fix: More Fault Tolerance with OpenAI Schemas #4328
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
6 tasks
|
I'll be very excited to provide feedback when this is released. Is there an incremental container build that I could test from this PR? |
|
Yes, once this is merged you can try out the nightly branch. More info here: https://docs.mealie.io/documentation/getting-started/installation/installation-checklist/#docker-tags |
hay-kot
reviewed
Oct 12, 2024
hay-kot
approved these changes
Oct 12, 2024
|
Can confirm this works with my local instance of ollama now. Sadly though it appears to be less valuable than using NLP or Brute. Is there a place that people are discussing the model performance with mealie parsing? |
michael-genson
deleted the
fix/make-openai-responses-more-fault-tolerant
branch
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Outdated suggestions cannot be applied.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.
What type of PR is this?
(REQUIRED)
What this PR does / why we need it:
(REQUIRED)
Some LLMs don't properly read our schema. While in general it should be the burden of the model/training-data to handle things correctly, we can be a bit more fault tolerant.
This PR coerces empty strings as a value of "0" for float fields.
Which issue(s) this PR fixes:
(REQUIRED)
Fixes #4327