{ "openapi": "3.0.1", "info": { "title": "Arxiv Semantic Search", "description": "Scrape arXiv papers by category and find relevant research using AI-powered semantic search. Get papers from any field (AI, physics, biology, economics, etc.) with embeddings for RAG systems. Find your categories at: https://arxiv.org/category_taxonomy", "version": "1.0", "x-build-id": "wOTwVwSTiIX7sdOJI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/draouadmohamed~arxiv-semantic-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-draouadmohamed-arxiv-semantic-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/draouadmohamed~arxiv-semantic-search/runs": { "post": { "operationId": "runs-sync-draouadmohamed-arxiv-semantic-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/draouadmohamed~arxiv-semantic-search/run-sync": { "post": { "operationId": "run-sync-draouadmohamed-arxiv-semantic-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "categories", "maxPapers" ], "properties": { "categories": { "title": "ArXiv Categories", "type": "array", "description": "Select research categories. Common options:\n• Physics: quant-ph (Quantum), cond-mat (Condensed Matter), hep-th (High Energy)\n• Computer Science: cs.AI (AI), cs.LG (Machine Learning), cs.CL (NLP), cs.CV (Computer Vision)\n• Math: math.CO (Combinatorics), math.ST (Statistics)\n• Biology: q-bio.NC (Neuroscience), q-bio.GN (Genomics)\n• Economics: econ.EM (Econometrics), econ.TH (Economic Theory)\n• Statistics: stat.ML (Machine Learning), stat.ME (Methodology)\n\nFull list: https://arxiv.org/category_taxonomy", "default": [ "cs.AI" ], "items": { "type": "string" } }, "maxPapers": { "title": "Maximum Papers per Category", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many papers to fetch from each category. Example: 100 papers from cs.AI + 100 from cs.LG = 200 total", "default": 100 }, "startDate": { "title": "Start Date (Optional)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only fetch papers published after this date. Format: YYYY-MM-DD. Example: 2024-01-01 for papers from 2024 onwards. Leave empty for all papers." }, "endDate": { "title": "End Date (Optional)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Only fetch papers published before this date. Format: YYYY-MM-DD. Example: 2024-12-31. Leave empty for today." }, "searchQuery": { "title": "Semantic Search Query (Optional)", "type": "string", "description": "Enter your research topic in plain English. Examples:\n• 'transformer architecture for language models'\n• 'quantum error correction with topological codes'\n• 'deep learning for protein folding'\n\nLeave empty to just scrape papers without ranking them." }, "enableSemanticSearch": { "title": "Enable Semantic Search", "type": "boolean", "description": "Turn this ON to rank papers by relevance to your search query. Turn OFF to just download papers without ranking.\n\n✅ ON = Papers ranked by similarity to your query\n❌ OFF = All papers returned (faster, cheaper)", "default": false }, "topK": { "title": "Number of Results", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many of the most relevant papers to return (only used when Semantic Search is enabled). Example: 20 returns the top 20 most similar papers.", "default": 10 } } }, "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 } } }, "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 } } } } } } } } } }