This package contains common resources to access Google AI/ML models and other Google services in an auth-independent way.
AI/ML models are supported using the same interface no matter if you are using the Google AI Studio-based version of the model or the Google Cloud Vertex AI version of the model.
This is not a stand-alone package since it does not contain code to do authorization.
Instead, you should install one of the following packages:
See those packages for details about installation.
This package does not depend on any Google library. Instead, it relies on REST calls to Google endpoints. This is deliberate to reduce (sometimes conflicting) dependencies and make it usable on platforms that do not include file storage.
When using tools or functions with Gemini models, the following Zod schema features are not supported:
z.discriminatedUnion()) - Use flat objects with optional fields insteadz.union()) - Use separate optional fieldsz.number().positive()) - Automatically converted to z.number().min(0.01)For detailed examples and workarounds, see the Tool Schema Limitations section in the @langchain/google-vertexai or @langchain/google-genai package documentation.
Tasks and services that may be implemented in the future:
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Represents a chunk of data that can be identified by the path where the
A specialized Store that is designed to handle MediaBlobs and use the
A specialized Store that is designed to handle MediaBlobs and use the
A specialized Store that is designed to handle MediaBlobs and use the
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
A specialized Store that is designed to handle MediaBlobs and use the
A specialized Store that is designed to handle MediaBlobs and use the
A blob "store" that works with data: URLs that will turn the URL into
Represents a chunk of data that can be identified by the path where the
Responsible for converting a URI (typically a web URL) into a MediaBlob.
A specialized Store that is designed to handle MediaBlobs and use the
A specialized Store that is designed to handle MediaBlobs and use the
Parameters needed to setup the client connection.
Enables calls to Google APIs for generating
Parameters needed to setup the client connection.
Integration with a Google chat model.
Parameters needed to setup the client connection.
Integration with an LLM.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Based on https://cloud.google.com/storage/docs/json_api/v1/objects#resource
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
Input to chat model class.
Defines additional options specific to the
Defines the parameters required to initialize a
The params which can be passed to the API at request time.
Parameters needed to setup the client connection.
The params which can be passed to the API at request time.
Input to LLM class.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
A simplified version of the GoogleSpeakerVoiceConfig
Represents an instance for generating embeddings using the Google
Defines the structure of the embeddings results returned by the Google
Defines additional options specific to the
Defines the parameters required to initialize a
The params which can be passed to the API at request time.
Parameters needed to setup the client connection.
The params which can be passed to the API at request time.
Input to LLM class.
Parameters needed to setup the client connection.
Parameters needed to setup the client connection.
A simplified version of the GoogleSpeakerVoiceConfig
Represents an instance for generating embeddings using the Google
Defines the structure of the embeddings results returned by the Google
What platform is this running on?
A simplified way to represent the voices.
A simplified way to represent the voice (or voices) and language code.
What platform is this running on?
A simplified way to represent the voices.
A simplified way to represent the voice (or voices) and language code.