AI Agent to chat with you Search Console Data, using OpenAI and Postgres

{"id": "PoiRk5w0xd1ysq4U", "meta": {"instanceId": "b9faf72fe0d7c3be94b3ebff0778790b50b135c336412d28fd4fca2cbbf8d1f5", "templateCredsSetupCompleted": true}, "name": "AI Agent to chat with you Search Console Data, using OpenAI and Postgres", "tags": [], "nodes": [{"id": "9ee6710b-19b7-4bfd-ac2d-0fe1e2561f1d", "name": "Postgres Chat Memory", "type": "@n8n/n8n-nodes-langchain.memoryPostgresChat", "position": [1796, 220], "parameters": {"tableName": "insights_chat_histories"}, "credentials": {"postgres": {"id": "", "name": "[Your postgres]"}}, "typeVersion": 1.1}, {"id": "eb9f07e9-ded1-485c-9bf3-cf223458384a", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [1356, 240], "parameters": {"model": "gpt-4o", "options": {"maxTokens": 16000}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "1d3d6fb7-a171-4590-be42-df7eb0c208ed", "name": "Set fields", "type": "n8n-nodes-base.set", "position": [940, -20], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "9f47b322-e42f-42d7-93eb-a57d22adb849", "name": "chatInput", "type": "string", "value": "={{ $json.body?.chatInput || $json.chatInput }}"}, {"id": "73ec4dd0-e986-4f60-9dca-6aad2f86bdeb", "name": "sessionId", "type": "string", "value": "={{ $json.body?.sessionId || $json.sessionId }}"}, {"id": "4b688c46-b60f-4f0a-83d8-e283f2d7055c", "name": "date_message", "type": "string", "value": "={{ $now.format('yyyy-MM-dd') }}"}]}}, "typeVersion": 3.4}, {"id": "92dc5e8b-5140-49be-8713-5749b7e2d46b", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [407.32142857142867, -320], "parameters": {"color": 7, "width": 347.9910714285712, "height": 516.8973214285712, "content": "## Webhook - ChatInput\n\nThis webhook serves as the endpoint for receiving `ChatInput` data. Ensure that you include:\n- `chatInput` \u2013 the content you wish to send (\ud83d\ude09)\n- `sessionId` \u2013 a unique identifier for the session\n\nIf you're using an interface such as **Open WebUI**, the `sessionId` will be generated automatically."}, "typeVersion": 1}, {"id": "ca9f3732-9b62-4f44-b970-77d5d470ec76", "name": "Webhook - ChatInput", "type": "n8n-nodes-base.webhook", "position": [500, -20], "webhookId": "a6820b65-76cf-402b-a934-0f836dee6ba0", "parameters": {"path": "a6820b65-76cf-402b-a934-0f836dee6ba0/chat", "options": {}, "httpMethod": "POST", "responseMode": "responseNode", "authentication": "basicAuth"}, "credentials": {"httpBasicAuth": {"id": "", "name": "[Your httpBasicAuth]"}}, "typeVersion": 2}, {"id": "9d684873-6dfe-4709-928d-293b187dfb30", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [820, -320], "parameters": {"color": 7, "width": 347.9910714285712, "height": 516.8973214285712, "content": "## Set fields\n\nThis node sets three fields:\n- `chatInput`: retrieved from the previous webhook node\n- `sessionId`: retrieved from the previous webhook node\n- `date_message`: formatted within this node. This will be used later to help the AI agent determine the date range for retrieving Search Console data."}, "typeVersion": 1}, {"id": "8750215a-1e33-4ac8-a6da-95efa8ffed65", "name": "Respond to Webhook", "type": "n8n-nodes-base.respondToWebhook", "position": [2600, -20], "parameters": {"options": {}}, "typeVersion": 1.1}, {"id": "1b879496-5c0f-4bd5-b4cb-18df2662aef2", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [1240, -320], "parameters": {"color": 7, "width": 1154.2857142857138, "height": 516.8973214285712, "content": "## AI Agent - Tools Agent\n\nThis AI Agent is configured with a system prompt that instructs it to:\n- On the first user message, **retrieve available Search Console properties** and offer the user the option to **fetch data from these properties**\n- Based on the user\u2019s natural language input, **construct an API call** to the selected Search Console property and retrieve the requested data\n- Present the data in a **markdown-formatted table**\n\nThe AI Agent has a friendly tone and is designed to **confirm the user\u2019s data requirements accurately** before executing any API requests.