{ "openapi": "3.0.1", "info": { "title": "Search & URL Markdown Extractor for LLMs", "description": "Turn a search query or a list of URLs into clean Markdown, plain text, or HTML pages, with filters for domain, keyword, and minimum content length. No login or cookies needed.", "version": "1.0", "x-build-id": "gPqkQf6syKae3DRXC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vexaloom-labs~rag-web-browser/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vexaloom-labs-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vexaloom-labs~rag-web-browser/runs": { "post": { "operationId": "runs-sync-vexaloom-labs-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vexaloom-labs~rag-web-browser/run-sync": { "post": { "operationId": "run-sync-vexaloom-labs-rag-web-browser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "query": { "title": "Search query (or one URL)", "type": "string", "description": "What to look up, or a single web page URL to read. Examples: `vector database comparison`, `https://en.wikipedia.org/wiki/Retrieval-augmented_generation`. When `startUrls` or `queries` are also set, everything is processed in one run.", "default": "what is retrieval augmented generation" }, "queries": { "title": "More search queries", "type": "array", "description": "Additional queries for batch research runs. Each query is searched and its top results are fetched. A query that is itself a URL is fetched directly.", "default": [], "items": { "type": "string" } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Pages to read directly. With `maxCrawlDepth` above 0, the actor walks links found on these pages within the same website instead.", "default": [], "items": { "type": "string" } }, "searchEngine": { "title": "Search engine", "enum": [ "auto", "google", "bing", "duckduckgo" ], "type": "string", "description": "Which search engine to use. `Automatic` tries Google first and silently falls back to Bing, then DuckDuckGo when an engine is blocked — recommended.", "default": "auto" }, "searchLanguage": { "title": "Search language", "enum": [ "auto", "en", "de", "fr", "es", "it", "pt", "nl", "sv", "da", "fi", "no", "pl", "cs", "sk", "hu", "ro", "bg", "el", "tr", "ru", "uk", "ar", "he", "fa", "hi", "id", "ms", "th", "vi", "ja", "ko", "zh" ], "type": "string", "description": "Language for search results. `Automatic` lets each engine choose based on the query.", "default": "auto" }, "searchCountry": { "title": "Search country", "enum": [ "auto", "ad", "ae", "af", "ag", "ai", "al", "am", "ao", "aq", "ar", "as", "at", "au", "aw", "ax", "az", "ba", "bb", "bd", "be", "bf", "bg", "bh", "bi", "bj", "bl", "bm", "bn", "bo", "bq", "br", "bs", "bt", "bv", "bw", "by", "bz", "ca", "cc", "cd", "cf", "cg", "ch", "ci", "ck", "cl", "cm", "cn", "co", "cr", "cu", "cv", "cw", "cx", "cy", "cz", "de", "dj", "dk", "dm", "do", "dz", "ec", "ee", "eg", "eh", "er", "es", "et", "fi", "fj", "fk", "fm", "fo", "fr", "ga", "gb", "gd", "ge", "gf", "gg", "gh", "gi", "gl", "gm", "gn", "gp", "gq", "gr", "gs", "gt", "gu", "gw", "gy", "hk", "hm", "hn", "hr", "ht", "hu", "id", "ie", "il", "im", "in", "io", "iq", "ir", "is", "it", "je", "jm", "jo", "jp", "ke", "kg", "kh", "ki", "km", "kn", "kp", "kr", "kw", "ky", "kz", "la", "lb", "lc", "li", "lk", "lr", "ls", "lt", "lu", "lv", "ly", "ma", "mc", "md", "me", "mf", "mg", "mh", "mk", "ml", "mm", "mn", "mo", "mp", "mq", "mr", "ms", "mt", "mu", "mv", "mw", "mx", "my", "mz", "na", "nc", "ne", "nf", "ng", "ni", "nl", "no", "np", "nr", "nu", "nz", "om", "pa", "pe", "pf", "pg", "ph", "pk", "pl", "pm", "pn", "pr", "ps", "pt", "pw", "py", "qa", "re", "ro", "rs", "ru", "rw", "sa", "sb", "sc", "sd", "se", "sg", "sh", "si", "sj", "sk", "sl", "sm", "sn", "so", "sr", "ss", "st", "sv", "sx", "sy", "sz", "tc", "td", "tf", "tg", "th", "tj", "tk", "tl", "tm", "tn", "to", "tr", "tt", "tv", "tw", "tz", "ua", "ug", "um", "us", "uy", "uz", "va", "vc", "ve", "vg", "vi", "vn", "vu", "wf", "ws", "ye", "yt", "za", "zm", "zw" ], "type": "string", "description": "Country bias for search results. `Automatic` means no country bias.", "default": "auto" }, "maxResults": { "title": "Max search results per query", "minimum": 1, "maximum": 250, "type": "integer", "description": "How many top organic results to fetch and emit for each search query. Values above 10 need multiple search-result pages (slower). With `Emit results for pages that could not be fetched` on, each of the requested results yields one record — a page record when the fetch succeeds, or a metadata record with `fetchError` when it does not.", "default": 3 }, "maxItems": { "title": "Max pages per run", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Overall cap on how many pages the run may emit across all queries, URLs, and crawled pages. 