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.

Modules

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).

• ChatGoogleGenerativeAI — Gemini chat models (primary interface). Reference

• GoogleGenerativeAI — (Legacy) Google text completion abstraction. Reference

• GoogleGenerativeAIEmbeddings — Gemini embedding models. Reference

• create_context_cache — Utility to create a context cache for reusing large content across requests. Reference

• HarmCategory — Enum for safety setting harm categories. Reference

• HarmBlockThreshold — Enum for safety setting blocking thresholds. Reference

• Modality — Enum for input/output modality configuration. Reference

• MediaResolution — Enum for media resolution settings. Reference

• ComputerUse — Enum for computer use capabilities. Reference

• Environment — Enum for environment configuration. Reference