### README Style Guide Table Format

Source: https://github.com/enescingoz/awesome-n8n-templates/blob/main/CONTRIBUTING.md

This table defines the expected format for columns in the README.md when listing templates. Adhere to these guidelines for consistency.

```markdown
| Column | Format |
|--------|--------|
| Title | Full template name as it appears in n8n |
| Description | 1-2 sentences explaining what the template does |
| Department | The business function (e.g., Marketing, Support, Engineering, HR, Ops) |
| Link | Relative path to the JSON file in the repository |
```

--------------------------------

### Control Docker Services via n8n Webhook

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

Use cURL commands to interact with n8n webhooks for starting or stopping Docker services. Ensure correct authentication and service names are used. Invalid actions will result in an error.

```bash
curl -X POST \
  -u "username:password" \
  https://your-n8n-domain/webhook/docker/start/nextcloud
```

```bash
curl -X POST \
  -u "username:password" \
  https://your-n8n-domain/webhook/docker/stop/nextcloud
```

```bash
curl -X POST -u "username:password" \
  https://your-n8n-domain/webhook/docker/restart/nextcloud
```

--------------------------------

### WhatsApp Chatbot Webhook Verification (GET)

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This node handles the GET request for webhook verification by echoing the `hub.challenge` parameter. It's part of the setup for a WhatsApp Business API chatbot.

```json
{
  "name": "Respond to Webhook",
  "type": "n8n-nodes-base.respondToWebhook",
  "parameters": {
    "respondWith": "text",
    "responseBody": "={{ $json.query['hub.challenge'] }}"
  }
}
```

--------------------------------

### Telegram AI Chatbot with Image Generation

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This n8n workflow creates a Telegram bot that supports free-form chat, a start message, and image generation via DALL-E. The Settings node configures model parameters and the system prompt, including language detection and response style. The image generation node uses the OpenAI resource for creating images.

```json
{
  "name": "Settings",
  "type": "n8n-nodes-base.set",
  "parameters": {
    "values": {
      "number": [
        { "name": "model_temperature", "value": 0.8 },
        { "name": "token_length", "value": 500 }
      ],
      "string": [
        {
          "name": "system_command",
          "value": "You are a friendly chatbot. User name is {{ $json?.message?.from?.first_name }}. Detect the user's language and reply in the same language. Include suitable emojis."
        },
        {
          "name": "bot_typing",
          "value": "={{ $json?.message?.text.startsWith('/image') ? 'upload_photo' : 'typing' }}"
        }
      ]
    }
  }
}
```

```json
{
  "name": "Create an image",
  "type": "n8n-nodes-base.openAi",
  "parameters": {
    "resource": "image",
    "prompt": "={{ $json.message.text.split(' ').slice(1).join(' ') }}",
    "options": { "n": 1, "size": "512x512" },
    "responseFormat": "imageUrl"
  }
}
```

--------------------------------

### Importing n8n Templates via CLI and API

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

Demonstrates how to download an n8n template JSON file and import it into an n8n instance using the command-line interface or the REST API.

```bash
# Download a template from the repository
curl -LO "https://raw.githubusercontent.com/enescingoz/awesome-n8n-templates/main/devops/linux-update-via-webhook.json"

# Import via n8n CLI (self-hosted)
n8n import:workflow --input=linux-update-via-webhook.json

# Or via the n8n REST API
curl -X POST http://localhost:5678/api/v1/workflows \
  -H "Content-Type: application/json" \
  -H "X-N8N-API-KEY: your-api-key" \
  -d @linux-update-via-webhook.json

# Expected response
# {"id":"XGBwtopjOPIN0oNt","name":"Update Server","active":true,...}
```

--------------------------------

### Contributing a New Template: Git Commands

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This section provides bash commands for contributing a new n8n template. It covers forking the repository, cloning locally, exporting the workflow, adding it to the correct category, and committing changes.

```bash
# 1. Fork the repository and clone locally
git clone https://github.com/your-username/awesome-n8n-templates.git
cd awesome-n8n-templates

# 2. Export your workflow from n8n (UI: Workflow menu → Download)
#    Place the JSON in the correct category folder
cp ~/Downloads/my-workflow.json Gmail_and_Email_Automation/

# 3. Add a row to README.md in the appropriate category table
# Format:
# | Template Title | Brief 1-2 sentence description. | Department | [Link to Template](Category/File%20Name.json) |

# 4. Validate the JSON is well-formed
python3 -c "import json,sys; json.load(open('Gmail_and_Email_Automation/my-workflow.json'))" \
  && echo "JSON valid" || echo "JSON invalid"

# 5. Commit and open a pull request
git add Gmail_and_Email_Automation/my-workflow.json README.md
git commit -m "Add: AI-powered Gmail auto-responder workflow"
git push origin main
# Then open a PR at https://github.com/enescingoz/awesome-n8n-templates/pulls
```

--------------------------------

### Add Template Row to README

Source: https://github.com/enescingoz/awesome-n8n-templates/blob/main/CONTRIBUTING.md

When adding a new template, update the category table in README.md with this row format. Ensure the link points to the correct JSON file.

```markdown
| Template Title | Brief description of what it does. | Department | [Link to Template](Category_Folder/Template%20Name.json) |
```

