@youdotcom-oss/n8n-nodes-youdotcom 0.2.6 → 0.2.7

package/README.md

@@ -1,109 +1,90 @@
-# n8n-nodes-youdotcom
+# @youdotcom-oss/n8n-nodes-youdotcom
 
-An n8n community node for integrating [You.com APIs](https://you.com/apis) into your n8n workflows. Search the web and extract content from URLs.
+Add real time web search, page content extraction, and AI powered deep research to your n8n workflows with the [You.com](https://you.com) API.
 
-## Installation
-
-Follow the [installation guide](https://docs.n8n.io/integrations/community-nodes/installation/) in the n8n community nodes documentation.
+[n8n](https://n8n.io/) is a [fair-code licensed](https://docs.n8n.io/reference/license/) workflow automation platform.
 
-```bash
-npm install @youdotcom-oss/n8n-nodes-youdotcom
-```
+[Installation](#installation) | [Operations](#operations) | [Credentials](#credentials) | [Usage](#usage) | [Resources](#resources)
 
-Or install via the n8n UI:
+## Installation
 
-1. Go to **Settings > Community Nodes**
-2. Select **Install**
-3. Enter `@youdotcom-oss/n8n-nodes-youdotcom`
-4. Agree to the risks and select **Install**
+Follow the [installation guide](https://docs.n8n.io/integrations/community-nodes/installation/) in the n8n community nodes documentation.
 
 ## Operations
 
 ### Search
 
-Search the web and news using You.com's search API.
-
-| Parameter        | Required | Description                                             |
-| ---------------- | -------- | ------------------------------------------------------- |
-| Query            | Yes      | The search query (supports search operators, see below) |
-| Count            | No       | Maximum number of results per section (1-100)           |
-| Country          | No       | Country code for geographical focus (e.g., US, GB, DE)  |
-| Freshness        | No       | Filter by recency: day, week, month, or year            |
-| Language         | No       | Language of results (BCP 47 format)                     |
-| Livecrawl        | No       | Fetch full page content for web, news, or all results   |
-| Livecrawl Format | No       | Format for livecrawled content (HTML or Markdown)       |
-| Offset           | No       | Pagination offset (0-9)                                 |
-| Safe Search      | No       | Content moderation: off, moderate, or strict            |
+Search the web and news with up to date results. Supports advanced query operators (`site:`, `filetype:`, `+`, `-`, `AND`, `OR`, `NOT`) and geographic/language filtering.
 
-**Search operators:**
+Great for monitoring mentions, pulling recent news, or feeding live data into AI agent workflows.
 
-Include these directly in your query to refine results. See [search operators documentation](https://docs.you.com/search/search-operators) for details.
-
-| Operator   | Example                 | Description                                        |
-| ---------- | ----------------------- | -------------------------------------------------- |
-| `site:`    | `site:github.com`       | Restrict to a specific domain (including subdomains) |
-| `filetype:`| `filetype:pdf`          | Filter by file type                                |
-| `+`        | `+GAAP`                 | Require exact term in results                      |
-| `-`        | `-marketing`            | Exclude exact term from results                    |
-| `AND`      | `Python AND PyTorch`    | Logical AND to combine expressions                 |
-| `OR`       | `Python OR PyTorch`     | Logical OR to combine expressions                  |
-| `NOT`      | `NOT site:example.com`  | Negate an expression                               |
-
-**Example:** `machine learning (Python OR PyTorch) -TensorFlow filetype:pdf` searches for ML content about Python or PyTorch, excluding TensorFlow, in PDF format.
+| Parameter | Description |
+|-----------|-------------|
+| Query | The search query (required) |
+| Count | Max results per section, 1-100 (default: 10) |
+| Country | Two-letter country code to focus results geographically |
+| Freshness | Filter by recency: day, week, month, or year |
+| Language | BCP 47 language code for results (default: EN) |
+| Livecrawl | Fetch full page content for web, news, or all results |
+| Livecrawl Format | Format for livecrawled content: markdown or HTML |
+| Offset | Pagination offset, 0-9 |
+| Safe Search | Content filter: off, moderate, or strict |
 
 ### Get Contents
 
-Extract content from one or more URLs. Returns clean text, HTML, or structured metadata.
+Extract clean, structured content from one or more web pages. Returns page text as markdown or HTML, plus metadata like JSON-LD, OpenGraph, and Twitter Cards.
 
