a few updates that makes it work much better for me but adds openai api for creating summaries...#8
Open
jamie-beck wants to merge 10 commits intoSogody:mainfrom
Open
a few updates that makes it work much better for me but adds openai api for creating summaries...#8jamie-beck wants to merge 10 commits intoSogody:mainfrom
jamie-beck wants to merge 10 commits intoSogody:mainfrom
Conversation
jamie-beck
changed the title
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This helped with "content too long" #3
I also made it work as described in the openapi.yaml in regards to the first 3 results having the full text and the results 4-5 being summaries. Some minor logic cleanup removing redundant ranges for loops etc.
I added a .env.template to more easily work with added variables over time.
The readme was updated with the new openai key requirements.
EDIT:
I've upped the search results returned to 10 but still only the first 3 have full (3500 char limit) text.
Now added the ability to read the text of pdf search results.
EDIT 2:
Now uses token counts to shorten text so we can more accurately pack the context.