This workflow follows the Agent → OpenAI Embeddings recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "NovaCart_Monthly_Report_Agent_V2",
"nodes": [
{
"parameters": {
"jsCode": "// Compute previous calendar month (reporting period)\nconst now = new Date();\nconst firstOfThisMonth = new Date(now.getFullYear(), now.getMonth(), 1);\nconst lastOfPrevMonth = new Date(firstOfThisMonth.getTime() - 1);\n\nconst reportYear = lastOfPrevMonth.getFullYear();\nconst reportMonthIndex = lastOfPrevMonth.getMonth(); // 0-11\nconst reportMonth = reportMonthIndex + 1; // 1-12\n\nconst monthNames = [\n 'January','February','March','April','May','June',\n 'July','August','September','October','November','December'\n];\n\nconst reportMonthName = monthNames[reportMonthIndex];\n\nconst periodStart = new Date(reportYear, reportMonthIndex, 1);\nconst periodEnd = new Date(reportYear, reportMonthIndex + 1, 0);\n\nconst fmt = (d) => d.toISOString().slice(0, 10);\n\nreturn [{\n json: {\n generated_at: now.toISOString(),\n report_year: reportYear,\n report_month: reportMonth,\n report_month_name: reportMonthName,\n period_start: fmt(periodStart),\n period_end: fmt(periodEnd)\n }\n}];"
},
"id": "c0a8e653-b1f9-4f56-a035-34ea03764ef5",
"name": "Set Reporting Period",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
272,
400
]
},
{
"parameters": {
"jsCode": "// Build the monthly reporting request for the AI Agent\nconst meta = $json;\n\nconst chatInput = `Create the **Monthly Financial Standing Report** for NovaCart for **${meta.report_month_name} ${meta.report_year}** (period ${meta.period_start} to ${meta.period_end}).\\n\\n` +\n`Requirements:\\n` +\n`1) Use the Internal Finance vector store tool to pull internal performance (sales, units, revenue, margins, anomalies) for the month.\\n` +\n`2) Use the External Market Reports vector store tool to pull market trends, competitor moves, macro conditions, and any relevant category insights.\\n` +\n`3) Correlate internal performance with external conditions. Explicitly call out what likely drove results.\\n` +\n`4) Provide a clear narrative plus tables where appropriate.\\n` +\n`5) Output MUST be valid HTML (no Markdown, no code fences).\\n\\n` +\n`Focus on decision-useful insights for executives. If any key data is missing, state assumptions and data gaps clearly.`;\n\nconst sessionId = `monthly_finance_report_${meta.report_year}_${String(meta.report_month).padStart(2,'0')}`;\n\nreturn [{ json: { ...meta, sessionId, chatInput, text: chatInput } }];"
},
"id": "285d38d7-14e2-4ba7-8953-de2b7763c862",
"name": "Build Report Request",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
496,
400
]
},
{
"parameters": {
"options": {
"systemMessage": "You are a senior finance & strategy analyst writing for NovaCart executives.\n\nYou MUST:\n- Use BOTH tools at least once: (1) Internal Finance Vector Store Tool and (2) External Market Reports Vector Store Tool.\n- Ground all key claims in retrieved evidence.\n- If evidence is insufficient for a claim, say so explicitly.\n\nOutput requirements:\n- Return a SINGLE HTML string only (no Markdown, no code fences).\n- Use simple inline CSS for email readability.\n- Structure the report with these sections:\n 1) Title + reporting period\n 2) Executive Summary (3\u20136 bullets)\n 3) KPI Dashboard (table)\n 4) Performance Deep Dive (by product/category and any available dimensions)\n 5) Market Context (external trends)\n 6) Drivers & Correlations (internal vs external)\n 7) Risks, Opportunities, Recommendations (bullets)\n 8) Sources (list the retrieved sources with file_name and drive_url when available)\n\nWhen citing, include the source in parentheses, e.g. (Source: <file_name> <drive_url>)."
}
},
"id": "1528d2aa-ae39-4145-9d21-76404c11b125",
"name": "AI Finance Reporting Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 2.2,
"position": [
720,
400
]
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"id": "d2da0c4a-0454-4189-b6f6-cd852740b03d",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
608,
656
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "Use this tool to retrieve NovaCart INTERNAL product performance data (sales metrics, units, revenue, margins, anomalies, operational notes) for the requested month.",
"pineconeIndex": {
"__rl": true,
"value": "nova-cart-n8n",
"mode": "list",
"cachedResultName": "nova-cart-n8n"
},
"topK": 12,
"options": {
"pineconeNamespace": "int-finance-data"
}
},
"id": "365c13ea-2857-4b91-94f4-379cb6126cd6",
"name": "Pinecone Tool - Internal",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"typeVersion": 1.3,
"position": [
848,
640
],
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "Use this tool to retrieve insights from EXTERNAL market report PDFs (industry trends, competitor moves, macro signals, forecasts) relevant to NovaCart's performance.",
"pineconeIndex": {
"__rl": true,
"value": "nova-cart-n8n",
"mode": "list",
"cachedResultName": "nova-cart-n8n"
},
"topK": 12,
"options": {
"pineconeNamespace": "ext-market-reports"
}
},
"id": "765be56b-3d6e-456c-9be4-d1ff223c819d",
"name": "Pinecone Tool - External",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"typeVersion": 1.3,
"position": [
1136,
640
],
