NvidiaChatGenerator

Generates text using generative models hosted on NVIDIA's cloud or self-hosted with NVIDIA NIM.

Key Features

Generates text using NVIDIA generative models, including self-hosted NVIDIA NIM models and NVIDIA API Catalog models.
Supports streaming responses for real-time token delivery.
Accepts tool definitions for function-calling workflows.
Configurable generation parameters through generation_kwargs, including temperature, max_tokens, and top_p.
Compatible with ChatPromptBuilder for structured prompt construction.

Configuration

Authentication

Connect Haystack Platform to your NVIDIA account on the Integrations page. For detailed instructions, see Use NVIDIA Models.

Drag the NvidiaChatGenerator component onto the canvas from the Component Library.
Click the component to open the configuration panel.
On the General tab:
1. Enter the name of the NVIDIA model to use, such as meta/llama-3.1-8b-instruct. For supported models, see NVIDIA Docs.
Go to the Advanced tab to configure the API key, API URL, timeout, generation parameters, and streaming callback.

Connections

NvidiaChatGenerator accepts a list of messages (ChatMessage objects) and optional generation_kwargs, tools, streaming_callback, and tools_strict as inputs. It outputs a list of replies (ChatMessage objects).

Connect ChatPromptBuilder to its messages input. Connect its replies output to OutputAdapter or DeepsetAnswerBuilder for further processing.

Usage Example

This is an example RAG pipeline with NvidiaChatGenerator and DeepsetAnswerBuilder:

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

  NvidiaChatGenerator:
    type: haystack_integrations.components.generators.nvidia.chat.chat_generator.NvidiaChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - NVIDIA_API_KEY
        strict: false
      model: meta/llama-3.1-8b-instruct
      api_base_url:
      generation_kwargs:
      streaming_callback:
      tools:
      timeout:
      max_retries:
      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: NvidiaChatGenerator.messages
- sender: NvidiaChatGenerator.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	A dictionary containing keyword arguments to customize text generation. For more information on the arguments you can use, see NVIDIA API docs.
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 in pipeline configuration.
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.
tools_strict	Optional[bool]	None	Whether to strictly enforce the tools provided in the `tools` parameter. If set to `True`, the model will only use the tools provided in the `tools` parameter. If set to `False`, the model can use other tools that are not provided in the `tools` parameter.

Outputs

Parameter	Type	Default	Description
replies	List[ChatMessage]		A list of `ChatMessage` objects representing the generated responses.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var('NVIDIA_API_KEY')	The NVIDIA API key.
model	str	meta/llama-3.1-8b-instruct	The name of the NVIDIA chat completion model to use.
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.
api_base_url	Optional[str]	os.getenv('NVIDIA_API_URL', DEFAULT_API_URL)	The NVIDIA API Base url.
generation_kwargs	Optional[Dict[str, Any]]	None	Other parameters to use for the model. These parameters are all sent directly to the NVIDIA API endpoint. See NVIDIA API docs for more details. Some of the supported parameters: - `max_tokens`: The maximum number of tokens the output text can have. - `temperature`: What sampling temperature to use. Higher values mean the model will take more risks. Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer. - `top_p`: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. - `stream`: Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools or a Toolset for which the model can prepare calls. This parameter can accept either a list of `Tool` objects or a `Toolset` instance.
timeout	Optional[float]	None	The timeout for the NVIDIA API call.
max_retries	Optional[int]	None	Maximum number of retries to contact NVIDIA after an internal error. If not set, it defaults to either the `NVIDIA_MAX_RETRIES` environment variable, or set to 5.
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` objects representing the input messages.
generation_kwargs	Optional[Dict[str, Any]]	None	A dictionary containing keyword arguments to customize text generation. For more information on the arguments you can use, see NVIDIA API docs.
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 in pipeline configuration.
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.
tools_strict	Optional[bool]	None	Whether to strictly enforce the tools provided in the `tools` parameter. If set to `True`, the model will only use the tools provided in the `tools` parameter. If set to `False`, the model can use other tools that are not provided in the `tools` parameter.

Was this page helpful?

Key Features​

Configuration​

Connections​

Usage Example​

Parameters​

Inputs​

Outputs​

Init Parameters​

Run Method Parameters​