langchain-google-genai
LangChain integration for Google's Generative AI models, providing access to Gemini models via both the Gemini Developer API and Vertex AI.
As of langchain-google-genai 4.0.0, this package uses the consolidated google-genai SDK instead of the legacy google-ai-generativelanguage SDK.
This migration brings support for Gemini models both via the Gemini Developer API and Gemini API in Vertex AI, superseding certain classes in langchain-google-vertexai, such as ChatVertexAI. Refer to the provider docs and release notes for more information.
Usage documentation Refer to the docs for a high-level guide on how to use each module. These reference pages contain auto-generated API documentation for each module, focusing on the "what" rather than the "how" or "why" (i.e. no end-to-end tutorials or conceptual overviews).
Wrapper exception class for errors associated with the Google GenAI API.
ClientError raised when input exceeds Google's context limit.
Google authentication error classified as a LangChain model error.
Google permission error classified as a LangChain model error.
Google invalid-request error classified as a LangChain model error.
Google not-found error classified as a LangChain model error.
Google rate-limit error classified as a LangChain model error.
Google server error classified as a LangChain model error.
Google GenAI chat model integration.
Google Generative AI Embeddings.
Image loading route.
Loads media bytes from multiple sources given a string.
Google GenerativeAI text completion large language models (legacy LLMs).
Custom exception class for errors associated with the Google GenAI API.
Translate LangChain Citations to Google AI grounding metadata format.
Creates a context cache for the specified model and content.
Encodes image bytes into a b64 encoded string.
Convert tools to google-genai Tool objects.
Returns a custom user agent header.