-| Parameter     | Required | Description                                              |
-| ------------- | -------- | -------------------------------------------------------- |
-| URLs          | Yes      | Comma-separated list of URLs to extract content from     |
-| Formats       | No       | Output formats: Markdown, HTML, and/or Metadata          |
-| Crawl Timeout | No       | Timeout in seconds for page crawling (1-60)              |
+Useful for scraping product pages, pulling article text, or extracting structured data from any URL.
 
-**Output formats:**
+| Parameter | Description |
+|-----------|-------------|
+| URLs | Comma-separated list of URLs to extract (required) |
+| Formats | Output formats: markdown, HTML, and/or metadata (JSON-LD, OpenGraph, Twitter Cards) |
+| Crawl Timeout | Timeout in seconds for page crawling, 1-60 (default: 30) |
 
-- **Markdown** - Clean text content, ideal for LLM processing
-- **HTML** - Full HTML with layout preserved
-- **Metadata** - Structured data (JSON-LD, OpenGraph, Twitter Cards)
+### Research
 
-## Credentials
+Get a comprehensive, cited answer to a complex question. The Research API searches the web, reads multiple sources, and synthesizes a detailed markdown response with inline numbered citations.
 
-1. Visit [you.com/platform/api-keys](https://you.com/platform/api-keys) to get an API key
-2. In n8n, go to **Credentials > New Credential**
-3. Search for "You.com API"
-4. Enter your API key and save
+Perfect for competitive analysis, market research, technical due diligence, or any question that needs more than a simple search result.
 
-## Example Use Cases
+| Parameter | Description |
+|-----------|-------------|
+| Input | The research question (required) |
+| Research Effort | Controls depth and speed (see below, default: standard) |
 
-- **Research workflows**: Search for information and extract full content from top results
-- **Content aggregation**: Monitor news across topics with customizable filters
-- **Data enrichment**: Extract metadata from URLs in your workflows
+**Research Effort levels:**
 
-## Development
+| Level | Description |
+|-------|-------------|
+| Lite | Quick answers for straightforward questions |
+| Standard | Balanced speed and depth (default) |
+| Deep | More time researching and cross-referencing sources |
+| Exhaustive | Most thorough option for complex research tasks |
+
+## Credentials
 
-```bash
-# Install dependencies
-bun install
+1. Go to [you.com/platform/api-keys](https://you.com/platform/api-keys) to get an API key
+2. In n8n, go to Credentials and create a new "You.com API" credential
+3. Paste your API key and save
 
-# Build the package
-bun run build
+## Usage
 
-# Run tests
-bun test
+1. Add the "You.com" node to your workflow
+2. Select an operation (Search, Get Contents, or Research)
+3. Configure the parameters for your chosen operation
+4. Run the workflow
 
-# Linting, formatting, and type checking
-bun run check
-```
+This node also works as a tool for [AI agents in n8n](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/). Connect it to an agent node and let the agent decide when to search the web, extract page content, or run deep research.
 
