Discussion Piece: Allow env based openAI compatibilty. #1177
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Outdated suggestions cannot be applied.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.



Problem Statement
Long tail LLM providers have a unique value proposition that gives them a portion of the market without being mainstream. For this reason, rather than offer their own API they use OpenAI as the lingua di franco compatibility layer.
Embabel handles this well, allowing registration of a bean. But what about:
Proposed Solution
Most of the pieces are in place already to offer this. However there is a registry of possible openAI models to use. We need to be able to plug in the long-tail vendor's model on the fly, so Embabel can hook it up.
We can do that something like (in this pr):
I used this approach to spin up the hub powered by models provided by Groq. (Not the flashiest of models, but Groq lets them run blisteringly fast).