Input

The Input component is the entry point of every pipeline. It declares which named inputs the pipeline accepts, such as a user query, metadata filters, uploaded files, or chat messages. It then routes each input to the correct component sockets inside the pipeline.

Every pipeline must have at least one input.

Key Features

• Defines the external interface of the pipeline (what callers must provide).
• Supports standard input types: text queries, metadata filters, files, and chat messages.
• Accepts custom-named inputs that map to any compatible component socket.
• In Pipeline Builder, each output slot on the Input card connects to the downstream components that should receive it.

Configuration

1. Drag the Input component onto the canvas from the Input & Output group in the Component Library.
2. Click the component card to add input types the pipeline needs.
3. Connect each output slot to the component socket that should receive it.

Possible Inputs

You can use any of the following standard keys or define your own custom keys:

Input Key	Type	Description
query	str	The user's search query or question. Route it to any component that accepts a string input, such as a retriever or text embedder.
filters	Optional[Dict[str, Any]]	Metadata filters for document retrieval. Route it to the filters input of a retriever.
files	List[ByteStream]	Files uploaded at query time. Route it to a file converter or DeepsetFileUploader.
messages	List[ChatMessage]	Chat history for conversational pipelines. Route it to a ChatPromptBuilder or directly to an LLM.
streaming_callback	Optional[Callable]	A callback function invoked for each streaming token. Route it to the streaming_callback input of an LLM or generator. Set it to deepset_cloud_custom_nodes.callbacks.streaming.streaming_callback to enable streaming in Playground.
custom	Any	Any name that matches the input socket type of the receiving component. Useful for passing domain-specific parameters at query time.

Usage Examples

In a RAG Pipeline

In a RAG pipeline, you typically need query and filters inputs. On the Input component card, add:

- query
- filters

and then connect each input to the component that should receive it.

Here is an example of a RAG pipeline:

# haystack-pipeline
# If you need help with the YAML format, have a look at https://docs.cloud.deepset.ai/docs/create-a-pipeline-in-studio .
# This section defines components that you want to use in your pipelines. Each component must have a name and a type. You can also set the component's parameters here.
# The name is up to you, you can give your component a friendly name. You then use components' names when specifying the connections in the pipeline.
# Type is the class path of the component. You can check the type on the component's documentation page.
components:
  retriever:
    # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.open_search_hybrid_retriever.OpenSearchHybridRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          embedding_dim: 768
          hosts:
          index: ""
          max_chunk_bytes: 104857600
          return_embedding: false
          method:
          mappings:
          settings:
            index.knn: true
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return
      fuzziness: 0
      embedder:
        type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
        init_parameters:
          normalize_embeddings: true
          model: intfloat/e5-base-v2

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: tomaarsen/Qwen3-Reranker-0.6B-seq-cls
      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

  llm:
    type: haystack.components.generators.chat.llm.LLM
    init_parameters:
      # You can swap this for any other model. Switch to the Builder view and choose another model from the list on the component card.
      chat_generator:
        type: haystack.components.generators.chat.openai.OpenAIChatGenerator
        init_parameters:
          model: "gpt-5.4"
          generation_kwargs:
            max_completion_tokens: 650
            temperature: 0.0
      user_prompt: |-
        {% message role="user" %}
        You are a technical expert.
        You answer questions truthfully based on provided documents.
        Ignore typing errors in the question.
        For each document check whether it is related to the question.
        Only use documents that are related to the question to answer it.
        Ignore documents that are not related to the question.
        If the answer exists in several documents, summarize them.
        Only answer based on the documents provided. Don't make things up.
        Just output the structured, informative and precise answer and nothing else.
        If the documents can't answer the question, say so.
        Always use references in the form [NUMBER OF DOCUMENT] when using information from a document, e.g. [3] for Document [3] .
        Never name the documents, only enter a number in square brackets as a reference.
        The reference must only refer to the number that comes in square brackets after the document.
        Otherwise, do not use brackets in your answer and reference ONLY the number of the document without mentioning the word document.

