langchain_google changelog

📣 Check out the releases page or the #announcements channel on the LangChain.dart Discord server for more details.

0.6.4+2 #

REFACTOR: Add new lint rules and fix issues (#621). (60b10e00)

0.6.4+1 #

FIX: UUID 'Namespace' can't be assigned to the parameter type 'String?' (#566). (1e93a595)

0.6.4 #

FEAT: Add support for code execution in ChatGoogleGenerativeAI (#564). (020bc096)

0.6.3+1 #

FEAT: Add support for reduced output dimensionality in GoogleGenerativeAIEmbeddings (#544). (d5880704)
DOCS: Update Google's models in documentation (#551). (1da543f7)

0.6.2 #

FEAT: Add copyWith method to all RunnableOptions subclasses (#531). (42c8d480)

0.6.1 #

FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
REFACTOR: Remove default model from the language model options (#498). (44363e43)
REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

0.6.0 #

Note: ChatGoogleGenerativeAI now uses gemini-1.5-flash model by default.

BREAKING FEAT: Update ChatGoogleGenerativeAI default model to gemini-1.5-flash (#462). (c8b30c90)
FEAT: Add support for ChatToolChoiceRequired (#474). (bf324f36)
FEAT: Support response MIME type and schema in ChatGoogleGenerativeAI (#461). (e258399e)
REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

0.5.1 #

FEAT: Add Runnable.close() to close any resources associated with it (#439). (4e08cced)

0.5.0 #

Note: ChatGoogleGenerativeAI and GoogleGenerativeAIEmbeddings now use the version v1beta of the Gemini API (instead of v1) which support the latest models (gemini-1.5-pro-latest and gemini-1.5-flash-latest).

VertexAI for Firebase (ChatFirebaseVertexAI) is available in the new langchain_firebase package.

FEAT: Add support for tool calling in ChatGoogleGenerativeAI (#419). (df41f38a)
DOCS: Add Gemini 1.5 Flash to models list (#423). (40f4c9de)
BREAKING FEAT: Migrate internal client from googleai_dart to google_generative_ai (#407). (fa4b5c37)

0.4.0 #

Note: This release has breaking changes.
If you are using "function calling" check how to migrate to "tool calling".

BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)

0.3.0+2 #

Update a dependency to the latest release.

0.3.0+1 #

Update a dependency to the latest release.

0.3.0 #

Note: This release has breaking changes.
Migration guide

BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
BREAKING REFACTOR: Remove deprecated generate and predict APIs (#335). (c55fe50f)
REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
FEAT: Implement .batch support (#370). (d254f929)
FEAT: Add streaming support in ChatGoogleGenerativeAI (#360). (68bfdb04)
FEAT: Support tuned models in ChatGoogleGenerativeAI (#359). (764b633d)
FEAT: Add support for GoogleGenerativeAIEmbeddings (#362). (d4f888a0)
FEAT: Support output dimensionality in GoogleGenerativeAIEmbeddings (#373). (6dcb27d8)
FEAT: Support updating API key in Google AI client (#357). (b9b808e7)

0.2.4 #

FEAT: Update meta and test dependencies (#331). (912370ee)
DOCS: Update pubspecs. (d23ed89a)

0.2.3+3 #

DOCS: Update CHANGELOG.md. (d0d46534)

0.2.3+2 #

Update a dependency to the latest release.

0.2.3+1 #

REFACTOR: Remove tiktoken in favour of countTokens API on VertexAI (#307). (8158572b)

0.2.3 #

REFACTOR: Use cl100k_base encoding model when no tokenizer is available (#295). (ca908e80)
REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)
REFACTOR: Migrate tokenizer to langchain_tiktoken package (#285). (6a3b6466)
FEAT: Update internal dependencies (#291). (69621cc6)

0.2.2+1 #

Update a dependency to the latest release.

0.2.2 #

Update a dependency to the latest release.

0.2.1+2 #

Update a dependency to the latest release.

0.2.1+1 #

DOCS: Update langchain_google README. (5b2acfa1)

0.2.1 #

FEAT: Add support for ChatGoogleGenerativeAI wrapper (Gemini API) (#270). (5d006c12)

0.2.0+1 #

Update a dependency to the latest release.

0.2.0 #

Note: This release has breaking changes.

Migration guides:

VertexAI

ChatVertexAI

BREAKING FEAT: Move all model config options to VertexAIOptions (#241). (a714882a)
BREAKING FEAT: Move all model config options to ChatVertexAIOptions (#242). (89bef8a2)
FEAT: Allow to mutate default options (#256). (cb5e4058)

0.1.0+4 #

Update a dependency to the latest release.

0.1.0+3 #

Update a dependency to the latest release.

0.1.0+2 #

Update a dependency to the latest release.

0.1.0+1 #

DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

0.1.0 #

Note: This release has breaking changes.
Migration guide

BREAKING FEAT: Add multi-modal messages support with OpenAI Vision (#220). (6da2e069)

0.0.10+1 #

DOCS: Update vector stores documentation. (dad60d24)

0.0.10 #

FEAT: Add result id in ChatVertexAI generations (#195). (a5bea6d3)

0.0.9 #

Note: This release has breaking changes.

DOCS: Update changelog. (d45d624a)
BREAKING FEAT: Update uuid internal dependency to 4.x.x (#173). (b01f4afe)

0.0.8 #

Updated langchain dependency

0.0.7+1 #

REFACTOR: Require http.Client instead of AuthClient (#156). (0f7fee7f)

0.0.7 #