\n"}, "typeVersion": 1}, {"id": "c44c6402-9ddd-4a7b-bc5a-b6c3679a3f68", "name": "Call Search Console Tool", "type": "@n8n/n8n-nodes-langchain.toolWorkflow", "position": [2196, 220], "parameters": {"name": "SearchConsoleRequestTool", "workflowId": {"__rl": true, "mode": "list", "value": "PoiRk5w0xd1ysq4U", "cachedResultName": "My workflow 10"}, "description": "Call this tool when you need to get the website_list or custom_insights", "jsonSchemaExample": ""}, "typeVersion": 1.2}, {"id": "b1701a89-c5b3-47fb-99d5-4896a6d5c7a2", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [1234, 220], "parameters": {"color": 6, "width": 328.9664285714292, "height": 468.13107142857154, "content": "\n\n\n\n\n\n\n\n\n\n\n### AI Agent Sub-node - OpenAI Chat Model\n\nThis sub-node utilizes the selected **OpenAI Chat Model**. You can replace it with any LLM that **supports tool calling**.\n\n### \u26a0\ufe0f Choose Your Model\nIn this template, the **default model is `gpt-4o`**, a **costly option**. If you'd like a more **affordable alternative**, select `gpt4-o-mini`, though note that responses may occasionally be of slightly lower quality compared to `gpt-4o`."}, "typeVersion": 1}, {"id": "cd1a7cec-5845-47b1-a2c8-d3b458a02eb0", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [1656, 220], "parameters": {"color": 6, "width": 328.9664285714292, "height": 468.13107142857154, "content": "\n\n\n\n\n\n\n\n\n\n\n### AI Agent Sub-node - Postgres Chat Memory\n\nConnect your **Postgres credentials** and specify a **table name** to store the chat history. In this template, the default table name is `insights_chat_histories`, and the **context window length is set to 5**.\n\n**\ud83d\udc4b Tip:** If you don\u2019t have a Postgres database, you can quickly **set one up with [Supabase](https://supabase.com/)**.\n"}, "typeVersion": 1}, {"id": "290a07d1-c7ed-434d-9851-2a2dcdd35bdf", "name": "Sticky Note6", "type": "n8n-nodes-base.stickyNote", "position": [2076, 220], "parameters": {"color": 6, "width": 328.9664285714292, "height": 468.13107142857154, "content": "\n\n\n\n\n\n\n\n\n\n\n### AI Agent Sub-node - Call Search Console Tool\n\nThis **tool is used by the AI Agent** to:\n- Retrieve the **list of accessible properties in Search Console**\n- **Fetch Search Console data** based on the user\u2019s natural language request\n\n"}, "typeVersion": 1}, {"id": "07805c90-7ba5-44d0-b6eb-5a65efb0f8be", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [2480, -320], "parameters": {"color": 7, "width": 347.9910714285712, "height": 516.8973214285712, "content": "## Respond to Webhook\n\nThis node is used to send a response back to the user.\n\n**\ud83d\udc4b Tip:** `intermediateSteps` are configured, allowing you to use raw data fetched from Search Console to **create charts or other visualizations** if desired.\n"}, "typeVersion": 1}, {"id": "9a927a40-45e4-4fd5-ab3e-b77578469f82", "name": "Sticky Note7", "type": "n8n-nodes-base.stickyNote", "position": [400, 800], "parameters": {"color": 7, "width": 370.3910714285712, "height": 492.3973214285712, "content": "## Tool Call Trigger\n\nThis **node is triggered when the AI Agent needs to retrieve the `website_list`** (accessible Search Console properties) or **`custom_insights`** based on user data.