` tags where necessary).\n\n6. **Email Sending**:\n - The **Send Email** node sends the reviewed and formatted response back to the original sender.\n\n7. **Vector Database Integration**:\n - The **Qdrant Vector Store** node retrieves relevant information from a vector database (Qdrant) to assist in generating accurate responses. This is particularly useful for emails classified as \"Company info request\".\n - The **Embeddings OpenAI** node generates embeddings for the email content, which are used to query the vector database.\n\n8. **Document Vectorization**:\n - The workflow includes steps to create and refresh a Qdrant collection (**Create collection** and **Refresh collection** nodes).\n - Documents from Google Drive are downloaded (**Get folder** and **Download Files** nodes), processed into embeddings (**Embeddings OpenAI1** node), and stored in the Qdrant vector store (**Qdrant Vector Store1** node).\n\n---\n\n### **Set Up Steps**\n1. **Configure Email Trigger**:\n - Set up the **Email Trigger (IMAP)** node with the appropriate IMAP credentials to monitor the email inbox.\n\n2. **Set Up AI Models**:\n - Configure the **DeepSeek R1**, **OpenAI**, and **DeepSeek** nodes with the appropriate API credentials for text summarization, response generation, and review.\n\n3. **Set Up Email Classification**:\n - Define the categories in the **Email Classifier** node (e.g., \"Company info request\", \"Other\").\n - Ensure the **OpenAI 4-o-mini** node is configured to assist in classification.\n\n4. **Set Up Vector Database**:\n - Configure the **Qdrant Vector Store** and **Qdrant Vector Store1** nodes with the appropriate Qdrant API credentials and collection details.\n - Set up the **Embeddings OpenAI** and **Embeddings OpenAI1** nodes to generate embeddings for the email content and documents.\n\n5. **Set Up Document Processing**:\n - Configure the **Get folder** and **Download Files** nodes to access and download documents from Google Drive.\n - Use the **Token Splitter** and **Default Data Loader** nodes to process and split the documents into manageable chunks for vectorization.\n\n6. **Set Up Email Sending**:\n - Configure the **Send Email** node with the appropriate SMTP credentials to send responses.\n\n7. **Test the Workflow**:\n - Trigger the workflow manually using the **When clicking ‘Test workflow’** node to ensure all steps execute correctly.\n - Verify that emails are summarized, classified, and responded to accurately.\n\n8. **Activate the Workflow**:\n - Once tested, activate the workflow to automate the process of handling incoming emails.\n\n---\n\n### **Key Features**\n- **Automated Email Handling**: Automatically processes incoming emails, summarizes them, and generates professional responses.\n- **AI-Powered Classification**: Uses AI to classify emails into relevant categories for targeted responses.\n- **Vector Database Integration**: Retrieves relevant information from a vector database to enhance response accuracy.\n- **Document Vectorization**: Processes and stores documents from Google Drive in a vector database for quick retrieval.\n- **Professional Email Formatting**: Ensures responses are professionally formatted and concise.\n\n---\n\n\n### **Need help customizing?** \n[Contact me](mailto:info@n3w.it) for consulting and support or add me on [Linkedin](https://www.linkedin.com/in/davideboizza/). ",
"workflow": {
"id": "q8IFGLeOCGSfoWZu",
"meta": {
"instanceId": "a4bfc93e975ca233ac45ed7c9227d84cf5a2329310525917adaf3312e10d5462",
"templateCredsSetupCompleted": true
},
"name": "Email AI Auto-responder. Summerize and send email",
"tags": [],
"nodes": [
{
"id": "59885699-0f6c-4522-acff-9e28b2a07b82",
"name": "Email Trigger (IMAP)",
"type": "n8n-nodes-base.emailReadImap",
"position": [
-440,
-20
],
"parameters": {
"options": {}
},
"credentials": {
"imap": {
"id": "credential-id",
"name": "imap Credential"
}
},
"typeVersion": 2
},
{
"id": "b268ab9d-b2e3-46e6-b7ae-70aff0b5484d",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
-220,
-20
],
"parameters": {
"html": "={{ $json.textHtml }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "13c2d151-6f59-4e1f-a174-02d4d0bcaefd",
"name": "DeepSeek R1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-20,
160
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "deepseek/deepseek-r1:free",
"cachedResultName": "deepseek/deepseek-r1:free"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": "openAiApi Credential"
}
},
"typeVersion": 1.2
},
{
"id": "8149e40d-64e6-4fb9-aebc-2a2483961f07",
"name": "Send Email",
"type": "n8n-nodes-base.emailSend",
"position": [
500,
340
],
"parameters": {
"html": "={{ $json.text }}",
"options": {},
"subject": "=Re: {{ $('Email Trigger (IMAP)').item.json.subject }}",
"toEmail": "={{ $('Email Trigger (IMAP)').item.json.from }}",
"fromEmail": "={{ $('Email Trigger (IMAP)').item.json.to }}"
},
"credentials": {
"smtp": {
"id": "credential-id",
"name": "smtp Credential"