 ## Resources
 
-- [You.com API Documentation](https://docs.you.com/)
-- [Search API Reference](https://docs.you.com/api-reference/search/v1-search)
-- [Search Operators](https://docs.you.com/search/search-operators)
-- [Contents API Reference](https://docs.you.com/api-reference/search/contents)
-- [n8n Community Nodes Documentation](https://docs.n8n.io/integrations/community-nodes/)
+- [You.com API docs](https://docs.you.com/)
+- [Search API reference](https://docs.you.com/api-reference/search)
+- [Contents API reference](https://docs.you.com/api-reference/contents)
+- [Research API reference](https://docs.you.com/api-reference/research)
+- [n8n community nodes documentation](https://docs.n8n.io/integrations/community-nodes/)
 
 ## License
 
-MIT
+[MIT](LICENSE)

package/dist/credentials/YouDotComApi.credentials.js

@@ -2,27 +2,37 @@ var __defProp = Object.defineProperty;
 var __getOwnPropNames = Object.getOwnPropertyNames;
 var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
 var __hasOwnProp = Object.prototype.hasOwnProperty;
-var __moduleCache = /* @__PURE__ */ new WeakMap;
+function __accessProp(key) {
+  return this[key];
+}
 var __toCommonJS = (from) => {
-  var entry = __moduleCache.get(from), desc;
+  var entry = (__moduleCache ??= new WeakMap).get(from), desc;
   if (entry)
     return entry;
   entry = __defProp({}, "__esModule", { value: true });
-  if (from && typeof from === "object" || typeof from === "function")
-    __getOwnPropNames(from).map((key) => !__hasOwnProp.call(entry, key) && __defProp(entry, key, {
-      get: () => from[key],
-      enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable
-    }));
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (var key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(entry, key))
+        __defProp(entry, key, {
+          get: __accessProp.bind(from, key),
+          enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable
+        });
+  }
   __moduleCache.set(from, entry);
   return entry;
 };
+var __moduleCache;
+var __returnValue = (v) => v;
+function __exportSetter(name, newValue) {
+  this[name] = __returnValue.bind(null, newValue);
+}
 var __export = (target, all) => {
   for (var name in all)
     __defProp(target, name, {
       get: all[name],
       enumerable: true,
       configurable: true,
-      set: (newValue) => all[name] = () => newValue
+      set: __exportSetter.bind(all, name)
     });
 };
 

package/dist/nodes/YouDotCom/YouDotCom.node.js

@@ -2,27 +2,37 @@ var __defProp = Object.defineProperty;
 var __getOwnPropNames = Object.getOwnPropertyNames;
 var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
 var __hasOwnProp = Object.prototype.hasOwnProperty;
-var __moduleCache = /* @__PURE__ */ new WeakMap;
+function __accessProp(key) {
+  return this[key];
+}
 var __toCommonJS = (from) => {
-  var entry = __moduleCache.get(from), desc;
+  var entry = (__moduleCache ??= new WeakMap).get(from), desc;
   if (entry)
     return entry;
   entry = __defProp({}, "__esModule", { value: true });
-  if (from && typeof from === "object" || typeof from === "function")
-    __getOwnPropNames(from).map((key) => !__hasOwnProp.call(entry, key) && __defProp(entry, key, {
-      get: () => from[key],
-      enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable
-    }));
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (var key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(entry, key))
+        __defProp(entry, key, {
+          get: __accessProp.bind(from, key),
+          enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable
+        });
+  }
   __moduleCache.set(from, entry);
   return entry;
 };
+var __moduleCache;
+var __returnValue = (v) => v;
+function __exportSetter(name, newValue) {
+  this[name] = __returnValue.bind(null, newValue);
+}
 var __export = (target, all) => {
   for (var name in all)
     __defProp(target, name, {
       get: all[name],
       enumerable: true,
       configurable: true,
-      set: (newValue) => all[name] = () => newValue
+      set: __exportSetter.bind(all, name)
     });
 };
 
