For ChatGPT-based Typescript SDK assistance, go here.

Getting started

Installing the exa-js SDK

npm install exa-js
pnpm install exa-js

and then instantiate an Exa client

import Exa from 'exa-js';

const exa = new Exa(process.env.EXA_API_KEY);

search Method

Perform an Exa search given an input query and retrieve a list of relevant results as links.

Input Example

const result = await exa.search(
  "hottest AI startups",
  {
    useAutoprompt: true,
    numResults: 2
  }
);

Input Parameters

ParameterTypeDescriptionDefault
querystringThe input query string.Required
numResultsnumberNumber of search results to return.10
includeDomainsstring[]List of domains to include in the search.undefined
excludeDomainsstring[]List of domains to exclude in the search.undefined
startCrawlDatestringResults will only include links crawled after this date.undefined
endCrawlDatestringResults will only include links crawled before this date.undefined
startPublishedDatestringResults will only include links with a published date after this date.undefined
endPublishedDatestringResults will only include links with a published date before this date.undefined
useAutopromptbooleanIf true, convert query to a query best suited for Exa.false
typestringThe type of search, "keyword" or "neural"."auto"
categorystringA data category to focus on when searching, with higher comprehensivity and data cleanliness. Available categories: "company", "research paper", "news", "github", "tweet", "movie", "song", "personal site", "pdf".undefined

Returns Example

{
  "autopromptString": "Here is a link to one of the hottest AI startups:",
  "results": [
    {
      "score": 0.17025552690029144,
      "title": "Adept: Useful General Intelligence",
      "id": "https://www.adept.ai/",
      "url": "https://www.adept.ai/",
      "publishedDate": "2000-01-01",
      "author": null
    },
    {
      "score": 0.1700288951396942,
      "title": "Home | Tenyx, Inc.",
      "id": "https://www.tenyx.com/",
      "url": "https://www.tenyx.com/",
      "publishedDate": "2019-09-10",
      "author": null
    }
  ]
}

Return Parameters

SearchResponse

FieldTypeDescription
resultsResult[]List of Result objects
autopromptString?stringExa query created by autoprompt functionality

Result Object

FieldTypeDescription
urlstringURL of the search result
idstringTemporary ID for the document
title`stringnull`Title of the search result
score?numberSimilarity score between query/url and result
publishedDate?stringEstimated creation date
author?stringAuthor of the content, if available

searchAndContents Method

Perform an Exa search given an input query and retrieve a list of relevant results as links, optionally including the full text and/or highlights of the content.

Input Example

// Search with full text content
const resultWithText = await exa.searchAndContents(
  "AI in healthcare",
  {
    text: true,
    numResults: 2
  }
);

// Search with highlights
const resultWithHighlights = await exa.searchAndContents(
  "AI in healthcare",
  {
    highlights: true,
    numResults: 2
  }
);

// Search with both text and highlights
const resultWithTextAndHighlights = await exa.searchAndContents(
  "AI in healthcare",
  {
    text: true,
    highlights: true,
    numResults: 2
  }
);

Input Parameters

ParameterTypeDescriptionDefault
querystringThe input query string.undefined
textbooleanIf provided, includes the full text of the content in the results.undefined
highlightsbooleanIf provided, includes highlights of the content in the results.undefined
numResultsnumberNumber of search results to return.10
includeDomainsstring[]List of domains to include in the search.undefined
excludeDomainsstring[]List of domains to exclude in the search.undefined
startCrawlDatestringResults will only include links crawled after this date.undefined
endCrawlDatestringResults will only include links crawled before this date.undefined
startPublishedDatestringResults will only include links with a published date after this date.undefined
endPublishedDatestringResults will only include links with a published date before this date.undefined
useAutopromptbooleanIf true, convert query to a query best suited for Exa.false
typestringThe type of search, "keyword" or "neural"."auto"
categorystringA data category to focus on when searching, with higher comprehensivity and data cleanliness. Available categories: "company", "research paper", "news", "github", "tweet", "movie", "song", "personal site", "pdf".undefined

Returns Example

{
  "results": [
    {
      "score": 0.20826785266399384,
      "title": "2023 AI Trends in Health Care",
      "id": "https://aibusiness.com/verticals/2023-ai-trends-in-health-care-",
      "url": "https://aibusiness.com/verticals/2023-ai-trends-in-health-care-",
      "publishedDate": "2022-12-29",
      "author": "Wylie Wong",
      "text": "While the health care industry was initially slow to [... TRUNCATED FOR BREVITY ...]",
      "highlights": [
        "But to do so, many health care institutions would like to share data, so they can build a more comprehensive dataset to use to train an AI model. Traditionally, they would have to move the data to one central repository. However, with federated or swarm learning, the data does not have to move. Instead, the AI model goes to each individual health care facility and trains on the data, he said. This way, health care providers can maintain security and governance over their data."
      ],
      "highlightScores": [
        0.5566554069519043
      ]
    },
    {
      "score": 0.20796334743499756,
      "title": "AI in healthcare: Innovative use cases and applications",
      "id": "https://www.leewayhertz.com/ai-use-cases-in-healthcare",
      "url": "https://www.leewayhertz.com/ai-use-cases-in-healthcare",
      "publishedDate": "2023-02-13",
      "author": "Akash Takyar",
      "text": "The integration of AI in healthcare is not [... TRUNCATED FOR BREVITY ...]",
      "highlights": [
        "The ability of AI to analyze large amounts of medical data and identify patterns has led to more accurate and timely diagnoses. This has been especially helpful in identifying complex medical conditions, which may be difficult to detect using traditional methods. Here are some examples of successful implementation of AI in healthcare. IBM Watson Health: IBM Watson Health is an AI-powered system used in healthcare to improve patient care and outcomes. The system uses natural language processing and machine learning to analyze large amounts of data and provide personalized treatment plans for patients."
      ],
      "highlightScores": [
        0.6563674807548523
      ]
    }
  ]
}

