Checked other resources

• This is a feature request, not a bug report or usage question.
• I added a clear and descriptive title that summarizes the feature request.
• I used the GitHub search to find a similar feature request and didn't find it.
• I checked the LangChain documentation and API reference to see if this feature already exists.
• This is not related to the langchain-community package.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-cli
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-perplexity
• langchain-prompty
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Feature Description

Google Gen AI is not supported as a provider in init_embeddings.

Only the Google VertexAI VertexAIEmbedding is used within the factory function for the embeddings. The _init_chat_model already has Google Gen AI has a supported provider.

(In this release note)[https://github.com/langchain-ai/langchain-google/discussions/1422], it is mentioned that the google_gen_ai is the new provider that langchain recommended when using Google services.

Use Case

I am using Google as my service provider and I used the API key as my certification method and I was refused to use google_genai for my embedding while my chat models use Google Generative ai.

From the documentation, I understand that the Google Generative AI will be the new recommended package for Google services, so I just want to make sure that the migration works for embeddings as well.

Proposed Solution

This could be done by adding:

    "google_genai": "langchain_google_genai",

in the mapping (dictionnary) of _SUPPORTED_PROVIDERS in langchain/embeddings/base.py.

if provider == "google_genai":
        from langchain_google_genai import GoogleGenerativeAIEmbeddings
        
        return GoogleGenerativeAIEmbeddings(model=model_name, **kwargs)

in the init_embeddings function in langchain/embeddings/base.py.

Alternatives Considered

I could use Google VertexAI, but the documentation recommend Google Generative AI.

Additional Context

No response