feat(embedding-model-v2): add providerOptions #5698
Merged
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
|
This needs to be introduced end-to-end, i.e. |
samdenty
commented
Apr 12, 2025
lgrammel
reviewed
Apr 12, 2025
packages/provider/src/language-model/v2/language-model-v2-call-options.ts
Outdated
Show resolved
Hide resolved
lgrammel
reviewed
Apr 12, 2025
lgrammel
requested changes
Apr 12, 2025
samdenty
force-pushed
the
feat/embedding-v2-providerOptions
branch
from
3ab9610 to
5a6339f
Compare
lgrammel
reviewed
Apr 14, 2025
lgrammel
approved these changes
Apr 14, 2025
samdenty
added a commit
that referenced
this pull request
Apr 15, 2025
* origin/v5: (36 commits) fix (provider): remove deprecated `Experimental_LanguageModelV2Middleware` (#5775) fix (ai): remove deprecated `options.throwErrorForEmptyVectors` from `cosineSimilarity()` (#5772) fix (ai/core): filter out empty content/text assistant messages (#5767) (#5783) fix (ai): remove deprecated `CoreTool*` types (#5768) chore: refactor text parts (spec) (#5759) feat(embedding-model-v2): add response body field (#5700) feat(embedding-model-v2): add providerOptions (#5698) chore: refactor reasoning parts (spec) (#5756) chore: update .gitignore (#5755) chore: refactor source parts (spec) (#5753) chore: refactor file parts (spec) (#5750) chore: refactor tool call and tool call delta parts (spec) (#5746) fix(providers/xai): edit supported models for structured output (#5715) (#5741) chore (ai): remove provider re-exports (#5734) chore (provider): extract shared provider options and metadata (spec) (#5733) fix(ai/core): properly handle custom separator in provider registry (#5713) (#5732) chore (providers/xai): update grok-3 model aliases (#5646) chore(embedding-model-v2): rename rawResponse to response (#5699) chore(providers/mistral): convert to providerOptions (#5675) chore: refactor file towards source pattern (spec) (#5709) ...
samdenty
added a commit
that referenced
this pull request
Apr 15, 2025
…der-options * origin/v5: (36 commits) fix (provider): remove deprecated `Experimental_LanguageModelV2Middleware` (#5775) fix (ai): remove deprecated `options.throwErrorForEmptyVectors` from `cosineSimilarity()` (#5772) fix (ai/core): filter out empty content/text assistant messages (#5767) (#5783) fix (ai): remove deprecated `CoreTool*` types (#5768) chore: refactor text parts (spec) (#5759) feat(embedding-model-v2): add response body field (#5700) feat(embedding-model-v2): add providerOptions (#5698) chore: refactor reasoning parts (spec) (#5756) chore: update .gitignore (#5755) chore: refactor source parts (spec) (#5753) chore: refactor file parts (spec) (#5750) chore: refactor tool call and tool call delta parts (spec) (#5746) fix(providers/xai): edit supported models for structured output (#5715) (#5741) chore (ai): remove provider re-exports (#5734) chore (provider): extract shared provider options and metadata (spec) (#5733) fix(ai/core): properly handle custom separator in provider registry (#5713) (#5732) chore (providers/xai): update grok-3 model aliases (#5646) chore(embedding-model-v2): rename rawResponse to response (#5699) chore(providers/mistral): convert to providerOptions (#5675) chore: refactor file towards source pattern (spec) (#5709) ...
4 tasks
gr2m
added a commit
that referenced
this pull request
Apr 30, 2025
…5977) ## Background Compare #5698 ## Summary Additional provider-specific options to the image model provider interface. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. Unlike other models, ImageModel request return an array of images, and provider can return image-specific metadata for each. So far, this pull request passing through the revised prompt used for each image. In order to make that possible, I introduced a new type `ImageModelV2ProviderMetadata` which is the same as `SharedV2ProviderMetadata` plus it guarantees the presence of the `.images` key ```js export type ImageModelV2ProviderMetadata = Record< string, { images: JSONArray; } & JSONValue >; ``` That also makes it possible to deeply merge providerMetadata from multiple responses effectively. ## Verification I updated the `examples/ai-core/src/generate-image/openai.ts` example to verify that the code is working.
iteratetograceness
pushed a commit
to iteratetograceness/ai
that referenced
this pull request
May 9, 2025
…ercel#5977) ## Background Compare vercel#5698 ## Summary Additional provider-specific options to the image model provider interface. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider. Unlike other models, ImageModel request return an array of images, and provider can return image-specific metadata for each. So far, this pull request passing through the revised prompt used for each image. In order to make that possible, I introduced a new type `ImageModelV2ProviderMetadata` which is the same as `SharedV2ProviderMetadata` plus it guarantees the presence of the `.images` key ```js export type ImageModelV2ProviderMetadata = Record< string, { images: JSONArray; } & JSONValue >; ``` That also makes it possible to deeply merge providerMetadata from multiple responses effectively. ## Verification I updated the `examples/ai-core/src/generate-image/openai.ts` example to verify that the code is working.
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.
Background
Summary
This adds providerOptions to embedding model v2 for future PRs
Tasks
pnpm prettier-fixto fix any formatting issuesFuture Work