ParallelWebSearch

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

Key Features

• Wraps the Parallel Search API and returns LLM-optimized excerpts as structured documents.
• Returns documents with content and URL links, plus a session identifier for linking related searches.
• Supports session continuity: pass the returned session_id to follow-up searches for better contextual results.
• Configurable search modes (turbo, fast, basic, advanced) for different latency and quality trade-offs.
• Supports domain and date filters through search_params.

Configuration

1. Drag the ParallelWebSearch 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 Parallel API key and set it as api_key. Use PARALLEL_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).
4. Go to the Advanced tab to configure search_params and timeout.

Connections

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

Source Code

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

Usage Examples

Basic Configuration

  ParallelWebSearch:
    type: haystack_integrations.components.websearch.parallel.parallel_websearch.ParallelWebSearch
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - PARALLEL_API_KEY
        strict: false
      top_k: 5

Using the Component in a Pipeline

# haystack-pipeline
components:
  websearch:
    type: haystack_integrations.components.websearch.parallel.parallel_websearch.ParallelWebSearch
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - PARALLEL_API_KEY
        strict: false
      top_k: 5

  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 LLM-optimized search result excerpts.
links	List[str]	A list of URLs from the search results.
session_id	str	Session identifier for this search. Pass it to follow-up searches in the same task for better contextual results.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var("PARALLEL_API_KEY")	The Parallel API key.
top_k	Optional[int]	10	Maximum number of results to return. Maps to advanced_settings.max_results in the API.
search_params	Optional[Dict[str, Any]]	None	Additional parameters for the Parallel Search API. Supported keys include objective, mode (turbo, fast, basic, or advanced), max_chars_total, session_id, client_model, and advanced_settings (with nested source policy, date filters, and excerpt settings).
timeout	float	30.0	Request timeout in seconds.

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.
search_params	Optional[Dict[str, Any]]	None	Per-run override of search parameters. If provided, fully replaces the init-time search_params.

Related Information

• ParallelChatGenerator
• Pipeline Components