\n"}, "typeVersion": 1}, {"id": "c54a4653-0f09-46b0-bd20-68919b96e154", "name": "Tool calling", "type": "n8n-nodes-base.executeWorkflowTrigger", "position": [500, 1080], "parameters": {}, "typeVersion": 1}, {"id": "cc7303ee-1afa-4859-83e7-3af0e963a0f1", "name": "Switch", "type": "n8n-nodes-base.switch", "position": [1300, 1080], "parameters": {"rules": {"values": [{"outputKey": "custom_insights", "conditions": {"options": {"version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "a30fe6a6-7d0a-4f14-8492-ae021ddc8ec6", "operator": {"type": "string", "operation": "contains"}, "leftValue": "={{ $json.request_type }}", "rightValue": "custom_insights"}]}, "renameOutput": true}, {"outputKey": "website_list", "conditions": {"options": {"version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "1b7d6039-6474-4a73-b157-584743a9d7f0", "operator": {"type": "string", "operation": "contains"}, "leftValue": "={{$json.request_type}}", "rightValue": "website_list"}]}, "renameOutput": true}]}, "options": {}}, "typeVersion": 3.2}, {"id": "6860ff98-4050-4f64-b8c1-a153e3388df0", "name": "Set fields - Consruct API CALL", "type": "n8n-nodes-base.set", "position": [920, 1080], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "06373437-8288-4171-9f98-e8a417220dd4", "name": "request_type", "type": "string", "value": "={{ $json.query.parseJson().request_type }}"}, {"id": "da45c0c5-05f6-4107-81aa-8c08c972d9bf", "name": "start_date", "type": "string", "value": "={{ $json.query.parseJson().startDate }}"}, {"id": "59d55034-c612-43d7-9700-4cacdb630ec2", "name": "end_date", "type": "string", "value": "={{ $json.query.parseJson().endDate }}"}, {"id": "4c2478c0-7f96-4d3d-a632-089307dc989e", "name": "dimensions", "type": "string", "value": "={{ $json.query.parseJson().dimensions }}"}, {"id": "eceefbf9-44e5-4617-96ea-58aca2a29618", "name": "rowLimit", "type": "number", "value": "={{ $json.query.parseJson().rowLimit }}"}, {"id": "4e18386e-8548-4385-b620-43efbb11cd63", "name": "startRow", "type": "number", "value": "={{ $json.query.parseJson().startRow}}"}, {"id": "a9323a7b-08b4-4015-b3d7-632bcdf56f4e", "name": "property", "type": "string", "value": "={{ encodeURIComponent($json.query.parseJson().property) }}"}]}}, "typeVersion": 3.4}, {"id": "0a2dfb28-17ee-477f-b9ea-f1d8e05e3745", "name": "Sticky Note8", "type": "n8n-nodes-base.stickyNote", "position": [820, 800], "parameters": {"color": 7, "width": 370.3910714285712, "height": 492.3973214285712, "content": "## Set Fields - Construct API Call\n\nThis node configures fields based on the JSON sent by the AI agent:\n- The `request_type` field determines the route: `website_list` (to retrieve the list of websites) or `custom_insights` (to get insights from Search Console)\n- Additional fields are set to construct the API call, following the **[Search Console API Documentation](https://developers.google.com/webmaster-tools/v1/searchanalytics/query?hl=en)**\n"}, "typeVersion": 1}, {"id": "e6ef5c28-01e4-4a0b-9081-b62ec28be635", "name": "Set fields - Create searchConsoleDataArray", "type": "n8n-nodes-base.set", "position": [2180, 980], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "2cffd36f-72bd-4535-8427-a88028ea0c4c", "name": "searchConsoleData", "type": "array", "value": "={{ $json.rows }}"}]}}, "typeVersion": 3.4}, {"id": "abc80061-a794-4e1d-a055-bd88ea5c93eb", "name": "Set fields - Create searchConsoleDataArray 2", "type": "n8n-nodes-base.set", "position": [2180, 1340], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "2cffd36f-72bd-4535-8427-a88028ea0c4c", "name": "searchConsoleData", "type": "array", "value": "={{ $json.siteEntry }}"}]}}, "typeVersion": 3.4}, {"id": "24981eea-980e-4e07-9036-d0042c5b2fbe", "name": "Search Console - Get Custom Insights", "type": "n8n-nodes-base.httpRequest", "position": [1620, 980], "parameters": {"url": "=https://www.googleapis.com/webmasters/v3/sites/{{ $json.property }}/searchAnalytics/query", "method": "POST", "options": {}, "jsonBody": "={\n \"startDate\": \"{{ $json.start_date }}\",\n \"endDate\": \"{{ $json.end_date }}\",\n \"dimensions\": {{ $json.dimensions }},\n \"rowLimit\": {{ $json.rowLimit }},\n \"startRow\": 0,\n \"dataState\":\"all\"\n}", "sendBody": true, "sendQuery": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "oAuth2Api", "queryParameters": {"parameters": [{}]}, "headerParameters": {"parameters": [{"name": "Content-Type", "value": "application/json"}]}}, "credentials": {"oAuth2Api": {"id": "", "name": "[Your oAuth2Api]"}}, "typeVersion": 4.2}, {"id": "645ff407-857d-4629-926b-5cfc52cfa8ba", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [1520, 800], "parameters": {"color": 7, "width": 370.3910714285712, "height": 364.3185243941325, "content": "## Search Console - Get Custom Insights\n\nThis node **performs the API call to retrieve data from Search Console**.\n"}, "typeVersion": 1}, {"id": "15aa66e2-f288-4c86-8dad-47e22aa9104f", "name": "Sticky Note10", "type": "n8n-nodes-base.stickyNote", "position": [1520, 1180], "parameters": {"color": 7, "width": 370.3910714285712, "height": 334.24982142857124, "content": "## Search Console - Get List of Properties\n\nThis node **performs the API call to retrieve the list of accessible properties from Search Console**.\n"}, "typeVersion": 1}, {"id": "cd804a52-833a-451a-8e0c-f640210ee2c4", "name": "## Search Console - Get List of Properties", "type": "n8n-nodes-base.httpRequest", "position": [1620, 1340], "parameters": {"url": "=https://www.googleapis.com/webmasters/v3/sites", "options": {}, "sendHeaders": true, "authentication": "genericCredentialType", "genericAuthType": "oAuth2Api", "headerParameters": {"parameters": [{"name": "Content-Type", "value": "application/json"}]}}, "credentials": {"oAuth2Api": {"id": "", "name": "[Your oAuth2Api]"}}, "typeVersion": 4.2}, {"id": "3eac4df1-00ac-4262-b520-3a7e218c7e57", "name": "Sticky Note11", "type": "n8n-nodes-base.stickyNote", "position": [2040, 800], "parameters": {"color": 7, "width": 370.3910714285712, "height": 725.1298214285712, "content": "## Set Fields - Create `searchConsoleDataArray`\n\nThese nodes **create an array based on the response from the Search Console API**.\n"}, "typeVersion": 1}, {"id": "86db5800-a735-4749-a800-63d78908610b", "name": "Sticky Note12", "type": "n8n-nodes-base.stickyNote", "position": [2520, 800], "parameters": {"color": 7, "width": 370.3910714285712, "height": 722.6464176100125, "content": "## Array Aggregation - Response to AI Agent\n\nThese nodes **aggregate the array from the previous** step and send it back to the AI Agent through the field named output as `response`.\n"}, "typeVersion": 1}, {"id": "aefbacc7-8dfc-4655-bc4d-f0498c823711", "name": "Array aggregation - response to AI Agent", "type": "n8n-nodes-base.aggregate", "position": [2640, 980], "parameters": {"options": {}, "aggregate": "aggregateAllItemData", "destinationFieldName": "response"}, "typeVersion": 1}, {"id": "e5334c72-981c-4375-ae8e-9a3a0457880b", "name": "Array aggregation - response to AI Agent1", "type": "n8n-nodes-base.aggregate", "position": [2660, 1340], "parameters": {"options": {}, "aggregate": "aggregateAllItemData", "destinationFieldName": "response"}, "typeVersion": 1}, {"id": "2e93a798-6c26-4d34-a553-ba01b64ca3fe", "name": "Sticky Note13", "type": "n8n-nodes-base.stickyNote", "position": [-398.45627799387194, -320], "parameters": {"width": 735.5589746610085, "height": 1615.4504601771982, "content": "# AI Agent to Chat with Your Search Console Data\n\nThis **AI Agent enables you to interact with your Search Console data** through a **chat interface**. Each node is **documented within the template**, providing sufficient information for setup and usage. You will also need to **configure Search Console OAuth credentials**.