@@ -33,58 +43,7 @@ __export(exports_YouDotCom_node, {
 });
 module.exports = __toCommonJS(exports_YouDotCom_node);
 var import_n8n_workflow = require("n8n-workflow");
-var import_zod2 = require("zod");
-
-// nodes/YouDotCom/YouDotCom.schemas.ts
-var import_zod = require("zod");
-var SearchOptionsSchema = import_zod.z.object({
-  count: import_zod.z.number().int().min(1).max(100).optional().describe("Number of search results to return (1-100)"),
-  country: import_zod.z.string().optional().describe("Two-letter country code to filter results (e.g., US, GB)"),
-  freshness: import_zod.z.enum(["day", "week", "month", "year"]).optional().describe("Filter results by recency"),
-  language: import_zod.z.string().optional().describe("BCP 47 language code to filter results (e.g., en, es, fr)"),
-  livecrawl: import_zod.z.enum(["web", "news", "all"]).optional().describe("Type of content to crawl in real-time"),
-  livecrawl_formats: import_zod.z.enum(["html", "markdown"]).optional().describe("Format for live-crawled content"),
-  offset: import_zod.z.number().int().min(0).max(9).optional().describe("Pagination offset for search results (0-9)"),
-  safesearch: import_zod.z.enum(["off", "moderate", "strict"]).optional().describe("Safe search filtering level")
-});
-var WebResultSchema = import_zod.z.object({
-  url: import_zod.z.string().describe("URL of the search result"),
-  title: import_zod.z.string().describe("Title of the search result"),
-  description: import_zod.z.string().describe("Description snippet of the search result"),
-  snippets: import_zod.z.array(import_zod.z.string()).optional().describe("Content snippets"),
-  page_age: import_zod.z.string().optional().describe("Publication timestamp")
-}).passthrough();
-var NewsResultSchema = import_zod.z.object({
-  url: import_zod.z.string().describe("URL of the news article"),
-  title: import_zod.z.string().describe("Title of the news article"),
-  description: import_zod.z.string().describe("Description snippet of the news article"),
-  page_age: import_zod.z.string().optional().describe("Publication timestamp")
-}).passthrough();
-var MetadataSchema = import_zod.z.object({
-  search_uuid: import_zod.z.string().optional().describe("Unique search request ID"),
-  query: import_zod.z.string().optional().describe("Query that was searched"),
-  latency: import_zod.z.number().optional().describe("Latency in seconds")
-}).passthrough();
-var SearchResponseSchema = import_zod.z.object({
-  results: import_zod.z.object({
-    web: import_zod.z.array(WebResultSchema).optional().describe("Web search results"),
-    news: import_zod.z.array(NewsResultSchema).optional().describe("News search results")
-  }).passthrough(),
-  metadata: MetadataSchema.optional()
-}).passthrough();
-var ContentsOptionsSchema = import_zod.z.object({
-  formats: import_zod.z.array(import_zod.z.enum(["markdown", "html", "metadata"])).optional().describe("Output formats for extracted content"),
-  crawl_timeout: import_zod.z.number().int().min(1).max(60).optional().describe("Timeout in seconds for content crawling (1-60)")
-});
-var ContentsResponseSchema = import_zod.z.array(import_zod.z.object({
-  url: import_zod.z.string().url().describe("URL of the extracted content"),
-  markdown: import_zod.z.string().optional().describe("Content in Markdown format"),
-  html: import_zod.z.string().optional().describe("Content in HTML format"),
-  metadata: import_zod.z.record(import_zod.z.string(), import_zod.z.unknown()).optional().describe("Metadata extracted from the page")
-}).passthrough());
-
-// nodes/YouDotCom/YouDotCom.node.ts
-var PACKAGE_VERSION = "0.2.6";
+var PACKAGE_VERSION = "0.2.7";
 var USER_AGENT = `n8n-nodes-youdotcom/${PACKAGE_VERSION} (https://github.com/youdotcom-oss/n8n-nodes-youdotcom)`;
 