}
},
"typeVersion": 2.1
},
{
"id": "633f0ce9-04ff-4653-8bbc-7457ba0d18bd",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
-320,
600
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "company_knowladge_base",
"toolDescription": "Extracts information regarding the request made.",
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "=COLLECTION"
},
"includeDocumentMetadata": false
},
"credentials": {
"qdrantApi": {
"id": "credential-id",
"name": "qdrantApi Credential"
}
},
"typeVersion": 1
},
{
"id": "20daf5d3-dc9c-4fad-9f2f-98d86bc1660c",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-340,
760
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": "openAiApi Credential"
}
},
"typeVersion": 1.2
},
{
"id": "67699bca-4096-4259-bbd4-51a879539aca",
"name": "Email Classifier",
"type": "@n8n/n8n-nodes-langchain.textClassifier",
"position": [
360,
-20
],
"parameters": {
"options": {
"fallback": "other",
"multiClass": false,
"enableAutoFixing": true,
"systemPromptTemplate": "Please classify the text provided by the user into one of the following categories: {categories}, and use the provided formatting instructions below. Don't explain, and only output the json.\n"
},
"inputText": "=You must classify the following email::\n\n{{ $json.response.text }}",
"categories": {
"categories": [
{
"category": "Company info request",
"description": "Company info request"
}
]
}
},
"typeVersion": 1
},
{
"id": "9f7742e9-87d5-40b9-9129-0777d8a37933",
"name": "Email Summarization Chain",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
0,
-20
],
"parameters": {
"options": {
"binaryDataKey": "={{ $json.data }}",
"summarizationMethodAndPrompts": {
"values": {
"prompt": "=Write a concise summary of the following in max 100 words:\n\n\"{{ $json.data }}\"\n\nDo not enter the total number of words used.",
"combineMapPrompt": "=Write a concise summary of the following in max 100 words:\n\n\"{{ $json.data }}\"\n"
}
}
},
"operationMode": "nodeInputBinary"
},
"typeVersion": 2
},
{
"id": "e2d404c0-2aad-407d-b75e-5ef0c5105c0e",
"name": "Write email",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-440,
340
],
"parameters": {
"text": "=Write the text to reply to the following email:\n\n{{ $json.response.text }}",
"options": {
"systemMessage": "You are an expert at answering emails. You need to answer them professionally based on the information you have. This is a business email. Be concise and never exceed 100 words."
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "3786c2de-c5cb-4233-826e-7265f2bccbdb",
"name": "Review email",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
40,
340
],
"parameters": {
"text": "=Review at the following email:\n\n{{ $json.output }}",
"messages": {
"messageValues": [
{
"message": "=If you are an expert in reviewing emails before sending them. You need to review and structure them in such a way that you can send them. It must be in HTML format and you can insert (if you think it is appropriate) only HTML characters such as
, , ,
where necessary.\n\nNon superare le 100 parole."
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.5
},
{
"id": "baf60eba-5e7b-467f-b27e-1388a91622d0",
"name": "When clicking ‘Test workflow’",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-500,
-980
],
"parameters": {},
"typeVersion": 1
},
{
"id": "77e6160f-20a7-4a75-9fef-bc875b953a16",
"name": "Create collection",
"type": "n8n-nodes-base.httpRequest",
"position": [
-200,
-1120
],
"parameters": {
"url": "https://QDRANTURL/collections/COLLECTION",
"method": "POST",
"options": {},
"jsonBody": "{\n \"filter\": {}\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": "httpHeaderAuth Credential"
}
},
"typeVersion": 4.2
},
{
"id": "ab7764d1-531c-4281-8b89-015fb3f5e780",
"name": "Refresh collection",
"type": "n8n-nodes-base.httpRequest",
"position": [
-200,
-860
],
"parameters": {
"url": "https:/YOUR_AWS_SECRET_KEY_HERE/delete",
"method": "POST",
"options": {},
"jsonBody": "{\n \"filter\": {}\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "credential-id",
"name": "httpHeaderAuth Credential"
}
},
"typeVersion": 4.2
},
{
"id": "cd3eaa81-0f94-484b-b0c2-ecf0ca4541dc",
"name": "Get folder",
"type": "n8n-nodes-base.googleDrive",
"position": [
20,
-860
],
"parameters": {
"filter": {
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive",
"cachedResultUrl": "https://drive.google.com/drive/my-drive",
"cachedResultName": "My Drive"
},
"folderId": {
"__rl": true,
"mode": "id",
"value": "=test-whatsapp"
}
},
"options": {},
"resource": "fileFolder"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "credential-id",
"name": "googleDriveOAuth2Api Credential"
}
},
"typeVersion": 3
},
{
"id": "b39ecd2d-4d5b-4885-86a9-2cfe9f6074ef",
"name": "Download Files",
"type": "n8n-nodes-base.googleDrive",
"position": [
240,
-860
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.id }}"
},
"options": {
"googleFileConversion": {
"conversion": {