\n\nFollow this **[n8n documentation](https://docs.n8n.io/integrations/builtin/credentials/google/oauth-generic/#configure-your-oauth-consent-screen)** to set up the OAuth credentials.\n\n## Important Notes\n\n### Correctly Configure Scopes for Search Console API Calls\n- It\u2019s essential to **configure the scopes correctly** in your Google Search Console API OAuth2 credentials. Incorrect **configuration can cause issues with the refresh token**, requiring frequent reconnections. Below is the configuration I use to **avoid constant re-authentication**:\n![Search Console API oAuth2 config 1](https://i.imgur.com/vVLM7gG.png)\n![Search Console API oAuth2 config 2](https://i.imgur.com/naT1NaX.png)\n\nOf course, you'll need to add your **client_id** and **client_secret** from the **Google Cloud Platform app** you created to access your Search Console data.\n\n### Configure Authentication for the Webhook\n\nSince the **webhook will be publicly accessible**, don\u2019t forget to **set up authentication**. I\u2019ve used **Basic Auth**, but feel free to **choose the method that best meets your security requirements**.\n\n## \ud83e\udd29\ud83d\udc96 Example of awesome things you can do with this AI Agent\n![Example of chat with this AI Agent](https://i.imgur.com/jbfsYvT.png)\n\n\n"}, "typeVersion": 1}, {"id": "fa630aa9-3c60-4b27-9477-aaeb79c7f37d", "name": "AI Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [1676, -20], "parameters": {"text": "=user_message : {{ $json.chatInput }}\ndate_message : {{ $json.date_message }}", "options": {"systemMessage": "=Assist users by asking natural, conversational questions to understand their data needs and building a custom JSON API request to retrieve Search Console data. Handle assumptions internally, confirming them with the user in a friendly way. Avoid technical jargon and never imply that the user is directly building an API request.\n\nPre-Step: Retrieve the Website List\nImportant: Initial Action: Before sending your first message to the user, retrieve the list of connected Search Console properties.\n\nTool Call for Website List:\n\nTool name: SearchConsoleRequestTool\nRequest:\n{\n \"request_type\": \"website_list\" // Always include `request_type` in the API call.\n}\nUsage: Use this list to personalize your response in the initial interaction.\nStep-by-Step Guide\nStep 1: Initial Interaction and Introduction\nGreeting:\n\n\"Hi there! I\u2019m here to help you gain valuable insights from your Search Console data. Whether you're interested in a specific time frame, performance breakdown by pages, queries, or other dimensions, I've got you covered.\n\nI can help you retrieve data for these websites:\n\nhttps://example1.com\nhttps://example2.com\nhttps://example3.com\nWhich of these properties would you like to analyze?\"\nStep 2: Handling User Response for Property Selection\nAction: When the user selects a property, use the property URL exactly as listed (e.g., \"https://example.com\") when constructing the API call.\n\nStep 3: Understanding the User's Needs\nAcknowledgment and Setting Defaults:\n\nIf the user expresses a general need (e.g., \"I want the last 3 months of page performance\"), acknowledge their request and set reasonable defaults.\n\nExample Response:\n\n\"Great! I'll gather the top 300 queries from the last 3 months for https://example.com. If you'd like more details or adjustments, just let me know.\"\n\nFollow-up Questions:\n\nConfirming Dimensions: If the user doesn\u2019t specify dimensions, ask:\n\n\"For this analysis, I\u2019ll look at page performance. Does that sound good, or would you like to include other details like queries, devices, or other dimensions?