langchain/libs/partners/google-genai
Sparsh Jain a2167614b7
google-genai[patch]: Invoke callback prior to yielding token (#17092)
- **Description:** Invoke callback prior to yielding token in stream and
astream methods for Google-genai,
  - **Issue:** the issue # 16913,
  - **Twitter handle:** Sparsh10649446

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-02-08 13:13:46 -08:00
..
langchain_google_genai google-genai[patch]: Invoke callback prior to yielding token (#17092) 2024-02-08 13:13:46 -08:00
scripts [Partner] Add langchain-google-genai package (gemini) (#14621) 2023-12-13 11:57:59 -08:00
tests google-genai[patch]: match function call interface (#17213) 2024-02-07 17:07:31 -08:00
.gitignore [Partner] Add langchain-google-genai package (gemini) (#14621) 2023-12-13 11:57:59 -08:00
LICENSE [Partner] Add langchain-google-genai package (gemini) (#14621) 2023-12-13 11:57:59 -08:00
Makefile [Partner] Add langchain-google-genai package (gemini) (#14621) 2023-12-13 11:57:59 -08:00
poetry.lock google-genai[minor]: support functions call (#15146) 2024-02-07 12:09:30 -08:00
pyproject.toml google-genai[patch]: release 0.0.7 (#17193) 2024-02-07 17:15:09 -08:00
README.md google-genai[patch]: add google-genai integration deps and extras (#14731) 2023-12-14 13:20:10 -08:00

langchain-google-genai

This package contains the LangChain integrations for Gemini through their generative-ai SDK.

Installation

pip install -U langchain-google-genai

Image utilities

To use image utility methods, like loading images from GCS urls, install with extras group 'images':

pip install -e "langchain-google-genai[images]"

Chat Models

This package contains the ChatGoogleGenerativeAI class, which is the recommended way to interface with the Google Gemini series of models.

To use, install the requirements, and configure your environment.

export GOOGLE_API_KEY=your-api-key

Then initialize

from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(model="gemini-pro")
llm.invoke("Sing a ballad of LangChain.")

Multimodal inputs

Gemini vision model supports image inputs when providing a single chat message. Example:

from langchain_core.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(model="gemini-pro-vision")
# example
message = HumanMessage(
    content=[
        {
            "type": "text",
            "text": "What's in this image?",
        },  # You can optionally provide text parts
        {"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},
    ]
)
llm.invoke([message])

The value of image_url can be any of the following:

  • A public image URL
  • An accessible gcs file (e.g., "gcs://path/to/file.png")
  • A local file path
  • A base64 encoded image (e.g., data:image/png;base64,abcd124)
  • A PIL image

Embeddings

This package also adds support for google's embeddings models.

from langchain_google_genai import GoogleGenerativeAIEmbeddings

embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
embeddings.embed_query("hello, world!")