Skip to content

Releases: lfoppiano/document-qa

v0.4.2

23 Aug 09:11
Compare
Choose a tag to compare

Fixed

  • Correct invalid dependency of promptlayer slipped in the build

Full Changelog: v0.4.1...v0.4.2

v0.4.1

23 Aug 05:33
Compare
Choose a tag to compare

Added

  • Scroll to the first relevant context passage, if the most relevant context passage is at the end, it will scroll to the end of the document
  • Added Mistral NEMO as default model

Changed

  • Rearranged the interface to get more space
  • Updated libraries to the latest versions

Fixed

  • Fixed the chat messages sequence that were buggy
  • Updated the PDF viewer to the latest version

Full Changelog: v0.4.0...v0.4.1

v0.4.0

24 Jun 22:58
Compare
Choose a tag to compare

What's Changed

  • Add possibility to select different embedding functions

  • Add text rendering on the pdf-viewer (provided by https://github.com/lfoppiano/streamlit-pdf-viewer)

  • Added an experimental feature for calculating the coefficient that relate the question and the embedding database #30

  • Added the data availability statement in the searchable text

  • Removed obsolete and non-working models zephyr and mistral v0.1

  • The underlying library was refactored to make it easier to maintain

  • Removed the native PDF viewer

  • Updated langchain and streamlit to the latest versions

  • Removed conversational memory which was causing more problems than bringing benefits

  • Rearranged the interface to get more space

  • various bugfixes #27

  • Updated and removed models that were not working

  • Fixed problems with langchain and other libraries

Full Changelog: v0.3.4...v0.4.0

v0.3.4

26 Dec 03:31
Compare
Choose a tag to compare

What's Changed

  • Added GPT4 and GPT4-Turbo
  • Update Interface
  • Fixed dependencies when using document-qa-engine as library

Full Changelog: v0.3.3...v0.3.4

v0.3.3

14 Dec 03:39
Compare
Choose a tag to compare

What's Changed

  • Add PDF document rendering in the page by @lfoppiano, @t29mato in #16
  • Minor fixes in the GrobidProcessors API

Full Changelog: v0.3.2...v0.3.3

v0.3.2

29 Nov 08:20
Compare
Choose a tag to compare

What's Changed

  • restrict the chat memory to avoid hallucinations by @lfoppiano in #23
  • fix memory embeddings when the same paper is re-uploaded using a different LLM engine

Full Changelog: v0.3.1...v0.3.2

v0.3.1

22 Nov 13:05
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.3.0...v0.3.1

v0.3.0

18 Nov 11:06
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.2.1...v0.3.0

v0.2.1

02 Nov 02:02
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.2.0...v0.2.1

v0.2.0

31 Oct 06:52
Compare
Choose a tag to compare

What's Changed

Added

  • Selection of chunk size on which embeddings are created upon
  • Mistral model to be used freely via the Huggingface free API

Changed

  • Improved documentation, adding privacy statement
  • Moved settings on the sidebar
  • Disable NER extraction by default, and allow user to activate it
  • Read API KEY from the environment variables and if present, avoid asking the user
  • Avoid changing model after update

Full Changelog: v0.1.3...v0.2.0