\"\n\nNumber of Results: If the user hasn\u2019t specified the number of results, confirm:\n\n\"I can show you the top 100 results. Let me know if you'd like more or fewer!\"\n\nStep 4: Gathering Specific Inputs (If Necessary)\nAction: If the user provides specific needs, capture and confirm them naturally.\n\nExample Response:\n\n\"Perfect, I\u2019ll pull the data for [specified date range], focusing on [specified dimensions]. Anything else you\u2019d like me to include?\"\n\nImplicit Defaults:\n\nDate Range: Assume \"last 3 months\" if not specified.\nRow Limit: Default to 100, adjustable based on user input.\nStep 5: Confirming Input with the User\nAction: Summarize the request to ensure accuracy.\n\nExample Response:\n\n\"Here\u2019s what I\u2019m preparing: data for https://example.com, covering the last 3 months, focusing on the top 100 queries. Let me know if you\u2019d like to adjust anything!\"\n\nStep 6: Constructing the JSON for Custom Insights\nAction: Build the API call based on the conversation.\n\n{\n \"property\": \"<USER_PROVIDED_PROPERTY_URL>\", // Use the exact property URL.\n \"request_type\": \"custom_insights\",\n \"startDate\": \"<ASSUMED_OR_USER_SPECIFIED_START_DATE>\",\n \"endDate\": \"<ASSUMED_OR_USER_SPECIFIED_END_DATE>\",\n \"dimensions\": [\"<IMPLIED_OR_USER_SPECIFIED_DIMENSIONS>\"], // Array of one or more: \"page\", \"query\", \"searchAppearance\", \"device\", \"country\"\n \"rowLimit\": 300 // Default or user-specified limit.\n}\nStep 7: Presenting the Data\nWhen Retrieving Custom Insights:\n\nImportant: Display all retrieved data in an easy-to-read markdown table format.\nStep 8: Error Handling\nAction: Provide clear, user-friendly error messages when necessary.\n\nExample Response:\n\n\"Hmm, there seems to be an issue retrieving the data. Let\u2019s review what we have or try a different approach.\"\n\nAdditional Notes\nProactive Assistance: Offer suggestions based on user interactions, such as adding dimensions or refining details.\nTone: Maintain a friendly and helpful demeanor throughout the conversation.", "returnIntermediateSteps": true}, "promptType": "define"}, "typeVersion": 1.6}], "active": true, "pinData": {}, "settings": {"executionOrder": "v1"}, "versionId": "abda3766-7d18-46fb-83e7-c2343ff26385", "connections": {"Switch": {"main": [[{"node": "Search Console - Get Custom Insights", "type": "main", "index": 0}], [{"node": "## Search Console - Get List of Properties", "type": "main", "index": 0}]]}, "AI Agent": {"main": [[{"node": "Respond to Webhook", "type": "main", "index": 0}]]}, "Set fields": {"main": [[{"node": "AI Agent", "type": "main", "index": 0}]]}, "Tool calling": {"main": [[{"node": "Set fields - Consruct API CALL", "type": "main", "index": 0}]]}, "OpenAI Chat Model": {"ai_languageModel": [[{"node": "AI Agent", "type": "ai_languageModel", "index": 0}]]}, "Webhook - ChatInput": {"main": [[{"node": "Set fields", "type": "main", "index": 0}]]}, "Postgres Chat Memory": {"ai_memory": [[{"node": "AI Agent", "type": "ai_memory", "index": 0}]]}, "Call Search Console Tool": {"ai_tool": [[{"node": "AI Agent", "type": "ai_tool", "index": 0}]]}, "Set fields - Consruct API CALL": {"main": [[{"node": "Switch", "type": "main", "index": 0}]]}, "Search Console - Get Custom Insights": {"main": [[{"node": "Set fields - Create searchConsoleDataArray", "type": "main", "index": 0}]]}, "## Search Console - Get List of Properties": {"main": [[{"node": "Set fields - Create searchConsoleDataArray 2", "type": "main", "index": 0}]]}, "Set fields - Create searchConsoleDataArray": {"main": [[{"node": "Array aggregation - response to AI Agent", "type": "main", "index": 0}]]}, "Set fields - Create searchConsoleDataArray 2": {"main": [[{"node": "Array aggregation - response to AI Agent1", "type": "main", "index": 0}]]}}}