{ "openapi": "3.0.1", "info": { "title": "Train Your Local LLM for Business & Finance - DataPro", "description": "Train your local LLM for business and finance with Ultimate DataPro. Scrapes live stock prices, SEC EDGAR filings, options chains, and financial news - then auto-builds Alpaca/ShareGPT fine-tuning datasets. Export as JSONL, CSV, or Parquet. Push to HuggingFace Hub.", "version": "1.0", "x-build-id": "vPeBTgm134VFDYiPL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/omissive_aurora~train-your-local-llm-for-business-finance---datapro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-omissive_aurora-train-your-local-llm-for-business-finance---datapro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/omissive_aurora~train-your-local-llm-for-business-finance---datapro/runs": { "post": { "operationId": "runs-sync-omissive_aurora-train-your-local-llm-for-business-finance---datapro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/omissive_aurora~train-your-local-llm-for-business-finance---datapro/run-sync": { "post": { "operationId": "run-sync-omissive_aurora-train-your-local-llm-for-business-finance---datapro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "tickers" ], "properties": { "mode": { "title": "Mode", "enum": [ "scrape", "training_data", "full" ], "type": "string", "description": "What to do with the scraped data.", "default": "scrape" }, "tickers": { "title": "Stock Tickers", "type": "array", "description": "List of stock ticker symbols to scrape (e.g., AAPL, MSFT, GOOGL).", "items": { "type": "string" }, "default": [ "AAPL" ] }, "keywords": { "title": "News Keywords", "type": "array", "description": "Additional keywords for news search (e.g., 'Federal Reserve', 'AI stocks').", "items": { "type": "string" }, "default": [] }, "include_technicals": { "title": "Include Technical Analysis", "type": "boolean", "description": "Calculate RSI, MACD, Bollinger Bands, moving averages, support/resistance for each ticker.", "default": true }, "include_sec": { "title": "Include SEC EDGAR Filings", "type": "boolean", "description": "Scrape 10-K, 10-Q, 8-K filings from SEC EDGAR with full-text extraction.", "default": false }, "filing_types": { "title": "SEC Filing Types", "type": "array", "description": "Types of SEC filings to scrape.", "items": { "type": "string" }, "default": [ "10-K", "10-Q" ] }, "max_filings": { "title": "Max Filings per Ticker", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of SEC filings to scrape per ticker.", "default": 5 }, "include_news": { "title": "Include Financial News", "type": "boolean", "description": "Scrape news from Yahoo Finance, Google News, SEC press releases.", "default": true }, "max_articles": { "title": "Max News Articles", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of news articles to scrape per source.", "default": 20 }, "include_economic": { "title": "Include FRED Economic Data", "type": "boolean", "description": "Fetch macroeconomic indicators from FRED (requires FRED_API_KEY env var).", "default": false }, "economic_indicators": { "title": "Economic Indicators", "type": "array", "description": "FRED indicator keys to fetch. Leave empty for defaults (GDP, CPI, unemployment, Fed rate, etc.).", "items": { "type": "string" }, "default": [] }, "training_format": { "title": "Training Data Format", "enum": [ "alpaca", "sharegpt" ], "type": "string", "description": "Format for generated LLM training examples.", "default": "alpaca" }, "include_options": { "title": "Include Options Chain Data", "type": "boolean", "description": "Scrape options chains with IV, Greeks, put/call ratios, and unusual activity detection.", "default": false }, "max_expiries": { "title": "Max Options Expiry Dates", "minimum": 1, "maximum": 12, "type": "integer", "description": "Maximum number of expiration dates to fetch per ticker.", "default": 4 }, "include_insider": { "title": "Include Insider Transactions", "type": "boolean", "description": "Parse Form 4 insider transactions with full details (shares, price, buyer/seller, title).", "default": false }, "include_ai_analysis": { "title": "AI-Enhanced Analysis", "type": "boolean", "description": "Use LLM (OpenAI/Gemini/Moonshot) for investment theses, sentiment analysis, and filing summaries. Requires an LLM API key.", "default": false }, "export_formats": { "title": "Export Formats", "type": "array", "description": "Output formats for scraped data and training datasets.", "items": { "type": "string" }, "default": [ "jsonl" ] }, "hf_repo_id": { "title": "HuggingFace Hub Repo ID", "type": "string", "description": "Push generated training dataset to HuggingFace Hub (e.g., 'username/my-financial-dataset'). Requires HF_TOKEN env var. Leave empty to skip.", "default": "" }, "hf_private": { "title": "HuggingFace Repo Private", "type": "boolean", "description": "Whether the HuggingFace dataset repo should be private.", "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 } } }, "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 } } } } } } } } } }