Skip to content
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.

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

feat: exclude embedding and llm metadata! #47

Merged
merged 14 commits into from
Jan 25, 2024

Conversation

amindadgar
Copy link
Member

  • Excluding all metadata for embedding model.
  • Including date, channel, author_username, channel and thread for LLM.
  • Adding a dot at the end of discord message content, as it would prevent the node not having any data when the message was empty.

- Excluding all metadata for embedding model.
- Including `date`, `channel`, `author_username`, `channel` and `thread` for LLM.
- Adding a dot at the end of discord message content, as it would prevent the node not having any data when the message was empty.
The test cases were related to previous PRs of adding `fromDate` to modules collection.
if from_date was equal to `None`, it would use the modules fromDate which in our case the modules date wasn't configured correctly!
- The url extractor is now more consistent as we changed to use a library.
- Checking the messages for any alphabetical content after urls removed.
In case of globalName and nickname being very different from username the LLM wouldn't be able to answer, so we included these two information.
…de-embed-llm-data

Merge branch 'update/backend-dependency-lib' into feat/hivemind-exclude-embed-llm-data
That branch was fixing some test cases which we forgot to fix before.
- We've included the `None` value for test cases so we the LLM wouldn't be confused if the message was sent in channel.
@cyri113 cyri113 merged commit 97c8b8c into main Jan 25, 2024
16 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
3 participants