Add files to LLM context. #253
Merged
Conversation
This file contains 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
|
Now that we have this, would be great to expose something like "attachment summarization" |
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Outdated suggestions cannot be applied.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.
Closes: #245
Closes: #61
Description
Adds files to the context of the context of the LLM. Any file that is supported by the server text extraction (including PDFs) should work as long as that text extraction works. For some reason that extraction doesn't work on text files so the ability to extract text files was added here.
Docs on Text extraction: https://docs.mattermost.com/collaborate/search-for-messages.html
Many files will be over the limit of your LLM or will reach the token limit set in the system console. Files that are too long will cause the prompt to be cut off at the beginning. Set the token limit of your LLM in the system console to make sure this works correctly.
Use a high token limit LLM to use this effectively, all but the latest (llama3.2) on-prem models will have issues with large files.