feat: add generic AI provider support (#64)#67
Open
Akash5908 wants to merge 1 commit into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Resolves #64
This PR introduces generic AI provider support to Passmark, allowing users to configure any Vercel AI SDK-compatible provider (e.g., corporate self-hosted proxies, LiteLLM, vLLM, Ollama, etc.) instead of being limited to the hardcoded
gatewayoptions.It adopts a programmatic approach, allowing users to pass a factory function (
createProvider) in theirconfigure()setup.Key Changes
CustomProviderConfigType: Users can now register custom providers and provide optional model name aliases.AIGateway: Thegatewayfield now accepts arbitrary strings without breaking autocomplete for the default literals. This allows routing all models through a single custom gateway.resolveModel):resolveModel()now handles provider-prefix mode (e.g.,llm-proxy/gpt-4) and gateway mode (all models routed through a specific custom provider).createProvideris only executed once per provider.providersmap down from global configurations to per-call and per-stepAIOverrideinstances.README.mdand custom proxy examples to.env.example.Usage Example
Testing Done
pnpm run buildsucceeds with no type errors.pnpm test).src/__tests__/models.test.tsto test custom provider resolution, model aliasing, and caching logic.src/__tests__/config.test.tsto verify overrides merging correctly.