--------------------------------

### RAG Chatbot Retrieval and Chat Pipeline

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This configuration outlines the retrieval and chat pipeline for a RAG chatbot. It uses an AI chat trigger, an AI agent with a language model (gpt-4o-mini), a Qdrant retriever for semantic search, and window buffer memory.

```json
// Retrieval + chat pipeline:
// [Chat Trigger] → [AI Agent]
//   ↓ ai_languageModel: lmChatOpenAi (gpt-4o-mini)
//   ↓ ai_tool: Qdrant Retriever (semantic search over movie embeddings)
//   ↓ ai_memory: Window Buffer Memory
// Output: "Based on your interest in sci-fi thrillers, I recommend 'Interstellar' (2014) — a mind-bending journey through space and time directed by Christopher Nolan."
```

--------------------------------

### AI Agent for PostgreSQL Database Queries

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This AI agent interacts with a PostgreSQL database, using GPT-4o-mini and specialized tools for schema introspection and SQL execution. It's prompted to always schema-prefix table names in queries.

```json
{
  "name": "AI Agent",
  "type": "@n8n/n8n-nodes-langchain.agent",
  "parameters": {
    "agent": "openAiFunctionsAgent",
    "options": {
      "systemMessage": "You are a DB assistant. Run queries aligned with user requests.\nMake sure every table has schema prefix in SQL queries (get schema from 'Get DB Schema and Tables List' tool)."
    }
  }
}
```

```json
{
  "name": "Execute SQL Query",
  "type": "n8n-nodes-base.postgresTool",
  "parameters": {
    "query": "{{ $fromAI(\"sql_query\", \"SQL Query\") }}",
    "operation": "executeQuery",
    "toolDescription": "Get all data from Postgres. Always prefix tables with correct schema."
  }
}
```

```json
{
  "name": "Get DB Schema and Tables List",
  "type": "n8n-nodes-base.postgresTool",
  "parameters": {
    "query": "SELECT table_schema, table_name FROM information_schema.tables WHERE table_type = 'BASE TABLE' AND table_schema NOT IN ('pg_catalog','information_schema') ORDER BY table_schema, table_name;",
    "toolDescription": "Get list of all tables with their schema in the database"
  }
}
```

--------------------------------

### AI Agent Chat with Web Search

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This AI agent uses GPT-4o-mini for language processing, SerpAPI for web searches, and a rolling window buffer for conversation memory. It's designed to be triggered by chat messages.

```json
{
  "name": "AI Agent",
  "type": "@n8n/n8n-nodes-langchain.agent",
  "parameters": { "options": {} },
  "typeVersion": 1.6
}
```

```json
{
  "connections": {
    "OpenAI Chat Model":  { "ai_languageModel": [[{"node": "AI Agent", "type": "ai_languageModel", "index": 0}]] },
    "Window Buffer Memory": { "ai_memory":       [[{"node": "AI Agent", "type": "ai_memory",        "index": 0}]] },
    "SerpAPI":            { "ai_tool":           [[{"node": "AI Agent", "type": "ai_tool",           "index": 0}]] },
    "When chat message received": { "main":       [[{"node": "AI Agent", "type": "main",             "index": 0}]] }
  }
}
```

--------------------------------

### AI Label Assignment for Incoming Gmail Messages

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This n8n workflow polls Gmail, extracts message content, uses GPT-4 via LangChain to assign labels, and applies them to the email. The LLM chain node configures the prompt and AI model, while the structured output parser enforces valid label names.

```json
{
  "name": "Assign labels for message",
  "type": "@n8n/n8n-nodes-langchain.chainLlm",
  "parameters": {
    "prompt": "={{ $json.text }}",
    "messages": {
      "messageValues": [{
        "message": "Categorize the email using these labels:\nPartnership - sponsored/cooperation emails\nInquiry - questions about products/services\nNotification - emails that don't require a response\nReturn ONLY label names as JSON. One email may have multiple labels."
      }]
    }
  }
}
```

```json
{
  "name": "JSON Parser",
  "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
  "parameters": {
    "jsonSchema": "{\"type\":\"object\",\"properties\":{\"labels\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"enum\":[\"Inquiry\",\"Partnership\",\"Notification\"]}}}}"
  }
}
```

--------------------------------

### Trigger Linux System Update via Webhook

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

Triggers a system update on a remote Debian-based server via SSH using an authenticated HTTP POST request. Requires httpBasicAuth and sshPassword credentials in n8n.

```bash
# Trigger a system update on the remote server
curl -X POST \
  -u "username:password" \
  https://your-n8n-domain/webhook/update

# Expected response (stdout from the server):
# Hit:1 http://archive.ubuntu.com/ubuntu jammy InRelease
# ...
# 0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.

# Workflow node chain:
# [Webhook (POST /update, basicAuth)]
#   → [SSH: sudo apt update && sudo apt upgrade -y]
#   → [Respond to Webhook: $json.stdout]
```

--------------------------------

### WhatsApp Chatbot AI Agent Configuration

Source: https://context7.com/enescingoz/awesome-n8n-templates/llms.txt

This node configures the AI Agent for a WhatsApp chatbot. It extracts user messages from the Meta webhook payload and uses a LangChain conversational agent with a system prompt and vector store retriever.

```json
{
  "name": "AI Agent",
  "type": "@n8n/n8n-nodes-langchain.agent",
  "parameters": {
    "agent": "conversationalAgent",
    "text": "={{ $('Respond').item.json.body.entry[0].changes[0].value.messages[0].text.body }}",
    "options": {
      "systemMessage": "You are an AI-powered assistant for an electronics store. Use the provided knowledge base to answer questions with precision and professionalism..."
    }
  }
}
```