VertexAIGeminiChatGenerator

Complete chats using Google Gemini models through Vertex AI.

Key Features

Chat completion using Google Gemini models on Vertex AI
Streaming support for real-time token-by-token responses
Tool/function calling support
Configurable safety settings for content filtering
Configurable generation parameters (temperature, top_p, and more)
Authenticates using Google Cloud Application Default Credentials (ADCs)

Configuration

Drag the VertexAIGeminiChatGenerator component onto the canvas from the Component Library.
Click on the component to open the configuration panel.
On the General tab:
1. Enter your GCP project ID. You must have an account with a project authorized to use Google Vertex AI endpoints. Find your project ID in the GCP resource manager.
2. Optionally, enter the location. If not set, uses us-central1.
3. Select a model. For available models, see Google documentation.
Go to the Advanced tab to configure generation settings, safety settings, tools, tool configuration, and streaming.

Connections

VertexAIGeminiChatGenerator accepts a list of ChatMessage objects through its messages input and outputs generated responses as replies (a list of ChatMessage instances).

Connect ChatPromptBuilder's prompt output to this component's messages input. Connect the replies output to DeepsetAnswerBuilder through OutputAdapter.

Source Code

To check this component's source code, open gemini.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  VertexAIGeminiChatGenerator:
    type: haystack_integrations.components.generators.google_vertex.chat.gemini.VertexAIGeminiChatGenerator
    init_parameters:
      model: gemini-1.5-flash

Using the Component in a Pipeline

This is an example RAG pipeline with VertexAIGeminiChatGenerator and DeepsetAnswerBuilder connected through OutputAdapter:

components:
  bm25_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.bm25_retriever.OpenSearchBM25Retriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'Standard-Index-English'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return
      fuzziness: 0

  query_embedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
    init_parameters:
      normalize_embeddings: true
      model: intfloat/e5-base-v2

  embedding_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'Standard-Index-English'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return

  document_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: intfloat/simlm-msmarco-reranker
      top_k: 8

  meta_field_grouping_ranker:
    type: haystack.components.rankers.meta_field_grouping_ranker.MetaFieldGroupingRanker
    init_parameters:
      group_by: file_id
      subgroup_by:
      sort_docs_by: split_id

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

  ChatPromptBuilder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      template:
      - _content:
        - text: "You are a helpful assistant answering the user's questions based on the provided documents.\nIf the answer is not in the documents, rely on the web_search tool to find information.\nDo not use your own knowledge.\n"
        _role: system
      - _content:
        - text: "Provided documents:\n{% for document in documents %}\nDocument [{{ loop.index }}] :\n{{ document.content }}\n{% endfor %}\n\nQuestion: {{ query }}\n"
        _role: user
      required_variables:
      variables:
  OutputAdapter:
    type: haystack.components.converters.output_adapter.OutputAdapter
    init_parameters:
      template: '{{ replies[0] }}'
      output_type: List[str]
      custom_filters:
      unsafe: false

  VertexAIGeminiChatGenerator:
    type: haystack_integrations.components.generators.google_vertex.chat.gemini.VertexAIGeminiChatGenerator
    init_parameters:
      model: gemini-1.5-flash
      project_id:
      location:
      generation_config:
      safety_settings:
      tools:
      tool_config:
      streaming_callback:

connections:  # Defines how the components are connected
- sender: bm25_retriever.documents
  receiver: document_joiner.documents
- sender: query_embedder.embedding
  receiver: embedding_retriever.query_embedding
- sender: embedding_retriever.documents
  receiver: document_joiner.documents
- sender: document_joiner.documents
  receiver: ranker.documents
- sender: ranker.documents
  receiver: meta_field_grouping_ranker.documents
- sender: meta_field_grouping_ranker.documents
  receiver: answer_builder.documents
- sender: meta_field_grouping_ranker.documents
  receiver: ChatPromptBuilder.documents
- sender: OutputAdapter.output
  receiver: answer_builder.replies
- sender: ChatPromptBuilder.prompt
  receiver: VertexAIGeminiChatGenerator.messages
- sender: VertexAIGeminiChatGenerator.replies
  receiver: OutputAdapter.replies

inputs:  # Define the inputs for your pipeline
  query:  # These components will receive the query as input
  - "bm25_retriever.query"
  - "query_embedder.text"
  - "ranker.query"
  - "answer_builder.query"
  - "ChatPromptBuilder.query"
  filters:  # These components will receive a potential query filter as input
  - "bm25_retriever.filters"
  - "embedding_retriever.filters"

outputs:  # Defines the output of your pipeline
  documents: "meta_field_grouping_ranker.documents"  # The output of the pipeline is the retrieved documents
  answers: "answer_builder.answers"  # The output of the pipeline is the generated answers

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
`messages`	List[ChatMessage]		A list of `ChatMessage` instances representing the input messages.
`streaming_callback`	Optional[StreamingCallbackT]	None	A callback function that is called when a new token is received from the stream.
`tools`	Optional[List[Tool]]	None	A list of tools for which the model can prepare calls. If set, overrides the `tools` parameter set during initialization.

Outputs

Parameter	Type	Description
`replies`	List[ChatMessage]	A list containing the generated responses as `ChatMessage` instances.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
`model`	str	gemini-1.5-flash	Name of the model to use. For available models, see Google documentation.
`project_id`	Optional[str]	None	ID of the GCP project to use. By default, it is set during Google Cloud authentication.
`location`	Optional[str]	None	The default location to use when making API calls. If not set, uses us-central-1.
`generation_config`	Optional[Union[GenerationConfig, Dict[str, Any]]]	None	Configuration for the generation process. See the GenerationConfig documentation for a list of supported arguments.
`safety_settings`	Optional[Dict[HarmCategory, HarmBlockThreshold]]	None	Safety settings to use when generating content. See the documentation for HarmBlockThreshold and HarmCategory for more details.
`tools`	Optional[List[Tool]]	None	A list of tools for which the model can prepare calls.
`tool_config`	Optional[ToolConfig]	None	The tool config to use. See the documentation for ToolConfig.
`streaming_callback`	Optional[StreamingCallbackT]	None	A callback function that is called when a new token is received from the stream. The callback function accepts StreamingChunk as an argument.

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
`messages`	List[ChatMessage]		A list of `ChatMessage` instances representing the input messages.
`streaming_callback`	Optional[StreamingCallbackT]	None	A callback function that is called when a new token is received from the stream.
`tools`	Optional[List[Tool]]	None	A list of tools for which the model can prepare calls. If set, overrides the `tools` parameter set during initialization.

Was this page helpful?

Key Features​

Configuration​

Connections​

Source Code​

Usage Examples​

Basic Configuration​

Using the Component in a Pipeline​

Parameters​

Inputs​

Outputs​

Init Parameters​

Run Method Parameters​

Related Information​