Felo API PlatformFelo API Platform
v0.1.0-beta
OpenAPI 3.1.0

Run a neural semantic web search.

伺服器:https://openapi.felo.ai
用戶端程式庫

Exa

​

Semantic search, page content, cited answers and asynchronous research.

Run a neural semantic web search.

​

Search the web by meaning rather than by keyword. query is required; narrow with category, includeDomains, excludeDomains, startPublishedDate, endPublishedDate, and set numResults. Returns requestId, resolvedSearchType, searchTime, costDollars and results[] with id, title and url. id is the URL, and it is what post_exa_contents takes. ⚠️ Results carry no page text unless you ask: pass contents, or follow up with post_exa_contents. Choose it over searchWeb when the query is a description rather than keywords; choose Tavily when you want the text in the same call, and post_exa_answer when you want a written answer rather than a list.

請求本文
必填
application/json
  • query
    類型: string
    必填

    The natural-language search query.

  • category
    類型: string 列舉

    Optional hint about the kind of pages to prioritize.

    值
    • company
    • research paper
    • news
    • personal site
    • financial report
    • people
  • contents
    類型: object

    Content options to return alongside each result.

    • highlights
      類型: boolean

      Return highlighted relevant snippets.

    • summary
      類型: boolean

      Return an AI-generated summary of the page.

    • text
      類型: boolean

      Return the full page text.

  • endPublishedDate
    類型: string 格式: date-time

    Only return results published on or before this ISO 8601 date.

  • excludeDomains
    類型: array string[]

    Exclude results from these domains.

  • includeDomains
    類型: array string[]

    Only return results from these domains.

  • numResults
    類型: integer
    最小值:  
    1
    最大值:  
    100

    Number of results to return.

  • outputSchema
    類型: object

    JSON Schema used to synthesize a structured output from the results.

  • startPublishedDate
    類型: string 格式: date-time

    Only return results published on or after this ISO 8601 date.

  • systemPrompt
    類型: string

    Instruction that guides how the structured output is generated.

  • type
    類型: string 列舉

    Search mode. auto lets Exa choose; the deep modes trade latency for higher-quality retrieval.

    值
    • auto
    • fast
    • instant
    • deep-lite
    • deep
    • deep-reasoning
回應
  • 200
    類型: object

    Search completed successfully.

    • costDollars
      可為 null

      Upstream Exa cost breakdown. Informational only; customer billing is the flat $0.08.

    • output
      可為 null

      Structured output, present only when outputSchema was supplied.

    • requestId
      類型: string

      Exa request identifier.

    • results
      類型: array object[]

      Ranked search results.

      • author
        類型: string
      • id
        類型: string
      • publishedDate
        類型: string
      • title
        類型: string
      • url
        類型: string
    application/json
  • 400

    The request could not be processed. Check the request parameters.

  • 401

    A valid Felo API key is required.

  • 402

    The request cannot proceed because a billing requirement is not met.

  • 403

    The account is not permitted to perform this operation.

  • 429

    A request or spending limit has been reached.

  • 502

    The service could not complete the request.

  • 503

    The API or billing service is temporarily unavailable.

  • 504

    The service timed out while processing the request.

  • default

    The operation failed. Keep the response request ID when contacting Felo support.

Request Example for post/v1/beta/exa/search
curl https://openapi.felo.ai/v1/beta/exa/search \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer YOUR_SECRET_TOKEN' \
  --data '{
  "query": "latest evaluation frameworks for AI agents",
  "type": "auto",
  "numResults": 10,
  "category": "company",
  "includeDomains": [
    ""
  ],
  "excludeDomains": [
    ""
  ],
  "startPublishedDate": "",
  "endPublishedDate": "",
  "contents": {
    "text": true,
    "highlights": true,
    "summary": true
  },
  "outputSchema": {},
  "systemPrompt": ""
}'
{
  "requestId": "string",
  "results": [
    {
      "title": "string",
      "url": "string",
      "publishedDate": "string",
      "author": "string",
      "id": "string"
    }
  ],
  "output": null,
  "costDollars": null
}
Run a neural semantic web search.