ChatVertex
ChatVertex(=None,
model=None,
project=None,
location=None,
api_key=None,
system_prompt=None,
turns=None,
kwargs )
Chat with a Google Vertex AI model.
Prerequisites
Python requirements
ChatGoogle
requires the google-genai
package (e.g., pip install google-genai
).
Credentials
To use Google’s models (i.e., Vertex AI), you’ll need to sign up for an account with Vertex AI, then specify the appropriate model, project, and location.
Parameters
Name | Type | Description | Default |
---|---|---|---|
model | Optional[str] | The model to use for the chat. The default, None, will pick a reasonable default, and warn you about it. We strongly recommend explicitly choosing a model for all but the most casual use. | None |
project | Optional[str] | The Google Cloud project ID (e.g., “your-project-id”). If not provided, the GOOGLE_CLOUD_PROJECT environment variable will be used. | None |
location | Optional[str] | The Google Cloud location (e.g., “us-central1”). If not provided, the GOOGLE_CLOUD_LOCATION environment variable will be used. | None |
system_prompt | Optional[str] | A system prompt to set the behavior of the assistant. | None |
turns | Optional[list[Turn]] | A list of turns to start the chat with (i.e., continuing a previous conversation). If not provided, the conversation begins from scratch. Do not provide non-None values for both turns and system_prompt . Each message in the list should be a dictionary with at least role (usually system , user , or assistant , but tool is also possible). Normally there is also a content field, which is a string. |
None |
Returns
Name | Type | Description |
---|---|---|
Chat | A Chat object. |
Examples
import os
from chatlas import ChatVertex
= ChatVertex(
chat ="your-project-id",
project="us-central1",
location
)"What is the capital of France?") chat.chat(