# Parallel AI (/integrations/parallel_ai)



{/* MANUAL-CONTENT-START:intro */}

Use [Parallel AI](https://parallel.ai/) to search the web, extract content from URLs, or start a deep-research task. Search accepts an objective and query controls, while extraction accepts the target URLs. Set the available result and content limits to keep downstream inputs bounded, and connect a Parallel API key.

{/* MANUAL-CONTENT-END */}

## Use the block [#usage-instructions]

Search the web, extract information from URLs, and conduct deep research.

## Actions [#actions]

### Parallel AI Search [#parallel-ai-search]

Search the web with Parallel AI and return matching pages with content excerpts.

#### Input [#input]

| Parameter | Type | Required | Description |
| - | - | - | - |
| `search_queries` | string | Yes | Comma-separated list of concise keyword search queries (3-6 words each). At least one is required |
| `objective` | string | No | Natural-language description of the search intent used to rank and excerpt results |
| `mode` | string | No | Search mode: turbo, fast, basic, or advanced (default: advanced) |
| `max_results` | number | No | Maximum number of results to return (default: 10, max: 20) |
| `max_chars_per_result` | number | No | Maximum characters of excerpts per result |
| `include_domains` | string | No | Comma-separated list of domains to restrict search results to |
| `exclude_domains` | string | No | Comma-separated list of domains to exclude from search results |
| `apiKey` | string | Yes | Parallel AI API Key |

#### Output [#output]

| Parameter | Type | Description |
| - | - | - |
| `search_id` | string | Unique identifier for this search request |
| `results` | array | Search results with excerpts from relevant pages |
| ↳ `url` | string | The URL of the search result |
| ↳ `title` | string | The title of the search result |
| ↳ `publish_date` | string | Publication date of the page (YYYY-MM-DD) |
| ↳ `excerpts` | array | LLM-optimized excerpts from the page |

### Parallel AI Extract [#parallel-ai-extract]

Extract targeted information from specific URLs using Parallel AI. Processes provided URLs to pull relevant content based on your objective.

#### Input [#input-1]

| Parameter | Type | Required | Description |
| - | - | - | - |
| `urls` | string | Yes | Comma-separated list of URLs to extract information from (up to 20) |
| `objective` | string | No | What information to extract from the provided URLs (up to 5,000 characters) |
| `full_content` | boolean | No | Include full page content as markdown in addition to excerpts (default: false) |
| `apiKey` | string | Yes | Parallel AI API Key |

#### Output [#output-1]

| Parameter | Type | Description |
| - | - | - |
| `extract_id` | string | Unique identifier for this extraction request |
| `results` | array | Extracted information from the provided URLs |
| ↳ `url` | string | The source URL |
| ↳ `title` | string | The title of the page |
| ↳ `publish_date` | string | Publication date (YYYY-MM-DD) |
| ↳ `excerpts` | array | Relevant text excerpts in markdown |
| ↳ `full_content` | string | Full page content as markdown (only when requested) |
| `errors` | array | URLs that could not be extracted, with the reason |
| ↳ `url` | string | The URL that failed |
| ↳ `error_type` | string | Category of the failure |
| ↳ `http_status_code` | number | HTTP status returned by the page, if any |
| ↳ `content` | string | Error detail |

### Parallel AI Deep Research [#parallel-ai-deep-research]

Research the web with Parallel AI and synthesize findings from multiple sources with citations. Can take up to 45 minutes to complete.

#### Input [#input-2]

| Parameter | Type | Required | Description |
| - | - | - | - |
| `input` | string | Yes | Research query or question (up to 15,000 characters) |
| `output_format` | string | No | Output format: text for a markdown report with inline citations, auto for a structured JSON object that needs the pro tier or higher (default: text) |
| `processor` | string | No | Processing tier: core, core2x, pro, ultra, ultra2x, ultra4x, ultra8x, or a -fast variant (default: pro) |
| `include_domains` | string | No | Comma-separated list of domains to restrict research to (source policy) |
| `exclude_domains` | string | No | Comma-separated list of domains to exclude from research (source policy) |
| `apiKey` | string | Yes | Parallel AI API Key |

#### Output [#output-2]

| Parameter | Type | Description |
| - | - | - |
| `status` | string | Task status (completed, failed, running) |
| `run_id` | string | Unique ID for this research task |
| `message` | string | Status message |
| `content` | json | Research findings: a markdown report string for the text output format, or a structured object with query-specific keys for the auto format |
| `basis` | array | Citations and sources with reasoning and confidence levels |
| ↳ `field` | string | Output field dot-notation path |
| ↳ `reasoning` | string | Explanation for the result |
| ↳ `citations` | array | Array of sources |
| ↳ `url` | string | Source URL |
| ↳ `title` | string | Source title |
| ↳ `excerpts` | array | Relevant excerpts from the source |
| ↳ `confidence` | string | Confidence level (low, medium, high) |