        These are the documents:
        {%- if documents|length > 0 %}
        {%- for document in documents %}
        Document [{{ loop.index }}] :
        Name of Source File: {{ document.meta.file_name }}
        {{ document.content }}
        {% endfor -%}
        {%- else %}
        No relevant documents found.
        Respond with "Sorry, no matching documents were found, please adjust the filters or try a different question."
        {% endif %}

        Question: {{ question }}
        Answer:
        {% endmessage %}
      required_variables: "*"

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

connections:
- sender: retriever.documents
  receiver: ranker.documents
- sender: ranker.documents
  receiver: meta_field_grouping_ranker.documents
- sender: llm.last_message
  receiver: answer_builder.replies
- sender: meta_field_grouping_ranker.documents
  receiver: llm.documents

inputs:
  query:
  - retriever.query
  - ranker.query
  - llm.question
  - answer_builder.query
  filters:
  - retriever.filters_bm25
  - retriever.filters_embedding
  files: []

outputs:
  answers: answer_builder.answers
  messages: llm.messages

max_runs_per_component: 100

metadata: {}

File Upload Pipeline

If you want a pipeline where users upload files at query time, add files to the Input component card and connect it to the component that should receive it. Make sure you add a Converter that can preprocess the uploaded files so that the query pipeline can use them.Here is an example:

components:
  retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.open_search_hybrid_retriever.OpenSearchHybridRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          embedding_dim: 768
      top_k: 20 # The number of results to return
      fuzziness: 0
      embedder:
        type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
        init_parameters:
          normalize_embeddings: true
          model: intfloat/e5-base-v2

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: tomaarsen/Qwen3-Reranker-0.6B-seq-cls
      top_k: 8

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

  llm:
    type: haystack.components.generators.chat.llm.LLM
    init_parameters:
      # You can swap this for any other model. Switch to the Builder view and choose another model from the list on the component card.
      chat_generator:
        type: haystack.components.generators.chat.openai.OpenAIChatGenerator
        init_parameters:
          model: "gpt-5.4"
          generation_kwargs:
            max_completion_tokens: 650
            temperature: 0.0
      user_prompt: |-
        {% message role="user" %}
        You are a technical expert.
        You answer questions truthfully based on provided documents.
        Ignore typing errors in the question.
        For each document check whether it is related to the question.
        Only use documents that are related to the question to answer it.
        Ignore documents that are not related to the question.
        If the answer exists in several documents, summarize them.
        Only answer based on the documents provided. Don't make things up.
        Just output the structured, informative and precise answer and nothing else.
        If the documents can't answer the question, say so.
        Always use references in the form [NUMBER OF DOCUMENT] when using information from a document, e.g. [3] for Document [3] .
        Never name the documents, only enter a number in square brackets as a reference.
        The reference must only refer to the number that comes in square brackets after the document.
        Otherwise, do not use brackets in your answer and reference ONLY the number of the document without mentioning the word document.

        These are the documents:
        {%- if documents|length > 0 %}
        {%- for document in documents %}
        Document [{{ loop.index }}] :
        Name of Source File: {{ document.meta.file_name }}
        {{ document.content }}
        {% endfor -%}
        {%- else %}
        No relevant documents found.
        Respond with "Sorry, no matching documents were found, please adjust the filters or try a different question."
        {% endif %}

        Question: {{ question }}
        Answer:
        {% endmessage %}
      required_variables: "*"



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

  attachments_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      weights:
      top_k:
      sort_by_score: true

  multi_file_converter:
    type: haystack.core.super_component.super_component.SuperComponent
    init_parameters:
      input_mapping:
        sources:
        - file_classifier.sources
      is_pipeline_async: false
      output_mapping:
        score_adder.output: documents
      pipeline:
        components:
          file_classifier:
            type: haystack.components.routers.file_type_router.FileTypeRouter
            init_parameters:
              mime_types:
              - text/plain
              - application/pdf
              - text/markdown
              - text/html
              - application/vnd.openxmlformats-officedocument.wordprocessingml.document
              - application/vnd.openxmlformats-officedocument.presentationml.presentation
              - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
              - text/csv

          text_converter:
            type: haystack.components.converters.txt.TextFileToDocument
            init_parameters:
              encoding: utf-8

          pdf_converter:
            type: haystack.components.converters.pdfminer.PDFMinerToDocument
            init_parameters:
              line_overlap: 0.5
              char_margin: 2
              line_margin: 0.5
              word_margin: 0.1
              boxes_flow: 0.5
              detect_vertical: true
              all_texts: false
              store_full_path: false

