LLMs
ChatGoogleVertexAI
LLMs
ChatGoogleVertexAI
The ChatGoogleVertexAI node is a wrapper around Google Vertex AI’s large language models that use the Chat endpoint. It provides an interface to interact with Google’s advanced conversational AI models.
Node Details
- Name: chatGoogleVertexAI
- Type: ChatGoogleVertexAI
- Version: 4.0
- Category: Chat Models
- Name: chatGoogleVertexAI
- Type: ChatGoogleVertexAI
- Version: 4.0
- Category: Chat Models
Base Classes
- ChatGoogleVertexAI
- BaseChatModel
- BaseLanguageModel
- Runnable
Parameters
Parameters
Credential
- Type: googleVertexAuth
- Description: Google Vertex AI credential. Not required if using a GCP service like Cloud Run or if default credentials are installed on the local machine.
Credential
- Type: googleVertexAuth
- Description: Google Vertex AI credential. Not required if using a GCP service like Cloud Run or if default credentials are installed on the local machine.
Inputs
- Model Name
- Type: asyncOptions
- Default: “chat-bison”
- Description: The name of the Google Vertex AI model to use
Inputs
-
Model Name
- Type: asyncOptions
- Default: “chat-bison”
- Description: The name of the Google Vertex AI model to use
-
Cache (optional)
- Type: BaseCache
- Description: Caching mechanism for storing and retrieving conversation history
-
Cache (optional)
- Type: BaseCache
- Description: Caching mechanism for storing and retrieving conversation history
-
Temperature (optional)
- Type: number
- Default: 0.9
- Step: 0.1
- Description: Controls the randomness of the model’s output. Higher values make the output more random, while lower values make it more deterministic
-
Temperature (optional)
- Type: number
- Default: 0.9
- Step: 0.1
- Description: Controls the randomness of the model’s output. Higher values make the output more random, while lower values make it more deterministic
-
Max Output Tokens (optional)
- Type: number
- Step: 1
- Description: The maximum number of tokens to generate in the output
-
Max Output Tokens (optional)
- Type: number
- Step: 1
- Description: The maximum number of tokens to generate in the output
-
Top Probability (Top P) (optional)
- Type: number
- Step: 0.1
- Description: Limits the selection of tokens to a subset that together have a cumulative probability of at most Top P
-
Top Probability (Top P) (optional)
- Type: number
- Step: 0.1
- Description: Limits the selection of tokens to a subset that together have a cumulative probability of at most Top P
-
Top Next Highest Probability Tokens (Top K) (optional)
- Type: number
- Step: 1
- Description: Limits the number of tokens considered for each step of text generation to the K highest probability tokens
-
Top Next Highest Probability Tokens (Top K) (optional)
- Type: number
- Step: 1
- Description: Limits the number of tokens considered for each step of text generation to the K highest probability tokens
Use Cases
- Conversational AI: Develop chatbots and virtual assistants that can engage in human-like conversations across various domains.
- Content Generation: Generate high-quality text content for articles, product descriptions, or creative writing.
- Language Translation: Utilize the model’s multilingual capabilities for translating text between different languages.
- Question Answering: Create systems that can understand and respond to user queries with relevant and accurate information.
- Text Summarization: Automatically generate concise summaries of longer texts or documents.
- Sentiment Analysis: Analyze the sentiment and emotional tone of text inputs for market research or customer feedback processing.
- Code Generation and Explanation: Assist developers by generating code snippets or explaining complex code structures.
- Personalized Recommendations: Generate personalized content or product recommendations based on user preferences and historical data.
Notes
- This node requires proper authentication with Google Vertex AI services. Ensure that you have the necessary credentials and permissions set up.
- The performance and capabilities of the model may vary depending on the selected model name and parameters.
- Be mindful of token usage and associated costs when using this node in production environments.