{
"openapi": "3.0.1",
"info": {
"title": "RSS & Atom to Markdown — JSON + RAG Chunks",
"description": "Parse RSS 2.0 and Atom feeds into structured JSON with Markdown body text for RAG and LLM pipelines. Optional feed discovery from a page, content hash, and heading-aware chunks. Failed feeds are reported, not fatal. 256 MB default.",
"version": "0.1",
"x-build-id": "dtyQDi9wNYW4LJjTY"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/ingenious_quip_bxq~rss-atom-to-markdown/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-ingenious_quip_bxq-rss-atom-to-markdown",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/ingenious_quip_bxq~rss-atom-to-markdown/runs": {
"post": {
"operationId": "runs-sync-ingenious_quip_bxq-rss-atom-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/ingenious_quip_bxq~rss-atom-to-markdown/run-sync": {
"post": {
"operationId": "run-sync-ingenious_quip_bxq-rss-atom-to-markdown",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"feedUrls": {
"title": "Feed URLs",
"type": "array",
"description": "Direct RSS 2.0 or Atom feed URLs (also accepts JSON Feed). Paste a list or upload a text file of URLs.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"pageUrls": {
"title": "Page URLs (discover feeds)",
"type": "array",
"description": "Optional. HTML pages to scan for `` (and common `/feed`, `/rss`, `/atom.xml` paths). Discovered feeds are fetched in the same run.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"maxItems": {
"title": "Max items",
"minimum": 0,
"maximum": 100000,
"type": "integer",
"description": "Stop after saving this many feed entries (0 = no limit). Also caps your cost: you pay only for items saved.",
"default": 500
},
"maxItemsPerFeed": {
"title": "Max items per feed",
"minimum": 0,
"type": "integer",
"description": "Optional cap per feed (0 = no cap), so one large feed cannot use up the whole Max items budget.",
"default": 0
},
"publishedAfter": {
"title": "Published on or after",
"type": "string",
"description": "Keep only entries whose published/updated date is on or after this date (YYYY-MM-DD). Entries without a date are kept when *Keep undated items* is on."
},
"keepUndatedItems": {
"title": "Keep undated items",
"type": "boolean",
"description": "When a date filter is set, keep entries that have no published/updated date.",
"default": true
},
"includeUrlPatterns": {
"title": "Include link patterns (regex)",
"type": "array",
"description": "Keep only entries whose link matches at least one of these regular expressions.",
"items": {
"type": "string"
}
},
"excludeUrlPatterns": {
"title": "Exclude link patterns (regex)",
"type": "array",
"description": "Drop entries whose link matches any of these regular expressions.",
"items": {
"type": "string"
}
},
"outputFormat": {
"title": "Output",
"enum": [
"items",
"chunks",
"items_and_chunks"
],
"type": "string",
"description": "`items`: one dataset row per feed entry (title, link, published, authors, summary, contentMarkdown, …). `chunks`: RAG-ready chunks (one row per chunk) plus a per-entry summary row. `items_and_chunks`: both.",
"default": "items"
},
"preferFullContent": {
"title": "Prefer full content over summary",
"type": "boolean",
"description": "When the feed provides both a summary and full content (Atom `content`, RSS `content:encoded`), use the full body for Markdown. Off = use summary when present.",
"default": true
},
"chunkSize": {
"title": "Chunk size",
"minimum": 100,
"maximum": 20000,
"type": "integer",
"description": "Maximum chunk size (in the unit below). Chunks break at headings and paragraphs.",
"default": 1000
},
"chunkOverlap": {
"title": "Chunk overlap",
"minimum": 0,
"maximum": 10000,
"type": "integer",
"description": "How much trailing context from the previous chunk is repeated at the start of the next one (same unit as chunk size).",
"default": 150
},
"chunkUnit": {
"title": "Chunk size unit",
"enum": [
"tokens",
"characters"
],
"type": "string",
"description": "`tokens` uses a fast approximation (≈4 characters per token); `characters` is exact.",
"default": "tokens"
},
"tryCommonFeedPaths": {
"title": "Try common feed paths on pages",
"type": "boolean",
"description": "When discovering from a page, also try `/feed`, `/rss`, `/atom.xml`, `/feed.xml`, `/index.xml` if no `` is found.",
"default": true
},
"requestTimeoutSecs": {
"title": "Request timeout (seconds)",
"minimum": 5,
"maximum": 180,
"type": "integer",
"description": "Timeout for each HTTP request.",
"default": 30
},
"maxRetries": {
"title": "Max retries",
"minimum": 0,
"maximum": 8,
"type": "integer",
"description": "Retries for timeouts, network errors, HTTP 429 and 5xx (exponential backoff).",
"default": 3
},
"maxConcurrency": {
"title": "Max concurrency",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "Parallel feed/page fetches.",
"default": 4
},
"userAgent": {
"title": "User-Agent",
"type": "string",
"description": "Optional custom User-Agent header."
},
"proxyConfiguration": {
"title": "Proxy",
"type": "object",
"description": "Optional. Use a proxy if a site blocks data-center IPs. Not needed for most public feeds.",
"default": {
"useApifyProxy": false
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}