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Prepare email payload (compatible with n8n Code node v2)\n\n// 1) Pull the reporting period metadata from the earlier node\nconst metaItems = $items('Set Reporting Period');\nconst meta = (metaItems?.[0]?.json) ?? {};\n\n// 2) The AI Agent output is the input to THIS node\nconst agentOut = $input.first().json;\n\n// Try common output fields (Agent nodes vary by version/config)\nlet html =\n agentOut.output ??\n agentOut.text ??\n agentOut.response ??\n agentOut.answer ??\n agentOut.result ??\n agentOut;\n\n// Ensure it's a string\nif (typeof html !== 'string') {\n html = JSON.stringify(html, null, 2);\n}\n\n// Strip accidental Markdown code fences if the model wrapped HTML\nhtml = html.replace(/^```(?:html)?\\s*/i, '').replace(/\\s*```$/i, '');\n\n// If it doesn't look like HTML, wrap in <pre> so the email still renders legibly\nif (!/<[a-z][\\s\\S]*>/i.test(html)) {\n const escape = (s) => s\n .replace(/&/g, '&')\n .replace(/</g, '<')\n .replace(/>/g, '>');\n html = `<pre style=\"white-space: pre-wrap; font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, 'Liberation Mono', 'Courier New', monospace;\">${escape(html)}</pre>`;\n}\n\nconst month = meta.report_month_name ?? '';\nconst year = meta.report_year ?? '';\nconst subject = `NovaCart Monthly Financial Standing Report \u2014 ${month} ${year}`.trim();\n\nreturn [{\n json: {\n ...meta,\n report_subject: subject,\n report_html: html\n }\n}];"
},
"id": "9d274263-a903-4f21-bfd6-7e301f2ebde4",
"name": "Prepare Email",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1280,
400
]
},
{
"parameters": {
"content": "## W2 Assignment: Monthly Financial Standing Report (Email)\n\n**This workflow generates the report and emails it.**\n\n### Before activating:\n1) Run both ingestion workflows at least once (internal + external).\n2) In **Pinecone Tool - Internal** and **Pinecone Tool - External**, confirm the index is `novacart-finance-assignment` and namespaces are `internal` / `external`.\n3) In **Send Email**, set:\n - From Email\n - To Email(s)\n - SMTP credentials\n4) In **Schedule Trigger**, set it to run on the **1st of every month** (choose your timezone).\n\nThen activate the workflow.\n",
"height": 1104,
"width": 2676,
"color": 5
},
"id": "87f32c3e-e153-4fd3-8e78-68abacdd5acd",
"name": "Sticky Note (Setup)1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-576,
-64
],
"typeVersion": 1
},
{
"parameters": {
"rule": {
"interval": [
{
"field": "months",
"triggerAtHour": 12
}
]
}
},
"id": "4579927e-ab44-4cd7-8c5e-0c1a06d61553",
"name": "Schedule Trigger2",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
48,
400
]
},
{
"parameters": {
"model": "text-embedding-3-large",
"options": {
"dimensions": 1024
}
},
"id": "2064432e-7051-4840-920b-0dde6782179e",
"name": "Embeddings OpenAI2",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"typeVersion": 1.2,
"position": [
1072,
880
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"sendTo": "jattaaihq@gmail.com",
"subject": "={{ $json.report_subject }}",
"message": "={{ $json.report_html }}",
"options": {}
},
"type": "n8n-nodes-base.gmail",
"typeVersion": 2.2,
"position": [
1488,
400
],
"id": "d5539078-a74b-40ac-93b6-96e51bfcaf65",
"name": "Send a message",
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Set Reporting Period": {
"main": [
[
{
"node": "Build Report Request",
"type": "main",
"index": 0
}
]
]
},
"Build Report Request": {
"main": [
[
{
"node": "AI Finance Reporting Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Finance Reporting Agent": {
"main": [
[
{
"node": "Prepare Email",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Finance Reporting Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Pinecone Tool - Internal": {
"ai_tool": [
[
{
"node": "AI Finance Reporting Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Pinecone Tool - External": {
"ai_tool": [
[
{
"node": "AI Finance Reporting Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Prepare Email": {
"main": [
[
{
"node": "Send a message",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger2": {
"main": [
[
{
"node": "Set Reporting Period",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI2": {
"ai_embedding": [
[
{
"node": "Pinecone Tool - Internal",
"type": "ai_embedding",
"index": 0
},
{
"node": "Pinecone Tool - External",
"type": "ai_embedding",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate"
},
"versionId": "2bdf6ea5-5f1d-4e1c-a61f-0b4a1de047fc",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "gxyWMNNoPItkENbs",
"tags": []
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
gmailOAuth2openAiApipineconeApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
NovaCart_Monthly_Report_Agent_V2. Uses agent, lmChatOpenAi, vectorStorePinecone, embeddingsOpenAi. Scheduled trigger; 11 nodes.
Source: https://github.com/praveenjatta/novaCart-n8n-finance-agent/blob/main/NovaCart_Monthly_Report_Agent_V2.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
WooriFisa. Uses agent, httpRequest, documentDefaultDataLoader, vectorStorePinecone. Scheduled trigger; 86 nodes.
Agent, HTTP Request, Document Default Data Loader +14
This workflow automates patient communication for medical clinics using the WhatsApp Business API. It supports appointment booking, rescheduling, service inquiries, follow-ups, and document submission
Google Sheets, Data Table, Data Table Tool +12
WooriFisa 최종. Uses memoryMongoDbChat, agent, httpRequest, documentDefaultDataLoader. Scheduled trigger; 68 nodes.
Memory Mongo Db Chat, Agent, HTTP Request +14
Collects cybersecurity news from trusted RSS feeds and uses OpenAI’s Retrieval-Augmented Generation (RAG) capabilities with Pinecone to filter for content that is directly relevant to your organizatio
RSS Feed Read, OpenAI Chat, Agent +7
Email_sequencing_SDR. Uses gmail, lmChatOpenAi, googleSheets, agent. Scheduled trigger; 25 nodes.
Gmail, OpenAI Chat, Google Sheets +3