# Exa Search

Blocks for searching the web using Exa's advanced neural and keyword search API.

## Exa Search

### What it is

Searches the web using Exa's advanced search API

### How it works

This block uses Exa's advanced search API to find web content. Unlike traditional search engines, Exa offers neural search that understands semantic meaning, making it excellent for finding specific types of content. You can choose between keyword search (traditional), neural search (semantic understanding), or fast search.

The block supports powerful filtering by domain, date ranges, content categories (companies, research papers, news, etc.), and text patterns. Results include URLs, titles, and optionally full content extraction.

### Inputs

| Input                  | Description                                                                                                                     | Type                                                                                                                                   | Required |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | -------- |
| query                  | The search query                                                                                                                | str                                                                                                                                    | Yes      |
| type                   | Type of search                                                                                                                  | "keyword" \| "neural" \| "fast" \| "auto"                                                                                              | No       |
| category               | Category to search within: company, research paper, news, pdf, github, tweet, personal site, linkedin profile, financial report | "company" \| "research paper" \| "news" \| "pdf" \| "github" \| "tweet" \| "personal site" \| "linkedin profile" \| "financial report" | No       |
| user\_location         | The two-letter ISO country code of the user (e.g., 'US')                                                                        | str                                                                                                                                    | No       |
| number\_of\_results    | Number of results to return                                                                                                     | int                                                                                                                                    | No       |
| include\_domains       | Domains to include in search                                                                                                    | List\[str]                                                                                                                             | No       |
| exclude\_domains       | Domains to exclude from search                                                                                                  | List\[str]                                                                                                                             | No       |
| start\_crawl\_date     | Start date for crawled content                                                                                                  | str (date-time)                                                                                                                        | No       |
| end\_crawl\_date       | End date for crawled content                                                                                                    | str (date-time)                                                                                                                        | No       |
| start\_published\_date | Start date for published content                                                                                                | str (date-time)                                                                                                                        | No       |
| end\_published\_date   | End date for published content                                                                                                  | str (date-time)                                                                                                                        | No       |
| include\_text          | Text patterns to include                                                                                                        | List\[str]                                                                                                                             | No       |
| exclude\_text          | Text patterns to exclude                                                                                                        | List\[str]                                                                                                                             | No       |
| contents               | Content retrieval settings                                                                                                      | ContentSettings                                                                                                                        | No       |
| moderation             | Enable content moderation to filter unsafe content from search results                                                          | bool                                                                                                                                   | No       |

### Outputs

| Output                 | Description                                                                 | Type                    |
| ---------------------- | --------------------------------------------------------------------------- | ----------------------- |
| error                  | Error message if the request failed                                         | str                     |
| results                | List of search results                                                      | List\[ExaSearchResults] |
| result                 | Single search result                                                        | ExaSearchResults        |
| context                | A formatted string of the search results ready for LLMs.                    | str                     |
| search\_type           | For auto searches, indicates which search type was selected.                | str                     |
| resolved\_search\_type | The search type that was actually used for this request (neural or keyword) | str                     |
| cost\_dollars          | Cost breakdown for the request                                              | CostDollars             |

### Possible use case

**Competitive Research**: Search for companies in a specific industry, filtered by recent news or funding announcements.

**Content Curation**: Find relevant articles and research papers on specific topics for newsletters or content aggregation.

**Lead Generation**: Search for companies matching specific criteria (industry, size, recent activity) for sales prospecting.

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://agpt.co/docs/integrations/block-integrations/search.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.