HuggingFaceAPIChatGenerator

Complete chats using Hugging Face APIs.

Key Features

• Chat completion using Hugging Face APIs: Serverless Inference API (Inference Providers), paid Inference Endpoints, and self-hosted Text Generation Inference (TGI)
• Multimodal support: send both text and images to Vision Language Models (VLMs)
• Streaming support for real-time token-by-token responses
• Tool/function calling support
• Consistent finish_reason behavior regardless of streaming mode

Configuration

1. Drag the HuggingFaceAPIChatGenerator component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Select the API type: serverless_inference_api, inference_endpoints, or text_generation_inference.
   2. Enter the API parameters: for serverless_inference_api, enter the model ID; for inference_endpoints or text_generation_inference, enter the endpoint URL.
   3. Enter your Hugging Face API token. Connect Haystack Platform to your Hugging Face account first. For details, see Use Hugging Face Models.
4. Go to the Advanced tab to configure generation parameters, stop words, tools, and streaming.

Connections

HuggingFaceAPIChatGenerator 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 hugging_face_api.py in the Haystack repository.

Usage Examples

Basic Configuration

  HuggingFaceAPIChatGenerator:
    type: haystack.components.generators.chat.hugging_face_api.HuggingFaceAPIChatGenerator
    init_parameters:
      api_type: serverless_inference_api
      api_params:
        model: HuggingFaceH4/zephyr-7b-beta
      token:
        type: env_var
        env_vars:
        - HF_API_TOKEN
        - HF_TOKEN
        strict: false

Using the Component in a Pipeline

This is an example RAG pipeline with HuggingFaceAPIChatGenerator and DeepsetAnswerBuilder. HuggingFaceAPIChatGenerator is configured to use the serverless inference API:

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

  HuggingFaceAPIChatGenerator:
    type: haystack.components.generators.chat.hugging_face_api.HuggingFaceAPIChatGenerator
    init_parameters:
      api_type: serverless_inference_api
      api_params:
        model: HuggingFaceH4/zephyr-7b-beta
      token:
        type: env_var
        env_vars:
        - HF_API_TOKEN
        - HF_TOKEN
        strict: false
      generation_kwargs:
      stop_words:
      streaming_callback:
      tools:

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: HuggingFaceAPIChatGenerator.messages
- sender: HuggingFaceAPIChatGenerator.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 objects representing the input messages.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for text generation.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls.
streaming_callback	Optional[StreamingCallbackT]	None	An optional callable for handling streaming responses.

Outputs

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

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_type	Union[HFGenerationAPIType, str]		The type of Hugging Face API to use. Available types: text_generation_inference (see TGI), inference_endpoints (see Inference Endpoints), serverless_inference_api (see Serverless Inference API).
api_params	Dict[str, str]		A dictionary with: model (Hugging Face model ID, required for SERVERLESS_INFERENCE_API), provider (recommended for SERVERLESS_INFERENCE_API), url (required for INFERENCE_ENDPOINTS or TEXT_GENERATION_INFERENCE), and other parameters specific to the chosen API type.
token	Optional[Secret]	Secret.from_env_var(['HF_API_TOKEN', 'HF_TOKEN'], strict=False)	The Hugging Face token to use as HTTP bearer authorization. Check your HF token in your account settings.
generation_kwargs	Optional[Dict[str, Any]]	None	A dictionary with keyword arguments to customize text generation. Some examples: max_tokens, temperature, top_p. For details, see Hugging Face chat_completion documentation.
stop_words	Optional[List[str]]	None	An optional list of strings representing the stop words.
streaming_callback	Optional[StreamingCallbackT]	None	An optional callable for handling streaming responses.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls.

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 objects representing the input messages.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for text generation.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls.
streaming_callback	Optional[StreamingCallbackT]	None	An optional callable for handling streaming responses.

Related Information

• Use Hugging Face Models
• Add Integrations