Return Parameters

SearchResponse

FieldTypeDescription
resultsSearchResult<T>[]List of SearchResult objects
autopromptString?stringExa query created by autoprompt functionality

SearchResult

Extends the Result object from the search method with additional fields based on T:

FieldTypeDescription
text?stringText of the search result page (if requested)
highlights?string[]Highlights of the search result (if requested)
highlightScores?number[]Scores of the highlights (if requested)

Note: The actual fields present in the SearchResult<T> object depend on the options provided in the searchAndContents call.

findSimilar Method

Find a list of similar results based on a webpage's URL.

Input Example

const similarResults = await exa.findSimilar(
  "https://www.example.com",
  {
    numResults: 2,
    excludeSourceDomain: true
  }
);

Input Parameters

ParameterTypeDescriptionDefault
urlstringThe URL of the webpage to find similar results for.Required
numResultsnumberNumber of similar results to return.undefined
includeDomainsstring[]List of domains to include in the search.undefined
excludeDomainsstring[]List of domains to exclude from the search.undefined
startCrawlDatestringResults will only include links crawled after this date.undefined
endCrawlDatestringResults will only include links crawled before this date.undefined
startPublishedDatestringResults will only include links with a published date after this date.undefined
endPublishedDatestringResults will only include links with a published date before this date.undefined
excludeSourceDomainbooleanIf true, excludes results from the same domain as the input URL.undefined
categorystringA data category to focus on when searching, with higher comprehensivity and data cleanliness.undefined

Returns Example

{
  "results": [
    {
      "score": 0.8777582049369812,
      "title": "Play New Free Online Games Every Day",
      "id": "https://www.minigames.com/new-games",
      "url": "https://www.minigames.com/new-games",
      "publishedDate": "2000-01-01",
      "author": null
    },
    {
      "score": 0.87653648853302,
      "title": "Play The best Online Games",
      "id": "https://www.minigames.com/",
      "url": "https://www.minigames.com/",
      "publishedDate": "2000-01-01",
      "author": null
    }
  ]
}

Return Parameters

SearchResponse

FieldTypeDescription
resultsResult[]List of Result objects
autopromptString?stringExa query created by autoprompt functionality

Result Object

FieldTypeDescription
urlstringURL of the search result
idstringTemporary ID for the document
titlestringTitle of the search result
score?numberSimilarity score between query/url and result
publishedDate?stringEstimated creation date
author?stringAuthor of the content, if available

findSimilarAndContents Method

Find a list of similar results based on a webpage's URL, optionally including the text content or highlights of each result.

Input Example

// Find similar with full text content
const similarWithText = await exa.findSimilarAndContents(
  "https://www.example.com/article",
  {
    text: true,
    numResults: 2
  }
);

// Find similar with highlights
const similarWithHighlights = await exa.findSimilarAndContents(
  "https://www.example.com/article",
  {
    highlights: true,
    numResults: 2
  }
);

// Find similar with both text and highlights
const similarWithTextAndHighlights = await exa.findSimilarAndContents(
  "https://www.example.com/article",
  {
    text: true,
    highlights: true,
    numResults: 2,
    excludeSourceDomain: true
  }
);

Input Parameters

ParameterTypeDescriptionDefault
urlstringThe URL of the webpage to find similar results for.Required
textbooleanIf provided, includes the full text of the content in the results.undefined
highlightsbooleanIf provided, includes highlights of the content in the results.undefined
numResultsnumberNumber of similar results to return.undefined
includeDomainsstring[]List of domains to include in the search.undefined
excludeDomainsstring[]List of domains to exclude from the search.undefined
startCrawlDatestringResults will only include links crawled after this date.undefined
endCrawlDatestringResults will only include links crawled before this date.undefined
startPublishedDatestringResults will only include links with a published date after this date.undefined
endPublishedDatestringResults will only include links with a published date before this date.undefined
excludeSourceDomainbooleanIf true, excludes results from the same domain as the input URL.undefined
categorystringA data category to focus on when searching, with higher comprehensivity and data cleanliness.undefined

