AzureOpenAIChatGenerator

Generate text using OpenAI's models on Azure. It works with GPT-4-type models and supports streaming responses.

Key Features

Generates text using OpenAI GPT-4-type models deployed on Azure OpenAI.
Supports streaming responses token by token.
Supports tool calling with Tool objects or a Toolset.
Accepts Azure Active Directory (Entra ID) tokens for authentication in addition to API keys.
Customizable generation behavior through generation_kwargs (temperature, max_tokens, and others).

Configuration

To use this component, connect Haystack Platform with Azure OpenAI first:

Add Workspace-Level Integration

Click your profile icon and choose Settings.
Go to Workspace>Integrations.
Find the provider you want to connect and click Connect next to them.
Enter the API key and any other required details.
Click Connect. You can use this integration in pipelines and indexes in the current workspace.

Add Organization-Level Integration

Click your profile icon and choose Settings.
Go to Organization>Integrations.
Find the provider you want to connect and click Connect next to them.
Enter the API key and any other required details.
Click Connect. You can use this integration in pipelines and indexes in all workspaces in the current organization.

:::

Drag the AzureOpenAIChatGenerator component onto the canvas from the Component Library.
Click the component to open the configuration panel.
Configure the parameters as needed. You can set the API key, endpoint, deployment name, and other parameters directly or through environment variables (AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT).

Connections

AzureOpenAIChatGenerator accepts a list of ChatMessage instances as input, along with optional streaming callback, generation parameters, and tools. It outputs a list of ChatMessage responses.

Typically, you connect a ChatPromptBuilder to the messages input to build dynamic prompts. Connect the replies output to DeepsetAnswerBuilder through an OutputAdapter for further processing.

Drag the AzureOpenAIChatGenerator component onto the canvas from the Component Library.
Click on the component to open the configuration panel.
On the General tab:
- Enter the Azure endpoint and deployment name (model name).
- Enter your API key, or set it using the AZURE_OPENAI_API_KEY environment variable.
- Set generation_kwargs to configure model behavior, such as temperature and max_tokens.
Go to the Advanced tab to configure additional settings, such as timeout, max_retries, organization, streaming_callback, tools, tools_strict, http_client_kwargs, and default_headers.

Source Code

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

Connections

AzureOpenAIChatGenerator receives a list of ChatMessage objects. Connect a ChatPromptBuilder's prompt output to its messages input.

It outputs a list of ChatMessage objects as replies. Connect its replies output to DeepsetAnswerBuilder through OutputAdapter, or use it as the pipeline's final output.

Usage Examples

Basic Configuration

  AzureOpenAIChatGenerator:
    type: haystack.components.generators.chat.azure.AzureOpenAIChatGenerator
    init_parameters:
      api_version: '2023-05-15'
      azure_deployment: gpt-4o-mini
      api_key:
        type: env_var
        env_vars:
        - AZURE_OPENAI_API_KEY
        strict: false
      azure_ad_token:
        type: env_var
        env_vars:
        - AZURE_OPENAI_AD_TOKEN
        strict: false
      tools_strict: false

This is a RAG pipeline where AzureOpenAIChatGenerator sends the generated replies to DeepsetAnswerBuilder 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

  AzureOpenAIChatGenerator:
    type: haystack.components.generators.chat.azure.AzureOpenAIChatGenerator
    init_parameters:
      azure_endpoint:
      api_version: '2023-05-15'
      azure_deployment: gpt-4o-mini
      api_key:
        type: env_var
        env_vars:
        - AZURE_OPENAI_API_KEY
        strict: false
      azure_ad_token:
        type: env_var
        env_vars:
        - AZURE_OPENAI_AD_TOKEN
        strict: false
      organization:
      streaming_callback:
      timeout:
      max_retries:
      generation_kwargs:
      default_headers:
      tools:
      tools_strict: false
      azure_ad_token_provider:
      http_client_kwargs:

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: AzureOpenAIChatGenerator.messages
- sender: AzureOpenAIChatGenerator.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.
`generation_kwargs`	Optional[Dict[str, Any]]	None	Optional arguments to pass to the generation endpoint.
`tools`	Optional[Union[List[Tool], Toolset]]	None	A list of Tool objects or a Toolset that the model can use. Each tool should have a unique name. If set, it will override the `tools` parameter set during component initialization.
`tools_strict`	Optional[Bool]	None	Whether to enable strict schema adherence for tool calls. If set to `True`, the model follows exactly the schema provided in the parameters field of the tool definition, but this may increase latency. If set, it overrides the `tools_strict` parameter set during component initialization.

Outputs

Parameter	Type	Description
`replies`	List[ChatMessage]	The responses from the model.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
`azure_endpoint`	Optional[str]	None	The endpoint of the deployed model, for example `"https://example-resource.azure.openai.com/"`.
`api_version`	Optional[str]	2024-12-01	The version of the API to use. Defaults to 2024-12-01.
`azure_deployment`	Optional[str]	gpt-4.1-mini	The deployment of the model, usually the model name.
`api_key`	Optional[Secret]	Secret.from_env_var('AZURE_OPENAI_API_KEY', strict=False)	The API key to use for authentication.
`azure_ad_token`	Optional[Secret]	Secret.from_env_var('AZURE_OPENAI_AD_TOKEN', strict=False)	Azure Active Directory token.
`organization`	Optional[str]	None	Your organization ID. For help, see Setting up your organization.
`streaming_callback`	Optional[StreamingCallbackT]	None	A callback function called when a new token is received from the stream. It accepts StreamingChunk as an argument.
`timeout`	Optional[float]	None	Timeout for OpenAI client calls. If not set, it defaults to either the `OPENAI_TIMEOUT` environment variable, or 30 seconds.
`max_retries`	Optional[int]	None	Maximum number of retries to contact OpenAI after an internal error. If not set, it defaults to either the `OPENAI_MAX_RETRIES` environment variable, or set to 5.
`generation_kwargs`	Optional[Dict[str, Any]]	None	Other parameters to use for the model. These parameters are sent directly to the OpenAI endpoint. For details, see OpenAI documentation. Some of the supported parameters: `max_tokens` (maximum output tokens), `temperature` (sampling temperature; higher values mean more risk), `top_p` (nucleus sampling probability mass), `n` (completions per prompt), `stop` (stop sequences), `presence_penalty`, `frequency_penalty`, `logit_bias`.
`default_headers`	Optional[Dict[str, str]]	None	Default headers to use for the AzureOpenAI client.
`tools`	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls.
`tools_strict`	bool	False	Whether to enable strict schema adherence for tool calls. If set to `True`, the model will follow exactly the schema provided in the `parameters` field of the tool definition, but this may increase latency.
`azure_ad_token_provider`	Optional[Union[AzureADTokenProvider, AsyncAzureADTokenProvider]]	None	A function that returns an Azure Active Directory token, will be invoked on every request.
`http_client_kwargs`	Optional[Dict[str, Any]]	None	A dictionary of keyword arguments to configure a custom `httpx.Client` or `httpx.AsyncClient`. For more information, see the HTTPX documentation.

Run Method Parameters

This component has no run method parameters.

Was this page helpful?

Key Features​

Configuration​

Add Workspace-Level Integration​

Add Organization-Level Integration​

Connections​

Source Code​

Connections​

Usage Examples​

Basic Configuration​

Parameters​

Inputs​

Outputs​

Init Parameters​

Run Method Parameters​

Related Information​

Key Features

Configuration

Add Workspace-Level Integration

Add Organization-Level Integration

Connections

Source Code

Connections

Usage Examples

Basic Configuration

Parameters

Inputs

Outputs

Init Parameters

Run Method Parameters

Related Information