LlamaStackChatGenerator

Generate text using models available on Llama Stack server.

Key Features

• Connects to a Llama Stack Server that supports multiple inference providers including Ollama, Together AI, vLLM, and other cloud providers.
• Accepts ChatMessage objects as input and returns generated replies as ChatMessage objects.
• Supports streaming responses via a callback function.
• Supports tool calls for agentic workflows.
• Compatible with any text generation parameters valid for the OpenAI chat completion API.

Configuration

Before using this component, set up a Llama Stack Server with an inference provider and make sure a model is available. For a quick start, see the Llama Stack documentation.

1. Drag the LlamaStackChatGenerator component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Set the model parameter to the name of the model available on your Llama Stack Server inference provider.
   • Set api_base_url to your Llama Stack API base URL. The default is http://localhost:8321/v1/openai/v1.
4. Go to the Advanced tab to configure timeout, max_retries, generation_kwargs, and http_client_kwargs.

Connections

LlamaStackChatGenerator accepts a list of ChatMessage objects as input. Connect its messages input to the prompt output of ChatPromptBuilder.

It outputs replies as a list of ChatMessage objects. Connect its replies output through OutputAdapter to DeepsetAnswerBuilder.

Source Code

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

Usage Examples

Basic Configuration

  LlamaStackChatGenerator:
    type: haystack_integrations.components.generators.llama_stack.chat.chat_generator.LlamaStackChatGenerator
    init_parameters:
      model: ollama/llama3.2:3b
      api_base_url: http://localhost:8321/v1/openai/v1

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

components:
  bm25_retriever:
    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
      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:
    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

  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.\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

  LlamaStackChatGenerator:
    type: haystack_integrations.components.generators.llama_stack.chat.chat_generator.LlamaStackChatGenerator
    init_parameters:
      model: ollama/llama3.2:3b
      api_base_url: http://localhost:8321/v1/openai/v1
      streaming_callback:
      generation_kwargs:
      tools:
      timeout:
      max_retries:
      http_client_kwargs:

connections:
- 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: LlamaStackChatGenerator.messages
- sender: LlamaStackChatGenerator.replies
  receiver: OutputAdapter.replies

inputs:
  query:
  - "bm25_retriever.query"
  - "query_embedder.text"
  - "ranker.query"
  - "answer_builder.query"
  - "ChatPromptBuilder.query"
  filters:
  - "bm25_retriever.filters"
  - "embedding_retriever.filters"

outputs:
  documents: "meta_field_grouping_ranker.documents"
  answers: "answer_builder.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 called when the model receives a new token from the stream.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for text generation. These parameters override the parameters in pipeline configuration.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls. If set, it overrides the tools parameter set during component initialization.
tools_strict	Optional[bool]	None	Whether to enable strict schema adherence for tool calls.

Outputs

Parameter	Type	Default	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		The name of the model to use for chat completion. This depends on the inference provider used for the Llama Stack Server.
api_base_url	str	http://localhost:8321/v1/openai/v1	The Llama Stack API base URL. If not specified, localhost is used with the default port 8321.
organization	Optional[str]	None	Your organization ID.
streaming_callback	Optional[StreamingCallbackT]	None	A callback function called when a new token is received from the stream. The callback function accepts StreamingChunk as an argument.
generation_kwargs	Optional[Dict[str, Any]]	None	Other parameters to use for the model. These parameters are sent directly to the Llama Stack endpoint. See the Llama Stack API documentation for more details. Supported parameters include: max_tokens, temperature, top_p, stream, safe_prompt, random_seed, response_format.
timeout	Optional[int]	None	Timeout for client calls. If not set, it defaults to either the OPENAI_TIMEOUT environment variable or 30 seconds.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls. Each tool should have a unique name.
tools_strict	bool	False	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.
max_retries	Optional[int]	None	Maximum number of retries to contact the server after an internal error. If not set, it defaults to either the OPENAI_MAX_RETRIES environment variable or five.
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

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 called when a new token is received from the stream.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for text generation. These parameters override the parameters in pipeline configuration.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls. If set, it overrides the tools parameter set during component initialization.
tools_strict	Optional[bool]	None	Whether to enable strict schema adherence for tool calls.