  4

• Parsing JSON error when increasing evidence_k with mixtral:8x7b

  #736 opened 19 days ago by Snikch63200
  6

• Retrying relevance score prompt if score was a float or response isn't valid JSON

  #749 opened 20 days ago by jamesbraza
  0

• Impact of carriage return ('\n'), multiple carriage return and multiple spaces dut to PDF parsing

  #751 opened 20 days ago by Snikch63200
  2

• Feature Request: Support for file ingestion via byte-streams

  #735 opened 20 days ago by steenfuentes
  2

• Fixing the parsing of scientific notation and non-ASCII characters

  #744 opened 21 days ago by loesinghaus
  2

• Pydantic error when parsing context

  #747 opened 20 days ago by Snikch63200
  4

• Paper QA Settings for AWS Bedrock

  #667 opened 2 months ago by istranic
  12

• maybe_is_text() discards valid text due to spaces from titles and tables

  #710 opened 22 days ago by loesinghaus
  1

• Is PaperQA requires LLM 'stream' set up as 'True' ?

  #720 opened a month ago by Snikch63200
  2

• Problem defining EnvironmentState?

  #732 opened a month ago by reubendocea
  3

• how docs are added when using the `agent_query` method?

  #727 opened a month ago by n400peanuts
  1

• Failures to correct evaluate non-single letter answers

  #709 opened a month ago by jamesbraza
  0

• Empty session.answer for exhaustive search without an answer

  #723 opened a month ago by mskarlin
  1

• save and import embeddings for faster answer generation

  #721 opened a month ago by n400peanuts
  4

• Impact of 'num_ctx' and 'num_predict' parameters on answer quality.

  #722 opened a month ago by Snikch63200
  1

• How to control the count of relevant papers and the words of answer?

  #712 opened a month ago by CGH20171006
  1

• JSON Schema

  #700 opened a month ago by cclark1e
  2

• Evaluation bug when answer is not in option list

  #693 opened a month ago by sidnarayanan
  1

• `rate_limited` decorator doesn't pass type checker

  #706 opened a month ago by jamesbraza
  0

• `LLMModel` does not support tool calling

  #701 opened a month ago by jamesbraza
  0

• When the agent is initialized

  #677 opened a month ago by bytesculptors
  3

• Using external vector DBs

  #676 opened 2 months ago by markokow
  1

• Anthropic Claude command line usage

  #663 opened 2 months ago by apaz-cli
  1

• Incorrect LLM Used and API Environment Variable Warnings

  #642 opened 2 months ago by jukti3742
  3

• Performance with Scientific Spec Sheets

  #656 opened 2 months ago by istranic
  1

• How to reproduce wikicrow article generation?

  #635 opened 2 months ago by nebw
  2

• Is using an Instruct model (Mixtral:8x7-INstruct) is relevant with PaperQA ?

  #654 opened 2 months ago by Snikch63200
  1

• api_base settings not useful

  #624 opened 2 months ago by ganansuan647
  4

• Processing files during indexing using multiprocessing for speed boost

  #646 opened 2 months ago by jamesbraza
  0

• Some questions about LLM settings?

  #645 opened 2 months ago by bwnjnOEI
  1

• Enhancement : adding different chunking strategies

  #644 opened 2 months ago by Snikch63200
  0

• Enhancement : complete API Documentation

  #643 opened 2 months ago by Snikch63200
  0

• Setting up SentenceTransformerEmbeddingModel for GPU use.

  #641 opened 2 months ago by Snikch63200
  3

• How correctly setting up a SentenceTransformerEmbeddingModel ?

  #634 opened 2 months ago by Snikch63200
  1

• Using rate_limit functionality in CLI and Python raises KeyError: 'model_list'

  #633 opened 2 months ago by jzqin
  1

• No difference between Docs.query and Docs.aquery in request execution time.

  #631 opened 2 months ago by Snikch63200
  1

• Effect of batch size on answer quality and speed.

  #630 opened 2 months ago by Snikch63200
  1

• Timout error

  #616 opened 2 months ago by Snikch63200
  7

• Agent LLM Token Usage and Cost

  #603 opened 2 months ago by irmadejski
  3

• Bug: changing embedding model doesn't invalidate `Text`s

  #609 opened 2 months ago by jamesbraza
  0

• Chunking strategy and answer relevance vs. Docs() object size ?

  #605 opened 2 months ago by Snikch63200
  1

• Literal translation: "Prompt missing file"？

  #601 opened 2 months ago by appleinmusic
  6

• Setting NumpyVectorStore as embedding model.

  #602 opened 2 months ago by Snikch63200
  2

• Adopting `fsspec` to enable building indexes directly in cloud buckets

  #599 opened 2 months ago by jamesbraza
  0

• Updating the index when using lazy embeddings

  #596 opened 2 months ago by jamesbraza
  0

• Supporting per-page `ImpossibleParsingError` as opposed to per-Document

  #591 opened 2 months ago by jamesbraza
  0