 class YouDotCom {
@@ -96,7 +55,7 @@ class YouDotCom {
     version: 1,
     usableAsTool: true,
     subtitle: '={{$parameter["operation"]}}',
-    description: "Search the web and extract content from URLs using You.com APIs",
+    description: "Search the web, extract content from URLs, and run multi-step research using You.com APIs",
     defaults: {
       name: "You.com"
     },
@@ -134,6 +93,12 @@ class YouDotCom {
             value: "contents",
             description: "Extract content from one or more URLs",
             action: "Extract content from web pages"
+          },
+          {
+            name: "Research",
+            value: "research",
+            description: "Get a comprehensive, cited answer to a complex question",
+            action: "Research a complex question"
           }
         ],
         default: "search"
@@ -410,6 +375,57 @@ class YouDotCom {
             description: "Timeout in seconds for page crawling (1-60)"
           }
         ]
+      },
+      {
+        displayName: "Input",
+        name: "input",
+        type: "string",
+        required: true,
+        typeOptions: {
+          rows: 4
+        },
+        displayOptions: {
+          show: {
+            operation: ["research"]
+          }
+        },
+        default: "",
+        placeholder: "e.g., Which global cities improved air quality the most over the past 10 years?",
+        description: "The research question or complex query requiring in-depth investigation"
+      },
+      {
+        displayName: "Research Effort",
+        name: "researchEffort",
+        type: "options",
+        displayOptions: {
+          show: {
+            operation: ["research"]
+          }
+        },
+        default: "standard",
+        description: "Controls the depth and time spent on research",
+        options: [
+          {
+            name: "Lite",
+            value: "lite",
+            description: "Quick answers for straightforward questions"
+          },
+          {
+            name: "Standard",
+            value: "standard",
+            description: "Balanced speed and depth for most questions"
+          },
+          {
+            name: "Deep",
+            value: "deep",
+            description: "More time researching and cross-referencing sources"
+          },
+          {
+            name: "Exhaustive",
+            value: "exhaustive",
+            description: "Most thorough option for complex research tasks"
+          }
+        ]
       }
     ]
   };
@@ -431,31 +447,14 @@ class YouDotCom {
             itemData: { item: i }
           });
           returnData.push(...executionData);
-        }
-      } catch (error) {
-        if (error instanceof import_zod2.ZodError) {
-          const errorMessage = `Validation error:
-${error.issues.map((e, i2) => `  ${i2 + 1}. ${e.path.join(".") || "root"}: ${e.message}`).join(`
-`)}`;
-          const serializedIssues = error.issues.map((issue) => ({
-            path: issue.path.join("."),
-            message: issue.message,
-            code: issue.code
-          }));
-          if (this.continueOnFail()) {
-            returnData.push({
-              json: {
-                error: errorMessage,
-                validationErrors: serializedIssues
-              },
-              pairedItem: { item: i }
-            });
-            continue;
-          }
-          throw new import_n8n_workflow.NodeApiError(this.getNode(), { message: errorMessage, issues: serializedIssues }, {
-            itemIndex: i
+        } else if (operation === "research") {
+          const response = await YouDotCom.#executeResearch(this, i);
+          const executionData = this.helpers.constructExecutionMetaData(this.helpers.returnJsonArray(response), {
+            itemData: { item: i }
           });
+          returnData.push(...executionData);
         }
+      } catch (error) {
         if (this.continueOnFail()) {
           returnData.push({
             json: {
@@ -474,8 +473,7 @@ ${error.issues.map((e, i2) => `  ${i2 + 1}. ${e.path.join(".") || "root"}: ${e.m
   }
   static async#executeSearch(context, itemIndex) {
     const query = context.getNodeParameter("query", itemIndex);
-    const rawOptions = context.getNodeParameter("searchOptions", itemIndex);
-    const options = SearchOptionsSchema.parse(rawOptions);
+    const options = context.getNodeParameter("searchOptions", itemIndex);
     const qs = { query };
     if (options.count)
       qs.count = options.count;
@@ -502,20 +500,19 @@ ${error.issues.map((e, i2) => `  ${i2 + 1}. ${e.path.join(".") || "root"}: ${e.m
       qs,
       json: true
     });
-    const response = SearchResponseSchema.parse(rawResponse);
-    return response;
+    return rawResponse;
   }
   static async#executeContents(context, itemIndex) {
     const urlsString = context.getNodeParameter("urls", itemIndex);
-    const rawOptions = context.getNodeParameter("contentsOptions", itemIndex);
-    const options = ContentsOptionsSchema.parse(rawOptions);
+    const options = context.getNodeParameter("contentsOptions", itemIndex);
     const urls = urlsString.split(",").map((url) => url.trim()).filter((url) => url.length > 0);
     if (urls.length === 0) {
       throw new import_n8n_workflow.NodeOperationError(context.getNode(), "At least one URL is required", { itemIndex });
     }
     const body = { urls };
-    if (options.formats && options.formats.length > 0) {
-      body.formats = options.formats;
+    const formats = options.formats;
+    if (formats && formats.length > 0) {
+      body.formats = formats;
     }
     if (options.crawl_timeout) {
       body.crawl_timeout = options.crawl_timeout;
@@ -529,7 +526,24 @@ ${error.issues.map((e, i2) => `  ${i2 + 1}. ${e.path.join(".") || "root"}: ${e.m
       body,
       json: true
     });
-    const response = ContentsResponseSchema.parse(rawResponse);
-    return response;
+    return rawResponse;
+  }
+  static async#executeResearch(context, itemIndex) {
+    const input = context.getNodeParameter("input", itemIndex);
+    const researchEffort = context.getNodeParameter("researchEffort", itemIndex);
+    const body = { input };
+    if (researchEffort) {
+      body.research_effort = researchEffort;
+    }
+    const rawResponse = await context.helpers.httpRequestWithAuthentication.call(context, "youDotComApi", {
+      method: "POST",
+      url: "https://api.you.com/v1/research",
+      headers: {
+        "User-Agent": USER_AGENT
+      },
+      body,
+      json: true
+    });
+    return rawResponse;
   }
 }