          markdown_converter:
            type: haystack.components.converters.txt.TextFileToDocument
            init_parameters:
              encoding: utf-8

          html_converter:
            type: haystack.components.converters.html.HTMLToDocument
            init_parameters:
              extraction_kwargs:
                output_format: markdown
                target_language:
                include_tables: true
                include_links: true

          docx_converter:
            type: haystack.components.converters.docx.DOCXToDocument
            init_parameters:
              link_format: markdown

          pptx_converter:
            type: haystack.components.converters.pptx.PPTXToDocument
            init_parameters: {}

          xlsx_converter:
            type: haystack.components.converters.xlsx.XLSXToDocument
            init_parameters: {}

          csv_converter:
            type: haystack.components.converters.csv.CSVToDocument
            init_parameters:
              encoding: utf-8

          splitter:
            type: haystack.components.preprocessors.document_splitter.DocumentSplitter
            init_parameters:
              split_by: word
              split_length: 250
              split_overlap: 30
              respect_sentence_boundary: true
              language: en

          score_adder:
            type: haystack.components.converters.output_adapter.OutputAdapter
            init_parameters:
              template: |
                {%- set scored_documents = [] -%}
                {%- for document in documents -%}
                  {%- set doc_dict = document.to_dict() -%}
                  {%- set _ = doc_dict.update({'score': 100.0}) -%}
                  {%- set scored_doc = document.from_dict(doc_dict) -%}
                  {%- set _ = scored_documents.append(scored_doc) -%}
                {%- endfor -%}
                {{ scored_documents }}
              output_type: List[haystack.Document]
              custom_filters:
              unsafe: true

          tabular_joiner:
            type: haystack.components.joiners.document_joiner.DocumentJoiner
            init_parameters:
              join_mode: concatenate
              sort_by_score: false
        connections:
        - sender: file_classifier.text/plain
          receiver: text_converter.sources
        - sender: file_classifier.application/pdf
          receiver: pdf_converter.sources
        - sender: file_classifier.text/markdown
          receiver: markdown_converter.sources
        - sender: file_classifier.text/html
          receiver: html_converter.sources
        - sender: file_classifier.application/vnd.openxmlformats-officedocument.wordprocessingml.document
          receiver: docx_converter.sources
        - sender: file_classifier.application/vnd.openxmlformats-officedocument.presentationml.presentation
          receiver: pptx_converter.sources
        - sender: file_classifier.application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
          receiver: xlsx_converter.sources
        - sender: file_classifier.text/csv
          receiver: csv_converter.sources
        - sender: text_converter.documents
          receiver: splitter.documents
        - sender: pdf_converter.documents
          receiver: splitter.documents
        - sender: markdown_converter.documents
          receiver: splitter.documents
        - sender: html_converter.documents
          receiver: splitter.documents
        - sender: pptx_converter.documents
          receiver: splitter.documents
        - sender: docx_converter.documents
          receiver: splitter.documents
        - sender: xlsx_converter.documents
          receiver: tabular_joiner.documents
        - sender: csv_converter.documents
          receiver: tabular_joiner.documents
        - sender: splitter.documents
          receiver: tabular_joiner.documents
        - sender: tabular_joiner.documents
          receiver: score_adder.documents

connections:
- sender: retriever.documents
  receiver: ranker.documents
- sender: ranker.documents
  receiver: meta_field_grouping_ranker.documents
- sender: llm.last_message
  receiver: answer_builder.replies

- sender: multi_file_converter.documents
  receiver: attachments_joiner.documents
- sender: meta_field_grouping_ranker.documents
  receiver: attachments_joiner.documents
- sender: attachments_joiner.documents
  receiver: answer_builder.documents
- sender: attachments_joiner.documents
  receiver: llm.documents

inputs:
  query:
  - "retriever.query"
  - "ranker.query"
  - "llm.question"
  - "answer_builder.query"

  filters:
  - "retriever.filters_bm25"
  - "retriever.filters_embedding"

  files:
  - multi_file_converter.sources

outputs:
  documents: "attachments_joiner.documents"
  answers: "answer_builder.answers"
  messages: llm.messages