AI Search Tool - Real-Time Web Search A powerful web search actor designed for AI agents and LLM applications that need real-time knowledge. ## Why This Actor? Break Through Knowledge Cutoffs - Give your LLM agents access to current information beyond their training data cutoff dates. Built for AI Agents - Structured JSON output perfect for LangGraph, AutoGPT, LangChain, and custom AI agent frameworks. Reliable Results - Multi-backend architecture with automatic fallback ensures you get results even when one search engine is rate-limited. ## Features - Multi-Backend Search - Automatically falls back between DuckDuckGo, Bing, Brave, Google, and Yahoo - 5 Search Types - Web, Images, Videos, News, and Books - 10+ Regions - Localized search results (US, UK, AU, JP, and more) - Smart Filtering - Safe search, time range filters, and result limits - Proxy Support - Apify Proxy (residential/datacenter/SERP) and custom proxies - AI-Ready Output - Clean JSON output in both Dataset and Key-Value Store ## Perfect For - LangGraph/LangChain Tools - Real-time web search for agent workflows - ChatGPT Plugins - External knowledge retrieval - RAG Systems - Current web data for retrieval augmented generation - AI Research Assistants - Fetch latest information on any topic - Autonomous Agents - AutoGPT, BabyAGI, and similar frameworks ## Input Configuration | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | query | string | required | Search query string | | maxResults | int | 50 | Maximum number of results (1-500) | | resultType | string | "web" | Type: web, images, videos, news, books | | region | string | "us-en" | Region code (see below) | | safeSearch | string | "moderate" | Options: off, moderate, strict | | timeRange | string | "" | Filter: d (day), w (week), m (month), y (year) | | proxy | object | null | Proxy configuration (optional) | ### Advanced Configuration | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | dev_transform_fields | array | [] | Transform output to include only specified fields. Use dot notation for nested objects (e.g., ["title", "link", "snippet"]) | | dev_dataset_name | string | "default" | Save results into a custom named Dataset. Supports placeholders: {ACTOR}, {DATE}, {TIME} | | dev_dataset_clear | boolean | false | Clear the dataset before inserting new data | ### Example Input - Basic Web Search json { "query": "artificial intelligence trends 2024", "maxResults": 10, "resultType": "web", "region": "us-en", "safeSearch": "moderate" } ### Example Input - Recent News with Time Filter json { "query": "OpenAI GPT-5", "maxResults": 20, "resultType": "news", "region": "us-en", "timeRange": "w", "safeSearch": "off" } ### Example Input - With Apify Proxy json { "query": "machine learning datasets", "maxResults": 50, "resultType": "web", "region": "us-en", "proxy": { "useApifyProxy": true, "apifyProxyGroups": ["RESIDENTIAL"], "apifyProxyCountry": "US" } } ## Supported Regions | Code | Region | Code | Region | |------|--------|------|--------| | us-en | United States | uk-en | United Kingdom | | au-en | Australia | ca-en | Canada | | nz-en | New Zealand | jp-jp | Japan | | de-de | Germany | fr-fr | France | | es-es | Spain | it-it | Italy | | nl-nl | Netherlands | br-pt | Brazil | ## Search Types ### 1. Web Search (resultType: "web") Returns standard web search results with titles, snippets, and URLs. Output Fields: - position - Result ranking (1, 2, 3...) - title - Page title - link - Full URL - snippet - Text excerpt - domain - Domain name - query - Original search query ### 2. Image Search (resultType: "images") Returns image search results with thumbnails and metadata. Output Fields: - position, title, link - image - Full-size image URL - thumbnail - Thumbnail URL - source - Source website - height, width - Image dimensions ### 3. Video Search (resultType: "videos") Returns video search results from multiple platforms. Output Fields: - position, title, link - description - Video description - thumbnail - Video thumbnail URL - duration - Video length - published - Publication date - publisher - Source (YouTube, Vimeo, etc.) ### 4. News Search (resultType: "news") Returns recent news articles with publication dates. Output Fields: - position, title, link - snippet - Article excerpt - date - Publication date - source - News source name - image - Article image URL ### 5. Books Search (resultType: "books") Returns book search results from Anna's Archive and other sources. Output Fields: - position, title, link - author - Book author - publisher - Publisher and year - info - Format and size info (e.g., "English [en], .epub, 0.5MB") - thumbnail - Book cover image URL ## Output Format Results are stored in two locations for maximum flexibility: ### 1. Dataset (Individual Results) Each search result is stored as a separate item in the dataset: json { "position": 1, "title": "Artificial intelligence", "link": "https://en.wikipedia.org/wiki/Artificial_intelligence", "snippet": "Artificial intelligence (AI) is the capability of computational systems...", "domain": "en.wikipedia.org", "query": "artificial intelligence" } ### 2. Key-Value Store (Complete Output) Three keys are stored for different use cases: OUTPUT - Full output with results and metadata: json { "results": [ { "position": 1, "title": "...", "link": "...", "snippet": "..." } ], "metadata": { "query": "artificial intelligence", "totalScraped": 10, "region": "us-en", "resultType": "web", "scrapeDuration": "2.18s" } } RESULTS - Just the results array for direct use METADATA - Just the metadata object ## Proxy Configuration ### Apify Proxy (Recommended) json { "proxy": { "useApifyProxy": true, "apifyProxyGroups": ["RESIDENTIAL"], "apifyProxyCountry": "US" } } Available Proxy Groups: - RESIDENTIAL - High-quality residential IPs - DATACENTER - Fast datacenter proxies - SERP - Specialized for search engines ### Custom Proxy URLs json { "proxy": { "proxyUrls": [ "http://user:pass@proxy1.example.com:8080", "http://user:pass@proxy2.example.com:8080" ] } } ### Manual Proxy Configuration json { "proxy": { "protocol": "http", "hostname": "proxy.example.com", "port": 8080, "username": "user", "password": "pass" } } ## Use Cases ### 1. Real-Time Knowledge for LLMs Give your AI assistant access to current events, latest research, or breaking news: json { "query": "latest developments in quantum computing", "maxResults": 10, "timeRange": "w" } ### 2. Fact-Checking & Verification Verify claims by searching recent news and authoritative sources: json { "query": "climate change statistics 2024", "resultType": "news", "timeRange": "m", "safeSearch": "strict" } ### 3. Research Assistant Gather information on specific topics for reports or analysis: json { "query": "best practices machine learning deployment", "maxResults": 50, "resultType": "web" } ### 4. Content Discovery Find images, videos, or news for content creation: json { "query": "startup funding 2024", "resultType": "news", "maxResults": 20 }