LinkupWebSearch

Search the web using the Linkup API and return results as Haystack Documents.

Key Features

• Uses the Linkup Search API, which is optimized for LLM applications.
• Supports three search depths: fast (sub-second, beta), standard (simple search), and deep (agentic workflow with higher quality).
• Returns structured documents with content and URL links.
• Supports per-run overrides of top_k, depth, and search parameters.
• Supports domain filtering, date range filtering, and image inclusion through search_params.

Configuration

1. Drag the LinkupWebSearch component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Create a secret with your Linkup API key and set it as api_key. Use LINKUP_API_KEY as the environment variable name. For instructions, see Create Secrets.
   2. Set top_k to control the maximum number of results (default: 10).
   3. Set depth to fast, standard, or deep depending on your latency and quality requirements.
4. Go to the Advanced tab to configure search_params for domain and date filters.

Connections

LinkupWebSearch receives a query string and returns a list of Document objects and a list of URLs. Connect its documents output to downstream components such as PromptBuilder for retrieval-augmented generation.

Source Code

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

Usage Examples

Basic Configuration

  LinkupWebSearch:
    type: haystack_integrations.components.websearch.linkup.linkup_websearch.LinkupWebSearch
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - LINKUP_API_KEY
        strict: false
      top_k: 5
      depth: standard

Using the Component in a Pipeline

# haystack-pipeline
components:
  websearch:
    type: haystack_integrations.components.websearch.linkup.linkup_websearch.LinkupWebSearch
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - LINKUP_API_KEY
        strict: false
      top_k: 5
      depth: standard

  prompt_builder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      required_variables: "*"
      template:
      - role: user
        content: |
          Answer the question using the following search results:
          {% for doc in documents %}
          {{ doc.content }}
          {% endfor %}
          Question: {{ question }}

  llm:
    type: haystack.components.generators.chat.openai.OpenAIChatGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - OPENAI_API_KEY
        strict: false
      model: gpt-4o-mini

connections:
- sender: websearch.documents
  receiver: prompt_builder.documents
- sender: prompt_builder.prompt
  receiver: llm.messages

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - websearch.query
  - prompt_builder.question

outputs:
  replies: llm.replies

Parameters

Inputs

Parameter	Type	Description
query	str	The search query string.

Outputs

Parameter	Type	Description
documents	List[Document]	A list of documents containing search result content.
links	List[str]	A list of URLs from the search results.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var("LINKUP_API_KEY")	The Linkup API key.
top_k	Optional[int]	10	Maximum number of results to return. Maps to the max_results parameter of the Linkup API.
depth	str	standard	Search depth: "fast" (sub-second, beta, keyword-based queries only), "standard" for a simple search, or "deep" for a more powerful agentic workflow.
search_params	Optional[Dict[str, Any]]	None	Additional parameters for the Linkup API. Supported keys include include_images, from_date, to_date, include_domains, and exclude_domains.

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
query	str		The search query string.
top_k	Optional[int]	None	Per-run override of the maximum number of results.
depth	Optional[str]	None	Per-run override of the search depth ("fast", "standard", or "deep").
search_params	Optional[Dict[str, Any]]	None	Per-run override of search parameters. If provided, fully replaces the init-time search_params.

Related Information

• Pipeline Components
• Integrations Overview