Tavily

搜索

执行一次 Tavily 搜索,返回结果列表与可选的 AI 摘要。

POST /tavily/search● 支持

Tavily 官方文档 ↗

请求体

  • querystring必填

    The search query to execute with Tavily.

  • search_depthstring可选
    默认 "basic"

    Controls the latency vs. relevance tradeoff and how `results[].content` is generated: - `advanced`: Highest relevance with increased latency. Best for detailed, high-precision queries. Returns multiple semantically relevant snippets per URL (configurable via `chunks_per_source`). - `basic`: A balanced option for relevance and latency. Ideal for general-purpose searches. Returns multiple semantically relevant snippets per URL (configurable via `chunks_per_source`). - `fast`: Prioritizes lower latency while maintaining good relevance. Returns multiple semantically relevant snippets per URL (configurable via `chunks_per_source`). - `ultra-fast`: Minimizes latency above all else. Best for time-critical use cases. Returns one NLP summary per URL. **Cost**: - `basic`, `fast`, `ultra-fast`: 1 API Credit - `advanced`: 2 API Credits See [Search Best Practices](/documentation/best-practices/best-practices-search#search-depth) for guidance on choosing the right search depth.

    取值 advancedbasicfastultra-fast
  • chunks_per_sourceinteger可选
    默认 3

    Chunks are short content snippets (maximum 500 characters each) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `content` length. Chunks will appear in the `content` field as: `<chunk 1> [...] <chunk 2> [...] <chunk 3>`. Available when `search_depth` is `advanced`, `basic` or `fast`.

  • max_resultsinteger可选
    默认 10

    The maximum number of search results to return.

  • topicstring可选
    默认 "general"

    The category of the search.`news` is useful for retrieving real-time updates, particularly about politics, sports, and major current events covered by mainstream media sources. `general` is for broader, more general-purpose searches that may include a wide range of sources.

    取值 generalnewsfinance
  • time_rangestring可选
    默认 null

    The time range back from the current date to filter results based on publish date or last updated date. Useful when looking for sources that have published or updated data. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them.

    取值 dayweekmonthyeardwmy
  • start_datestring可选
    默认 null

    Will return all results after the specified start date based on publish date or last updated date. Required to be written in the format YYYY-MM-DD. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them.

  • end_datestring可选
    默认 null

    Will return all results before the specified end date based on publish date or last updated date. Required to be written in the format YYYY-MM-DD. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them.

  • include_published_dateboolean可选
    默认 false

    Include a `published_date` field in each result. The date is Tavily's best estimate of when the source was published or last updated, so it can be later than the original publish date. Results with no detectable date return `null`. Automatically enabled when `topic` is `news`. **Note**: this feature is currently in beta.

  • filter_by_published_dateboolean可选
    默认 false

    Remove results whose published date falls outside the `time_range`, `start_date`, or `end_date` window. Results with no detectable published date are also removed. Setting this to `true` also enables `include_published_date`. If you want date-window filtering but don't want to lose sources without a detectable date, leave this `false` and set `include_published_date: true` together with a date range instead.

  • ▸ 更多参数(15)
    • include_answerboolean | string可选
      默认 false

      Include an LLM-generated answer to the provided query. `basic` or `true` returns a quick answer. `advanced` returns a more detailed answer.

    • include_raw_contentboolean | string可选
      默认 false

      Include the cleaned and parsed HTML content of each search result. `markdown` or `true` returns search result content in markdown format. `text` returns the plain text from the results and may increase latency.

    • include_imagesboolean可选
      默认 false

      Include images in the response. Returns both a top-level `images` list of query-related images and an `images` array inside each result object with images extracted from that specific source.

    • include_image_descriptionsboolean可选
      默认 false

      When `include_images` is `true`, also add a descriptive text for each image.

    • include_faviconboolean可选
      默认 false

      Whether to include the favicon URL for each result.

    • include_domainsarray可选
      默认 []

      A list of domains to specifically include in the search results. Maximum 300 domains.

    • exclude_domainsarray可选
      默认 []

      A list of domains to specifically exclude from the search results. Maximum 150 domains.

    • include_domains_modestring可选
      默认 null

      Controls how `include_domains` is applied. `restrict` limits results to only the listed domains. `prefer` also searches the rest of the web, so results outside `include_domains` can still surface, rather than excluding them. Requires `include_domains` to be set; returns a 400 error otherwise.

      取值 restrictprefer
    • countrystring可选
      默认 null

      Boost search results from a specific country. This will prioritize content from the selected country in the search results. Available only if topic is `general`.

