V0.2.3 #521
Open
V0.2.3 #521
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* refactor: simplify connection setup by removing retry logic and pooling configuration * fix: add endpoint to Azure translation client configuration * feat: split embedding model demand between questions and documents (#507) * feat: split embedding model demand betwee questions and documents * Clean up comments in llm.py * fix: delete Q&A documents when Chat message is deleted (#515) * fix: prevent error when pure keyword Q&A returns no source (#516) * fix: update broken user guide links (#513) updated user guide links * fix: caught exceptions for users with no email in entra_sync * fix: NLTK cache in Dockerfile, quieter logs, Entra user skip on blank email (#517) * feat: split embedding model demand betwee questions and documents * fix: enhance logging during markdown extraction and node creation * feat: add log filtering for specific request keywords * feat: add logging filter to raise log level for specific endpoints * feat: enhance logging during markdown extraction process * feat: add logging for markdown splitting process and page tag fixing * fix: handle missing email and integrity errors during user update or creation * feat: preload NLTK stopwords to avoid runtime errors in llama_index SentenceSplitter * feat: preload NLTK "punkt" and "stopwords" corpora to prevent runtime failures in llama_index SentenceSplitter * feat: preload additional NLTK corpora for enhanced NLP functionality in llama_index * feat: integrate WTPSplit for improved sentence splitting in MarkdownSplitter and preload model data * fix: update Python dependency installation process to ensure latest setuptools is used * fix: correct import path for WTPSplit in Dockerfile to ensure proper functionality * fix: update Dockerfile to set NLTK_DATA environment variable and remove WTPSplit model data preload * fix: refactor MarkdownSplitter to use SentenceSplitter for sentence splitting * fix: add download of 'punkt_tab' NLTK resource for enhanced NLP functionality * fix: refactor MarkdownSplitter to remove WTPSplit dependency and improve logging * fix: remove unnecessary logging in process_document_helper and extract_markdown functions * fix: remove unnecessary comments in OttoLLM class to improve code clarity --------- Co-authored-by: otto-jumpbox <otto@justice.gc.ca> --------- Co-authored-by: otto-jumpbox <otto@justice.gc.ca> Co-authored-by: jannable <Jason.Annable@justice.gc.ca> Co-authored-by: jannable <jason@magnara.ca>
Add cost warning buttons div to chat message template
* perf: single pgvector db connection per app instance * Limit embedding sleep time to a maximum of 64 seconds --------- Co-authored-by: Jules Kuehn <jk@jules.lol>
Contributor
Coverage report
Click to see where and how coverage changed
This report was generated by python-coverage-comment-action |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.