package/dist/nodes/YouDotCom/YouDotCom.node.json

@@ -6,7 +6,7 @@
   "resources": {
     "credentialDocumentation": [
       {
-        "url": "https://docs.you.com/get-started/quickstart"
+        "url": "https://docs.you.com/quickstart"
       }
     ],
     "primaryDocumentation": [
@@ -14,11 +14,27 @@
         "url": "https://docs.you.com/api-reference/search"
       },
       {
-        "url": "https://docs.you.com/api-reference/search/contents"
+        "url": "https://docs.you.com/api-reference/contents"
+      },
+      {
+        "url": "https://docs.you.com/api-reference/research"
       }
     ]
   },
-  "alias": ["search", "web search", "you", "youdotcom", "news", "ai search", "contents", "extract", "scrape", "crawl"],
+  "alias": [
+    "search",
+    "web search",
+    "you",
+    "youdotcom",
+    "news",
+    "ai search",
+    "contents",
+    "extract",
+    "scrape",
+    "crawl",
+    "research",
+    "deep research"
+  ],
   "subcategories": {
     "Utility": ["Data Transformation"]
   }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@youdotcom-oss/n8n-nodes-youdotcom",
-  "version": "0.2.6",
-  "description": "n8n community node for You.com APIs - Search and Contents extraction",
+  "version": "0.2.7",
+  "description": "n8n community node for You.com APIs - Search, Contents extraction, and Research",
   "license": "MIT",
   "engines": {
     "node": ">=18"
@@ -58,8 +58,7 @@
     ]
   },
   "peerDependencies": {
-    "n8n-workflow": "^2.6.0",
-    "zod": "^3.25.67"
+    "n8n-workflow": "^2.6.0"
   },
   "devDependencies": {
     "@biomejs/biome": "^2.3.8",
@@ -67,7 +66,6 @@
     "@types/bun": "^1.3.9",
     "eslint": "9.32.0",
     "n8n-workflow": "^2.6.0",
-    "typescript": "^5.9.3",
-    "zod": "^3.25.67"
+    "typescript": "^5.9.3"
   }
 }