feat: improve abstraction for external providers #123
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
pkarw
approved these changes
Dec 14, 2024
|
Great job. Approved with just one question regarding the token usage stats within LLM response - if not now we probably will add it later nevertheless, I mean it's kind of standard per LLM responsy in any framework |
|
Right now, Ollama won't work due to ollama/ollama#8095, unless I misconfigured the request. I will try to replicate this behavior by tweaking the schema and we will see. |
This was referenced Dec 15, 2024
pkarw
approved these changes
Dec 15, 2024
…ework into feat/completions-2
…ework into feat/completions-2
…ework into feat/completions-2
|
I am going to merge it, but let's test it thoroughly tomorrow before cutting release, to make sure it does work as expected! |
|
Grok working good! |
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Outdated suggestions cannot be applied.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.
Slightly better abstraction (but still light-weight) for other providers.
Support for Ollama (tho results with local LLMs are rather poor, I would love if someone could experiment with it).
We may need to tweak prompts on per model basis, which I would see as a task for the future.
Fixes #114