"docsToFormat": "text/plain"
}
}
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "credential-id",
"name": "googleDriveOAuth2Api Credential"
}
},
"typeVersion": 3
},
{
"id": "8171b8f2-998d-4d72-ac28-524daae4a2d7",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
620,
-660
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "ec6737ad-3fbe-4864-9df8-44f82d6f2c5c",
"name": "Token Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"position": [
600,
-500
],
"parameters": {
"chunkSize": 300,
"chunkOverlap": 30
},
"typeVersion": 1
},
{
"id": "57b6a4f3-e935-4058-bfdf-309d606c0ca9",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
-1180
],
"parameters": {
"color": 6,
"width": 880,
"height": 220,
"content": "# STEP 1\n\n## Create Qdrant Collection\nChange:\n- QDRANTURL\n- COLLECTION"
},
"typeVersion": 1
},
{
"id": "21e2326a-138d-46f3-a849-a80aa7917da9",
"name": "Qdrant Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
480,
-860
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "=COLLECTION"
}
},
"credentials": {
"qdrantApi": {
"id": "credential-id",
"name": "qdrantApi Credential"
}
},
"typeVersion": 1
},
{
"id": "0818fb6a-2adf-4725-90a4-11cdd7d14036",
"name": "Embeddings OpenAI1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
500,
-620
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": "openAiApi Credential"
}
},
"typeVersion": 1.1
},
{
"id": "8949d938-2743-45d6-b2ad-ce4ac139e0a3",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-220,
-920
],
"parameters": {
"color": 4,
"width": 620,
"height": 400,
"content": "# STEP 2\n\n\n\n\n\n\n\n\n\n\n\n\n## Documents vectorization with Qdrant and Google Drive\nChange:\n- QDRANTURL\n- COLLECTION"
},
"typeVersion": 1
},
{
"id": "36d384be-3e11-43b1-b8c3-f63df600a6a6",
"name": "Do nothing",
"type": "n8n-nodes-base.noOp",
"position": [
820,
0
],
"parameters": {},
"typeVersion": 1
},
{
"id": "386c27cb-6e69-4d96-a8ab-8cfd43e6b171",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-520,
580
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": "openAiApi Credential"
}
},
"typeVersion": 1.2
},
{
"id": "0bd17bef-e205-464e-9b36-dcda75254e06",
"name": "DeepSeek",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
40,
540
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "deepseek/deepseek-r1:free",
"cachedResultName": "deepseek/deepseek-r1:free"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": "openAiApi Credential"
}
},
"typeVersion": 1.2
},
{
"id": "3e68a65f-af29-432f-8159-4a599e8a0866",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-540,
-320
],
"parameters": {
"width": 1620,
"height": 240,
"content": "# STEP 3 - MAIN FLOW\n\n- Transform the email into Markdown format for optimal reading by the LLM model\n- Email Summarization through DeepSeek R1 (any model can be used)\n- I classify the email in such a way as to continue only with emails regarding general information about the company. In this way I can respond independently through the information obtained from the vector database\n- I create a chain where I entrust the review of the email to a high-performance model designed for this purpose\n- I send the response email\n\n\n"
},
"typeVersion": 1
},
{
"id": "3b6ae6aa-75a8-4038-bbc2-248ab533b3ab",
"name": "OpenAI 4-o-mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
360,
160
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": "openAiApi Credential"
}
},
"typeVersion": 1.2
}
],
"active": false,
"pinData": {
"Email Trigger (IMAP)": [
{
"json": {
"to": "info@n3witalia.com",
"date": "Wed, 5 Feb 2025 13:38:51 +0100",
"from": "n3w Italia
In particolare, avrei bisogno di sapere:
Gli orari di apertura del vostro negozio, inclusi eventuali giorni di chiusura o orari ridotti durante i festivi.
Se offrite servizi di assistenza tecnica per dispositivi elettronici e, in caso affermativo, quali tipologie di dispositivi supportate (es. smartphone, computer, tablet).
Se disponete di un catalogo prodotti aggiornato o un sito web dove posso consultare lâofferta disponibile.
Se effettuate consegne a domicilio o se è possibile prenotare prodotti online per il ritiro in negozio.
Se offrite sconti o promozioni per studenti, aziende o clienti abituali.
Se organizzate eventi o workshop legati alla tecnologia, come corsi di formazione o presentazioni di nuovi prodotti.
Inoltre, sarei interessato a sapere se il vostro negozio aderisce a programmi di riciclo di dispositivi elettronici o se offrite servizi di smaltimento ecologico per apparecchiature obsolete.
Se possibile, gradirei ricevere anche informazioni sui metodi di pagamento accettati (es. carte di credito, PayPal, finanziamenti) e se è possibile richiedere un preventivo personalizzato per acquisti di grandi dimensioni.
Resto a disposizione per eventuali chiarimenti o per fornire ulteriori dettagli sulle mie esigenze. Vi ringrazio in anticipo per il tempo dedicato alla mia richiesta e attendo con interesse una vostra risposta.
Cordiali saluti,