VertexAICodeGenerator

Generate code using Google Vertex AI generative models.

Key Features

• Generates code using Vertex AI models (code-bison, code-bison-32k, code-gecko).
• Accepts a code prefix and an optional suffix to enable in-fill code generation.
• Authenticates using Google Cloud Application Default Credentials.
• Returns a list of generated code snippets.

Configuration

Authentication

This component authenticates using Google Cloud Application Default Credentials (ADCs). For more information, see the official Google documentation.

Create secrets with the following keys: GCP_PROJECT_ID and optionally GCP_DEFAULT_REGION. For detailed instructions on creating secrets, see Create Secrets.

1. Drag the VertexAICodeGenerator component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name (for example, code-bison).
4. Go to the Advanced tab to configure the project ID, location, and additional model kwargs.

Connections

VertexAICodeGenerator accepts prefix (code before the current point) and an optional suffix (code after the current point) as inputs. It outputs a list of generated code snippets (replies).

Typically, you connect the pipeline query input to prefix and connect replies to AnswerBuilder.

Usage Example

This pipeline uses VertexAICodeGenerator to generate code:

components:
  VertexAICodeGenerator:
    type: haystack_integrations.components.generators.google_vertex.code_generator.VertexAICodeGenerator
    init_parameters:
      model: code-bison
      project_id:
      location:
  AnswerBuilder:
    type: haystack.components.builders.answer_builder.AnswerBuilder
    init_parameters:
      pattern:
      reference_pattern:
      last_message_only: false
      return_only_referenced_documents: true

connections:
- sender: VertexAICodeGenerator.replies
  receiver: AnswerBuilder.replies

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - VertexAICodeGenerator.prefix
  - AnswerBuilder.query

outputs:
  answers: AnswerBuilder.answers

Parameters

Inputs

Parameter	Type	Default	Description
prefix	str		Code before the current point.
suffix	Optional[str]	None	Code after the current point.

Outputs

Parameter	Type	Default	Description
replies	List[str]		A list of generated code snippets.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
project_id	Optional[str]	None	ID of the GCP project to use. By default, it is set during Google Cloud authentication.
model	str	code-bison	Name of the model to use.
location	Optional[str]	None	The default location to use when making API calls. If not set, uses us-central-1.
kwargs	Any		Additional keyword arguments to pass to the model. See the TextGenerationModel.predict() documentation.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
prefix	str		Code before the current point.
suffix	Optional[str]	None	Code after the current point.