Returns Example

{
  "results": [
    {
      "score": 0.8777582049369812,
      "title": "Similar Article: AI and Machine Learning",
      "id": "https://www.similarsite.com/ai-ml-article",
      "url": "https://www.similarsite.com/ai-ml-article",
      "publishedDate": "2023-05-15",
      "author": "Jane Doe",
      "text": "Artificial Intelligence (AI) and Machine Learning (ML) are revolutionizing various industries. [... TRUNCATED FOR BREVITY ...]",
      "highlights": [
        "AI and ML are transforming how businesses operate, enabling more efficient processes and data-driven decision making.",
        "The future of AI looks promising, with potential applications in healthcare, finance, and autonomous vehicles."
      ],
      "highlightScores": [
        0.95,
        0.89
      ]
    },
    {
      "score": 0.87653648853302,
      "title": "The Impact of AI on Modern Technology",
      "id": "https://www.techblog.com/ai-impact",
      "url": "https://www.techblog.com/ai-impact",
      "publishedDate": "2023-06-01",
      "author": "John Smith",
      "text": "In recent years, artificial intelligence has made significant strides in various technological domains. [... TRUNCATED FOR BREVITY ...]",
      "highlights": [
        "AI is not just a buzzword; it's a transformative technology that's reshaping industries and creating new opportunities.",
        "As AI continues to evolve, ethical considerations and responsible development become increasingly important."
      ],
      "highlightScores": [
        0.92,
        0.88
      ]
    }
  ]
}

Return Parameters

SearchResponse

FieldTypeDescription
resultsSearchResult<T>[]List of SearchResult objects
autopromptString?stringExa query created by autoprompt functionality

SearchResult

Extends the Result object with additional fields based on the requested content:

FieldTypeDescription
urlstringURL of the search result
idstringTemporary ID for the document
title`string`Title of the search result
score?numberSimilarity score between query/url and result
publishedDate?stringEstimated creation date
author?stringAuthor of the content, if available
text?stringText of the search result page (if requested)
highlights?string[]Highlights of the search result (if requested)
highlightScores?number[]Scores of the highlights (if requested)

Note: The actual fields present in the SearchResult<T> object depend on the options provided in the findSimilarAndContents call.

getContents Method

Retrieves contents of documents based on a list of document IDs.

Input Example

// Get contents for a single ID
const singleContent = await exa.getContents("https://www.example.com/article");

// Get contents for multiple IDs
const multipleContents = await exa.getContents([
  "https://www.example.com/article1",
  "https://www.example.com/article2"
]);

// Get contents with specific options
const contentsWithOptions = await exa.getContents(
  ["https://www.example.com/article1", "https://www.example.com/article2"],
  {
    text: { maxCharacters: 1000 },
    highlights: { query: "AI", numSentences: 2 }
  }
);

Input Parameters

ParameterTypeDescriptionDefault
idsstringA single ID, an array of IDs, or an array of SearchResults.Required
textbooleanIf provided, includes the full text of the content in the results.undefined
highlightsbooleanIf provided, includes highlights of the content in the results.undefined

Returns Example

{
  "results": [
    {
      "id": "https://www.example.com/article1",
      "url": "https://www.example.com/article1",
      "title": "The Future of Artificial Intelligence",
      "publishedDate": "2023-06-15",
      "author": "Jane Doe",
      "text": "Artificial Intelligence (AI) has made significant strides in recent years. [... TRUNCATED FOR BREVITY ...]",
      "highlights": [
        "AI is revolutionizing industries from healthcare to finance, enabling more efficient processes and data-driven decision making.",
        "As AI continues to evolve, ethical considerations and responsible development become increasingly important."
      ],
      "highlightScores": [
        0.95,
        0.92
      ]
    },
    {
      "id": "https://www.example.com/article2",
      "url": "https://www.example.com/article2",
      "title": "Machine Learning Applications in Business",
      "publishedDate": "2023-06-20",
      "author": "John Smith",
      "text": "Machine Learning (ML) is transforming how businesses operate and make decisions. [... TRUNCATED FOR BREVITY ...]",
      "highlights": [
        "Machine Learning algorithms can analyze vast amounts of data to identify patterns and make predictions.",
        "Businesses are leveraging ML for customer segmentation, demand forecasting, and fraud detection."
      ],
      "highlightScores": [
        0.93,
        0.90
      ]
    }
  ]
}

Return Parameters

SearchResponse

FieldTypeDescription
resultsSearchResult<T>[]List of SearchResult objects

SearchResult

The fields in the SearchResult<T> object depend on the options provided in the getContents call:

FieldTypeDescription
idstringTemporary ID for the document
urlstringURL of the search result
titlestringTitle of the search result
publishedDate?stringEstimated creation date
author?stringAuthor of the content, if available
text?stringText of the search result page (if requested)
highlights?string[]Highlights of the search result (if requested)
highlightScores?number[]Scores of the highlights (if requested)

Note: The actual fields present in the SearchResult<T> object depend on the options provided in the getContents call. If neither text nor highlights is specified, the method defaults to including the full text content.