ChatChat fix(deps): update dependency @google/generative-ai to ^0.21.0

fix(deps): update dependency @google/generative-ai to ^0.21.0

Open renovate[bot] opened this issue 10 months ago • 1 comments

This PR contains the following updates:

Package	Change	Age	Adoption	Passing	Confidence
@google/generative-ai	`^0.7.1` -> `^0.21.0`

Release Notes

google/generative-ai-js (@google/generative-ai)

`v0.21.0`

Compare Source

Minor Changes

8543716: Add search grounding feature to SDK.

`v0.20.0`

Compare Source

Minor Changes

dda0b5c: Add frequencyPenalty, presencePenalty, responseLogprobs, and logProbs parameters support for generationConfig. Added avgLogprobs and logprobsResult to GenerateContentResponse. Updated test cases.

`v0.19.0`

Compare Source

Minor Changes

00dc7a1: Use lowercase SchemaType enum values to match json-schema.

`v0.18.0`

Compare Source

Minor Changes

fc008a1: Add ability to set modelParams (generationConfig, safetySettings) on getGenerativeModelFromCachedContent().

`v0.17.2`

Compare Source

Patch Changes

d8f6b4f: Fix language marker in text helper for executable code results.

`v0.17.1`

Compare Source

Patch Changes

fdfb5bd: Fix reference to requestOptions in startChat.

`v0.17.0`

Compare Source

Minor Changes

3b5daae: Fix Schema type to reference itself and not a derived type in its items array and properties map.

`v0.16.1`

Compare Source

This is a cherry-picked patch to fix an bug for users pinned to versions 0.16.x.

Patch Changes

fdfb5bd: Fix reference to requestOptions in startChat.

`v0.16.0`

Compare Source

Minor Changes

d2d42ca: Adds SingleRequestOptions with AbortSignal support to most of the asynchronous methods of GenerativeModel, GoogleAIFileManager and ChatSession.

`v0.15.0`

Compare Source

Minor Changes

05b8631: Add FinishReason.LANGUAGE enum value.

Patch Changes

e87d5b0: Fix countTokens to include any params set on the model instance.

`v0.14.1`

Compare Source

Patch Changes

0c23bb3: Add CodeExecutionTool to Tool type.

`v0.14.0`

Compare Source

Minor Changes

fb1c0f2: Add a cachedContentTokenCount field to the UsageMetadata interface returned by generateContent responses.
06216be: Add code execution feature.

`v0.13.0`

Compare Source

Minor Changes

83ec4ac: Expand the model's countTokens method to alternatively accept a GenerateContentRequest.
5df61d1: Added GoogleAICacheManager utility to allow caching large content to be used in inference. This class is exported from the @google/generative-ai/server subpath. Breaking change: The GoogleAIFileManager class has been moved to be exported from this subpath as well instead of the /files subpath.

Patch Changes

1440a05: Removed the model field from the internally formatted payload of countToken requests as it was unnecessary.
03eb57b: Fix missing usageMetadata in streamed aggregated response (#174)