POST
/
search
curl -X POST 'https://api.exa.ai/search' \
  -H 'Authorization: Bearer YOUR-EXA-API-KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "Latest research in LLMs",
    "text": true
  }'
{
  "requestId": "b5947044c4b78efa9552a7c89b306d95",
  "autopromptString": "Heres a link to the latest research in LLMs:",
  "autoDate": "2024-02-08T02:15:42.180Z",
  "resolvedSearchType": "neural",
  "results": [
    {
      "title": "A Comprehensive Overview of Large Language Models",
      "url": "https://arxiv.org/pdf/2307.06435.pdf",
      "publishedDate": "2023-11-16T01:36:32.547Z",
      "author": "Humza  Naveed, University of Engineering and Technology (UET), Lahore, Pakistan",
      "score": 0.4600165784358978,
      "id": "https://arxiv.org/abs/2307.06435",
      "image": "https://arxiv.org/pdf/2307.06435.pdf/page_1.png",
      "favicon": "https://arxiv.org/favicon.ico",
      "text": "Abstract Large Language Models (LLMs) have recently demonstrated remarkable capabilities...",
      "highlights": [
        "Such requirements have limited their adoption..."
      ],
      "highlightScores": [
        0.4600165784358978
      ],
      "summary": "This overview paper on Large Language Models (LLMs) highlights key developments...",
      "subpages": [
        {
          "id": "https://arxiv.org/abs/2303.17580",
          "url": "https://arxiv.org/pdf/2303.17580.pdf",
          "title": "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face",
          "author": "Yongliang  Shen, Microsoft Research Asia, Kaitao  Song, Microsoft Research Asia, Xu  Tan, Microsoft Research Asia, Dongsheng  Li, Microsoft Research Asia, Weiming  Lu, Microsoft Research Asia, Yueting  Zhuang, Microsoft Research Asia, [email protected], Zhejiang  University, Microsoft Research Asia, Microsoft  Research, Microsoft Research Asia",
          "publishedDate": "2023-11-16T01:36:20.486Z",
          "text": "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face Date Published: 2023-05-25 Authors: Yongliang Shen, Microsoft Research Asia Kaitao Song, Microsoft Research Asia Xu Tan, Microsoft Research Asia Dongsheng Li, Microsoft Research Asia Weiming Lu, Microsoft Research Asia Yueting Zhuang, Microsoft Research Asia, [email protected] Zhejiang University, Microsoft Research Asia Microsoft Research, Microsoft Research Asia Abstract Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are abundant AI models available for different domains and modalities, they cannot handle complicated AI tasks. Considering large language models (LLMs) have exhibited exceptional ability in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks and language could be a generic interface to empower t",
          "summary": "HuggingGPT is a framework using ChatGPT as a central controller to orchestrate various AI models from Hugging Face to solve complex tasks. ChatGPT plans the task, selects appropriate models based on their descriptions, executes subtasks, and summarizes the results. This approach addresses limitations of LLMs by allowing them to handle multimodal data (vision, speech) and coordinate multiple models for complex tasks, paving the way for more advanced AI systems.",
          "highlights": [
            "2) Recently, some researchers started to investigate the integration of using tools or models in LLMs  ."
          ],
          "highlightScores": [
            0.32679107785224915
          ]
        }
      ],
      "extras": {
        "links": []
      }
    }
  ],
  "searchType": "auto",
  "costDollars": {
    "total": 0.005,
    "breakDown": [
      {
        "search": 0.005,
        "contents": 0,
        "breakdown": {
          "keywordSearch": 0,
          "neuralSearch": 0.005,
          "contentText": 0,
          "contentHighlight": 0,
          "contentSummary": 0
        }
      }
    ],
    "perRequestPrices": {
      "neuralSearch_1_25_results": 0.005,
      "neuralSearch_26_100_results": 0.025,
      "neuralSearch_100_plus_results": 1,
      "keywordSearch_1_100_results": 0.0025,
      "keywordSearch_100_plus_results": 3
    },
    "perPagePrices": {
      "contentText": 0.001,
      "contentHighlight": 0.001,
      "contentSummary": 0.001
    }
  }
}

Get your Exa API key

Authorizations

Authorization
string
header
required

API key can be provided either via x-api-key header or Authorization header with Bearer scheme

Body

application/json
query
string
required

The query string for the search.

Example:

"Latest developments in LLM capabilities"

useAutoprompt
boolean
default:true

Autoprompt converts your query to an Exa-style query. Enabled by default for auto search, optional for neural search, and not available for keyword search.

Example:

true

type
enum<string>
default:auto

The type of search. Neural uses an embeddings-based model, keyword is google-like SERP. Default is auto, which automatically decides between keyword and neural.

Available options:
keyword,
neural,
auto
Example:

"auto"

category
enum<string>

A data category to focus on.

Available options:
company,
research paper,
news,
pdf,
github,
tweet,
personal site,
linkedin profile,
financial report
Example:

"research paper"

numResults
integer
default:10

Number of results to return (up to thousands of results available for custom plans)

Required range: x <= 100
Example:

10

includeDomains
string[]

List of domains to include in the search. If specified, results will only come from these domains.

Example:
["arxiv.org", "paperswithcode.com"]
excludeDomains
string[]

List of domains to exclude from search results. If specified, no results will be returned from these domains.

startCrawlDate
string

Crawl date refers to the date that Exa discovered a link. Results will include links that were crawled after this date. Must be specified in ISO 8601 format.

Example:

"2023-01-01T00:00:00.000Z"

endCrawlDate
string

Crawl date refers to the date that Exa discovered a link. Results will include links that were crawled before this date. Must be specified in ISO 8601 format.

Example:

"2023-12-31T00:00:00.000Z"

startPublishedDate
string

Only links with a published date after this will be returned. Must be specified in ISO 8601 format.

Example:

"2023-01-01T00:00:00.000Z"

endPublishedDate
string

Only links with a published date before this will be returned. Must be specified in ISO 8601 format.

Example:

"2023-12-31T00:00:00.000Z"

includeText
string[]

List of strings that must be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.

Example:
["large language model"]
excludeText
string[]

List of strings that must not be present in webpage text of results. Currently, only 1 string is supported, of up to 5 words.

Example:
["course"]
contents
object

Response

200 - application/json
OK
requestId
string

Unique identifier for the request

Example:

"b5947044c4b78efa9552a7c89b306d95"

autopromptString
string

The prompt generated by autoprompt for your query

Example:

"Heres a link to the latest research in LLMs:"

autoDate
string

Timestamp of when autoprompt was generated

Example:

"2024-02-08T02:15:42.180Z"

resolvedSearchType
enum<string>

The search type that was actually used for this request

Available options:
neural,
keyword
Example:

"neural"

results
object[]

A list of search results containing title, URL, published date, author, and score.

searchType
enum<string>

For auto searches, indicates which search type was selected.

Available options:
neural,
keyword
Example:

"auto"

costDollars
object