      取值 afghanistanalbaniaalgeriaandorraangolaargentinaarmeniaaustraliaaustriaazerbaijanbahamasbahrainbangladeshbarbadosbelarusbelgiumbelizebeninbhutanboliviabosnia and herzegovinabotswanabrazilbruneibulgariaburkina fasoburundicambodiacamerooncanadacape verdecentral african republicchadchilechinacolombiacomoroscongocosta ricacroatiacubacyprusczech republicdenmarkdjiboutidominican republicecuadoregyptel salvadorequatorial guineaeritreaestoniaethiopiafijifinlandfrancegabongambiageorgiagermanyghanagreeceguatemalaguineahaitihondurashungaryicelandindiaindonesiairaniraqirelandisraelitalyjamaicajapanjordankazakhstankenyakuwaitkyrgyzstanlatvialebanonlesotholiberialibyaliechtensteinlithuanialuxembourgmadagascarmalawimalaysiamaldivesmalimaltamauritaniamauritiusmexicomoldovamonacomongoliamontenegromoroccomozambiquemyanmarnamibianepalnetherlandsnew zealandnicaraguanigernigerianorth koreanorth macedonianorwayomanpakistanpanamapapua new guineaparaguayperuphilippinespolandportugalqatarromaniarussiarwandasaudi arabiasenegalserbiasingaporeslovakiasloveniasomaliasouth africasouth koreasouth sudanspainsri lankasudanswedenswitzerlandsyriataiwantajikistantanzaniathailandtogotrinidad and tobagotunisiaturkeyturkmenistanugandaukraineunited arab emiratesunited kingdomunited statesuruguayuzbekistanvenezuelavietnamyemenzambiazimbabwe
    • languagestring可选
      默认 null

      Boost search results in a specific language. Accepts an ISO 639-1 code (e.g. `en`, `fr`, `zh-cn`) or an English language name (e.g. `english`, `french`). By default this only boosts matching-language results in ranking; pass `filter_by_language: true` to strictly filter out non-matching results instead. For best results, write your `query` in the same language you set here.

    • filter_by_languageboolean可选
      默认 false

      Strictly filter out search results that don't match the `language` parameter, instead of only boosting them in ranking. Requires `language` to be set; returns a 400 error otherwise.

    • auto_parametersboolean可选
      默认 false

      When `auto_parameters` is enabled, Tavily automatically configures search parameters based on your query's content and intent. You can still set other parameters manually, and your explicit values will override the automatic ones. The parameters `include_answer`, `include_raw_content`, and `max_results` must always be set manually, as they directly affect response size. Note: `search_depth` may be automatically set to advanced when it's likely to improve results. This uses 2 API credits per request. To avoid the extra cost, you can explicitly set `search_depth` to `basic`.

    • exact_matchboolean可选
      默认 false

      Ensure that only search results containing the exact quoted phrase(s) in the query are returned, bypassing synonyms or semantic variations. Wrap target phrases in quotes within your query (e.g. `"John Smith" CEO Acme Corp`). Punctuation is typically ignored inside quotes.

    • include_usageboolean可选
      默认 false

      Whether to include credit usage information in the response.

    • safe_searchboolean可选
      默认 false

      Whether to filter out adult or unsafe content from results. Not supported for `fast` or `ultra-fast` search depths.

返回

200

错误按 Tavily 格式返回,参见 错误码

响应

HTTP 200

Search results returned successfully

application/json

名称类型说明
querystringThe search query that was executed.
answerstringA short answer to the user's query, generated by an LLM. Included in the response only if `include_answer` is requested (i.e., set to `true`, `basic`, or `advanced`)
imagesarray<object>A list of query-related images from image search. If `include_image_descriptions` is true, each item will have `url` and `description`. Note: per-result images are also returned inside each result object's `images` field.
images[].urlstring
images[].descriptionstring
resultsarray<object>A list of sorted search results, ranked by relevancy.
results[].titlestringThe title of the search result.
results[].urlstringThe URL of the search result.
results[].contentstringA short description of the search result.
results[].scorenumberThe relevance score of the search result.
results[].raw_contentstringThe cleaned and parsed HTML content of the search result. Only if `include_raw_content` is true.
results[].published_datestringTavily's best estimate of when the source was published or last updated. Can be later than the original publish date. `null` if no date could be detected. Only returned when `include_published_date` is `true` (automatically enabled when `topic` is `news`).
results[].faviconstringThe favicon URL for the result.
results[].imagesarray<object>A list of images extracted from this search result. Only included when `include_images` is `true`. If `include_image_descriptions` is `true`, each item will have `url` and `description`.
results[].idstringUnique identifier for this result
auto_parametersobjectA dictionary of the selected auto_parameters, only shown when `auto_parameters` is true.
response_timenumberTime in seconds it took to complete the request.
usageobjectCredit usage details for the request.
request_idstringA unique request identifier you can share with customer support to help resolve issues with specific requests.