0 means no global cap.", "default": 0 }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which representations to include per page, in any combination. `Links` adds every link found on the page as structured `{url, text}` pairs.", "items": { "type": "string", "enum": [ "markdown", "text", "html", "links" ], "enumTitles": [ "Markdown", "Plain text", "HTML", "Links" ] }, "default": [ "markdown" ] }, "removeElementsCssSelector": { "title": "Remove elements (CSS selector)", "type": "string", "description": "Comma-separated CSS selectors removed before extraction (navigation, footers, ads, cookie bars). Set a non-matching selector such as `dummy_keep_everything` to keep everything.", "default": "nav, footer, aside, script, style, .ad, .advertisement, [aria-hidden='true']" }, "keepElementsCssSelector": { "title": "Keep only elements (CSS selector)", "type": "array", "description": "When set, only content inside these selectors is kept — everything else is dropped before extraction.", "default": [], "items": { "type": "string" } }, "htmlTransformer": { "title": "Main content extraction", "enum": [ "none", "readable-text" ], "type": "string", "description": "`Readable content` finds the article body and drops navigation and boilerplate. `None` keeps the full cleaned page.", "default": "readable-text" }, "maxContentLength": { "title": "Max content length (characters)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Truncate the emitted text and Markdown of each page to this many characters. 0 returns the full content. Useful for controlling embedding cost.", "default": 0 }, "includeMetadata": { "title": "Include page metadata", "type": "boolean", "description": "Add canonical URL, author, published date, keywords, social image, and site name (each only when the page provides it).", "default": true }, "chunkMarkdown": { "title": "Split content into chunks", "type": "boolean", "description": "Emit a `chunks` array per page — heading-aware Markdown chunks ready for embedding, never split inside code blocks or tables.", "default": false }, "chunkMaxChars": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Target size of each chunk when `chunkMarkdown` is on. Code blocks and tables are kept whole even when larger.", "default": 2000 }, "chunkOverlapChars": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Approximate overlap between consecutive chunks when `chunkMarkdown` is on, so context is not lost at chunk boundaries.", "default": 200 }, "maxCrawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "0 reads only the start URLs. 1+ follows links found on those pages, staying on the same website, up to this depth.", "default": 0 }, "maxCrawlPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 500, "type": "integer", "description": "Safety cap on pages visited in crawl mode.", "default": 25 }, "domainAllowlist": { "title": "Allowed domains", "type": "array", "description": "Keep only pages whose host contains one of these substrings (case-insensitive).", "default": [], "items": { "type": "string" } }, "domainBlocklist": { "title": "Blocked domains", "type": "array", "description": "Drop pages whose host contains one of these substrings.", "default": [], "items": { "type": "string" } }, "minTextLength": { "title": "Minimum text length", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Drop pages with fewer than this many characters of extracted text. Useful for skipping thin or placeholder pages." }, "excludeContentSelectors": { "title": "Extra selectors to remove", "type": "array", "description": "Additional CSS selectors removed before extraction, on top of `Remove elements`.", "default": [], "items": { "type": "string" } }, "keywordsAnyOf": { "title": "Required keywords (any of)", "type": "array", "description": "Keep only pages whose title or content contains at least one of these keywords (case-insensitive).", "default": [], "items": { "type": "string" } }, "emitFailedResults": { "title": "Emit results for pages that could not be fetched", "type": "boolean", "description": "When a search result page cannot be fetched after the full retry ladder, still emit one record for it with `url`, `title`, `description`, `searchResult`, `searchRank` and a `fetchError` note (no fabricated content). Turn off to skip failed pages entirely.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }