n8n-nodes-openai-compatible-chat-trigger 1.0.0

package/README.md

@@ -0,0 +1,99 @@
+# OpenAI-Compatible Chat Trigger & Tools for n8n
+
+A custom n8n community node package that lets you expose your n8n workflows as direct, OpenAI-compatible chatbot backends. Instead of exposing standard Webhook URLs and mapping custom endpoints, this plugin exposes standard OpenAI API endpoints (`/v1/chat/completions`, `/v1/completions`, `/v1/models`) natively, allowing you to connect n8n workflows directly to any external chatbot program or library that supports OpenAI-compatible APIs (such as LibreChat, Chatbox, etc.).
+
+---
+
+## Key Features
+
+1. **OpenAI-Compatible Chat Trigger Node:**
+   - Registers a wildcard path that catches POST requests for `/v1/chat/completions` and `/v1/completions`.
+   - Directly answers GET requests for `/v1/models` without executing the workflow, returning a custom mock models list.
+   - Built-in authorization support (Bearer API keys) that immediately responds with a `401 Unauthorized` block to clients on validation failure.
+   - Extracts prompt messages, historical chat messages, and the requested model name into easy-to-use variables (`message`, `messages`, `model`) for downstream nodes.
+
+2. **OpenAI Completions Response Node:**
+   - Automatically packages generated text from your workflow into the standard OpenAI Chat Completion or Text Completion JSON schemas.
+   - Exposes parameters to customize response model name, role, finish reason, and optional custom ID or created timestamp.
+   - Feeds back cleanly to the Chat Trigger node when set to "When Last Node Finishes".
+
+
+---
+
+## Installation
+
+### For Local Development & Testing
+
+1. Clone or download this repository.
+2. In the folder, compile the TypeScript code and copy assets:
+   ```bash
+   npm run build
+   ```
+3. Navigate to your local n8n data directory (typically `~/.n8n/` on Linux/macOS or `C:\Users\<Username>\.n8n\` on Windows).
+4. Create the nested directories if they do not exist:
+   ```bash
+   mkdir -p ~/.n8n/custom/node_modules/
+   ```
+5. Copy or symlink your package directory (`n8n-nodes-openai-compatible-chat-trigger`) into that folder:
+   ```bash
+   # On Linux/macOS
+   ln -s /path/to/n8n-nodes-openai-compatible-chat-trigger ~/.n8n/custom/node_modules/n8n-nodes-openai-compatible-chat-trigger
+   ```
+6. Restart your n8n server. The new nodes will be discoverable in the node selector.
+
+---
+
+## Node Configurations
+
+### 1. OpenAI-Compatible Chat Trigger
+
+- **Webhook Path Prefix** (`path`): The custom namespace prefix. For example, setting this to `my-bot` creates these active endpoints:
+  - `POST /webhook/my-bot/v1/chat/completions` (starts workflow)
+  - `POST /webhook/my-bot/v1/completions` (starts workflow)
+  - `GET /webhook/my-bot/v1/models` (immediate GET response list)
+- **Response Mode** (`responseMode`): Set to `When Last Node Finishes` (returns output of the final node) or `Using Respond to Webhook Node`.
+- **Authentication** (`authentication`): `None` or `Header (Bearer Token)`. If set to header authentication, provide an `API Key`.
+- **Mock Models** (`mockModels`): Comma-separated list of models returned from the `/v1/models` endpoint (e.g. `gpt-3.5-turbo, gpt-4o, my-n8n-agent`).
+
+### 2. OpenAI Completions Response
+
+- **Response Type** (`responseType`): Choose `Chat Completions` or `Text Completions`.
+- **Response Text** (`text`): The final text content to return to the caller (e.g. `{{ $json.text }}`).
+- **Model Name** (`model`): The model name value injected into the JSON metadata (e.g. `gpt-3.5-turbo`).
+- **Message Role** (`role`): Message role (e.g., `assistant`).
+- **Finish Reason** (`finishReason`): Standard OpenAI stop reasons (e.g., `stop`, `length`, `content_filter`).
+- **Additional Fields**: Optional custom ID and Unix epoch created timestamp overrides.
+
+
+---
+
+## API Testing Examples
+
+Ensure you use your **Test URL** when testing inside the n8n editor, and the **Production URL** when the workflow is published and activated.
+
+### 1. Get Models List
+
+```bash
+curl -X GET "http://localhost:5678/webhook/openai-compatible/v1/models" \
+     -H "Authorization: Bearer <your-api-key>"
+```
+
+### 2. Send Chat Completions Request
+
+```bash
+curl -X POST "http://localhost:5678/webhook/openai-compatible/v1/chat/completions" \
+     -H "Authorization: Bearer <your-api-key>" \
+     -H "Content-Type: application/json" \
+     -d '{
+       "model": "gpt-4o",
+       "messages": [
+         {"role": "user", "content": "Hello chatbot, how are you?"}
+       ]
+     }'
+```
+
+---
+
+## License
+
+This community node package is licensed under the [MIT License](LICENSE).

package/dist/icons/openai-compatible.dark.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#1A1F2C"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#E2E8F0" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#6366F1"/>
+  <circle cx="12" cy="11" r="1.5" fill="#22D3EE"/>
+  <circle cx="15" cy="11" r="1.5" fill="#34D399"/>
+</svg>

package/dist/icons/openai-compatible.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#F2F4F7"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#2D3748" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#4F46E5"/>
+  <circle cx="12" cy="11" r="1.5" fill="#06B6D4"/>
+  <circle cx="15" cy="11" r="1.5" fill="#10B981"/>
+</svg>

package/dist/nodes/OpenAiCompatible/OpenAiCompatibleResponse.node.d.ts

@@ -0,0 +1,5 @@
+import { INodeType, INodeTypeDescription, IExecuteFunctions, INodeExecutionData } from 'n8n-workflow';
+export declare class OpenAiCompatibleResponse implements INodeType {
+    description: INodeTypeDescription;
+    execute(this: IExecuteFunctions): Promise<INodeExecutionData[][]>;
+}

package/dist/nodes/OpenAiCompatible/OpenAiCompatibleResponse.node.js

@@ -0,0 +1,207 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OpenAiCompatibleResponse = void 0;
+const crypto_1 = require("crypto");
+class OpenAiCompatibleResponse {
+    description = {
+        displayName: 'OpenAI Completions Response',
+        name: 'openAiCompatibleResponse',
+        icon: {
+            light: 'file:icons/openai-compatible.svg',
+            dark: 'file:icons/openai-compatible.dark.svg',
+        },
+        group: ['transform'],
+        version: 1,
+        description: 'Formats response text into standard OpenAI-compatible completions format',
+        defaults: {
+            name: 'OpenAI Completions Response',
+        },
+        inputs: ['main'],
+        outputs: ['main'],
+        properties: [
+            {
+                displayName: 'Response Type',
+                name: 'responseType',
+                type: 'options',
+                options: [
+                    {
+                        name: 'Chat Completions (/v1/chat/completions)',
+                        value: 'chatCompletions',
+                    },
+                    {
+                        name: 'Text Completions (/v1/completions)',
+                        value: 'textCompletions',
+                    },
+                ],
+                default: 'chatCompletions',
+                description: 'The OpenAI-compatible format to use for the response',
+            },
+            {
+                displayName: 'Response Text',
+                name: 'text',
+                type: 'string',
+                typeOptions: {
+                    rows: 4,
+                },
+                default: '',
+                required: true,
+                description: 'The generated text message to send back to the chat program',
+            },
+            {
+                displayName: 'Model Name',
+                name: 'model',
+                type: 'string',
+                default: 'n8n-bot',
+                description: 'The model name to include in the OpenAI response JSON',
+            },
+            {
+                displayName: 'Message Role',
+                name: 'role',
+                type: 'options',
+                options: [
+                    {
+                        name: 'Assistant',
+                        value: 'assistant',
+                    },
+                    {
+                        name: 'System',
+                        value: 'system',
+                    },
+                    {
+                        name: 'User',
+                        value: 'user',
+                    },
+                ],
+                default: 'assistant',
+                displayOptions: {
+                    show: {
+                        responseType: ['chatCompletions'],
+                    },
+                },
+                description: 'The role of the message author',
+            },
+            {
+                displayName: 'Finish Reason',
+                name: 'finishReason',
+                type: 'options',
+                options: [
+                    {
+                        name: 'Stop',
+                        value: 'stop',
+                    },
+                    {
+                        name: 'Length',
+                        value: 'length',
+                    },
+                    {
+                        name: 'Content Filter',
+                        value: 'content_filter',
+                    },
+                ],
+                default: 'stop',
+                description: 'The reason the model stopped generating tokens',
+            },
+            {
+                displayName: 'Additional Fields',
+                name: 'additionalFields',
+                type: 'collection',
+                placeholder: 'Add Field',
+                default: {},
+                options: [
+                    {
+                        displayName: 'Custom ID',
+                        name: 'customId',
+                        type: 'string',
+                        default: '',
+                        description: 'Override the auto-generated response ID',
+                    },
+                    {
+                        displayName: 'Custom Created Timestamp',
+                        name: 'customCreated',
+                        type: 'number',
+                        default: 0,
+                        description: 'Override the auto-generated creation timestamp (Unix epoch in seconds)',
+                    },
+                ],
+            },
+        ],
+    };
+    async execute() {
+        const items = this.getInputData();
+        const returnData = [];
+        for (let i = 0; i < items.length; i++) {
+            try {
+                const responseType = this.getNodeParameter('responseType', i);
+                const text = this.getNodeParameter('text', i);
+                const model = this.getNodeParameter('model', i);
+                const role = this.getNodeParameter('role', i, 'assistant');
+                const finishReason = this.getNodeParameter('finishReason', i, 'stop');
+                const additionalFields = this.getNodeParameter('additionalFields', i, {});
+                const id = additionalFields.customId || (responseType === 'chatCompletions' ? `chatcmpl-${(0, crypto_1.randomUUID)()}` : `cmpl-${(0, crypto_1.randomUUID)()}`);
+                const created = additionalFields.customCreated || Math.floor(Date.now() / 1000);
+                let formattedResponse = {};
+                if (responseType === 'chatCompletions') {
+                    formattedResponse = {
+                        id,
+                        object: 'chat.completion',
+                        created,
+                        model,
+                        choices: [
+                            {
+                                index: 0,
+                                message: {
+                                    role,
+                                    content: text,
+                                },
+                                finish_reason: finishReason,
+                            },
+                        ],
+                        usage: {
+                            prompt_tokens: 0,
+                            completion_tokens: 0,
+                            total_tokens: 0,
+                        },
+                    };
+                }
+                else {
+                    formattedResponse = {
+                        id,
+                        object: 'text_completion',
+                        created,
+                        model,
+                        choices: [
+                            {
+                                text,
+                                index: 0,
+                                logprobs: null,
+                                finish_reason: finishReason,
+                            },
+                        ],
+                        usage: {
+                            prompt_tokens: 0,
+                            completion_tokens: 0,
+                            total_tokens: 0,
+                        },
+                    };
+                }
+                returnData.push({
+                    json: formattedResponse,
+                    pairedItem: { item: i },
+                });
+            }
+            catch (error) {
+                if (this.continueOnFail()) {
+                    returnData.push({
+                        json: { error: error.message },
+                        pairedItem: { item: i },
+                    });
+                }
+                else {
+                    throw error;
+                }
+            }
+        }
+        return [returnData];
+    }
+}
+exports.OpenAiCompatibleResponse = OpenAiCompatibleResponse;

package/dist/nodes/OpenAiCompatible/OpenAiCompatibleTrigger.node.d.ts

@@ -0,0 +1,5 @@
+import { INodeType, INodeTypeDescription, IWebhookFunctions, IWebhookResponseData } from 'n8n-workflow';
+export declare class OpenAiCompatibleTrigger implements INodeType {
+    description: INodeTypeDescription;
+    webhook(this: IWebhookFunctions): Promise<IWebhookResponseData>;
+}

package/dist/nodes/OpenAiCompatible/OpenAiCompatibleTrigger.node.js

@@ -0,0 +1,186 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OpenAiCompatibleTrigger = void 0;
+class OpenAiCompatibleTrigger {
+    description = {
+        displayName: 'OpenAI-Compatible Chat Trigger',
+        name: 'openAiCompatibleTrigger',
+        icon: {
+            light: 'file:icons/openai-compatible.svg',
+            dark: 'file:icons/openai-compatible.dark.svg',
+        },
+        group: ['trigger'],
+        version: 1,
+        description: 'Starts workflow on OpenAI-compatible API requests (e.g. /v1/chat/completions)',
+        defaults: {
+            name: 'OpenAI-Compatible Chat Trigger',
+        },
+        inputs: [],
+        outputs: ['main'],
+        webhooks: [
+            {
+                name: 'default',
+                httpMethod: 'POST',
+                responseMode: '={{$parameter["responseMode"]}}',
+                path: '={{$parameter["path"]}}/*',
+            },
+            {
+                name: 'setup',
+                httpMethod: 'GET',
+                responseMode: 'onReceived',
+                path: '={{$parameter["path"]}}/*',
+            },
+        ],
+        properties: [
+            {
+                displayName: 'Webhook Path Prefix',
+                name: 'path',
+                type: 'string',
+                default: 'openai-compatible',
+                placeholder: 'openai-compatible',
+                required: true,
+                description: 'The prefix for the webhook path. The endpoints /v1/chat/completions, /v1/completions, and /v1/models will be registered under this prefix.',
+            },
+            {
+                displayName: 'Response Mode',
+                name: 'responseMode',
+                type: 'options',
+                options: [
+                    {
+                        name: 'When Last Node Finishes',
+                        value: 'lastNode',
+                        description: 'Returns data of the last-executed node',
+                    },
+                    {
+                        name: 'Using Respond to Webhook Node',
+                        value: 'responseNode',
+                        description: 'Defines response in Respond to Webhook node',
+                    },
+                ],
+                default: 'lastNode',
+                description: 'How to respond to the HTTP request for completions',
+            },
+            {
+                displayName: 'Authentication',
+                name: 'authentication',
+                type: 'options',
+                options: [
+                    {
+                        name: 'None',
+                        value: 'none',
+                    },
+                    {
+                        name: 'Header (Bearer Token)',
+                        value: 'headerAuth',
+                    },
+                ],
+                default: 'none',
+                description: 'Whether to require authorization header',
+            },
+            {
+                displayName: 'API Key',
+                name: 'apiKey',
+                type: 'string',
+                typeOptions: {
+                    password: true,
+                },
+                default: '',
+                displayOptions: {
+                    show: {
+                        authentication: ['headerAuth'],
+                    },
+                },
+                required: true,
+                description: 'The Bearer API key that clients must provide in the Authorization header',
+            },
+            {
+                displayName: 'Mock Models',
+                name: 'mockModels',
+                type: 'string',
+                default: 'gpt-3.5-turbo, gpt-4o, n8n-bot',
+                description: 'Comma-separated list of models to return from the /v1/models endpoint',
+            },
+        ],
+    };
+    async webhook() {
+        const req = this.getRequestObject();
+        const url = req.originalUrl || req.url || '';
+        const method = req.method || 'POST';
+        // 1. Verify Authorization Header if required
+        const authentication = this.getNodeParameter('authentication', 'none');
+        if (authentication === 'headerAuth') {
+            const authHeader = req.headers['authorization'];
+            const expectedApiKey = this.getNodeParameter('apiKey', '');
+            if (!authHeader || authHeader !== `Bearer ${expectedApiKey}`) {
+                return {
+                    webhookResponse: {
+                        statusCode: 401,
+                        body: {
+                            error: {
+                                message: 'Unauthorized: Invalid API key',
+                                type: 'invalid_request_error',
+                                code: 'invalid_api_key',
+                            },
+                        },
+                    },
+                };
+            }
+        }
+        // 2. Handle /v1/models endpoint (GET)
+        if (method === 'GET' || url.endsWith('/v1/models') || url.endsWith('/models') || url.includes('/models')) {
+            const mockModelsStr = this.getNodeParameter('mockModels', 'gpt-3.5-turbo, gpt-4o, n8n-bot');
+            const modelsList = mockModelsStr.split(',').map((m) => m.trim()).filter((m) => m !== '');
+            const responseData = {
+                object: 'list',
+                data: modelsList.map((modelId) => ({
+                    id: modelId,
+                    object: 'model',
+                    created: Math.floor(Date.now() / 1000),
+                    owned_by: 'n8n',
+                })),
+            };
+            return {
+                webhookResponse: {
+                    body: responseData,
+                },
+            };
+        }
+        // 3. Process chat completions or completions (POST)
+        const body = this.getBodyData();
+        const query = this.getQueryData();
+        const headers = this.getHeaderData();
+        let messageContent = '';
+        let messagesArray = [];
+        let modelName = '';
+        let webhookType = 'chatCompletions';
+        const isCompletions = url.endsWith('/v1/completions') || url.endsWith('/completions');
+        if (isCompletions) {
+            messageContent = (body.prompt || '');
+            modelName = (body.model || '');
+            webhookType = 'completions';
+        }
+        else {
+            // default to chatCompletions
+            messagesArray = (body.messages || []);
+            if (messagesArray.length > 0) {
+                const lastMsg = messagesArray[messagesArray.length - 1];
+                messageContent = lastMsg.content || '';
+            }
+            modelName = (body.model || '');
+        }
+        return {
+            workflowData: [
+                this.helpers.returnJsonArray({
+                    message: messageContent,
+                    messages: messagesArray.length > 0 ? messagesArray : undefined,
+                    model: modelName || undefined,
+                    body: body,
+                    headers: headers,
+                    query: query,
+                    webhookType: webhookType,
+                }),
+            ],
+        };
+    }
+}
+exports.OpenAiCompatibleTrigger = OpenAiCompatibleTrigger;

package/dist/nodes/OpenAiCompatible/icons/openai-compatible.dark.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#1A1F2C"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#E2E8F0" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#6366F1"/>
+  <circle cx="12" cy="11" r="1.5" fill="#22D3EE"/>
+  <circle cx="15" cy="11" r="1.5" fill="#34D399"/>
+</svg>

package/dist/nodes/OpenAiCompatible/icons/openai-compatible.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#F2F4F7"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#2D3748" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#4F46E5"/>
+  <circle cx="12" cy="11" r="1.5" fill="#06B6D4"/>
+  <circle cx="15" cy="11" r="1.5" fill="#10B981"/>
+</svg>

package/gulpfile.js

@@ -0,0 +1,6 @@
+const gulp = require('gulp');
+
+gulp.task('copy-icons', function() {
+  gulp.src('icons/**/*.svg').pipe(gulp.dest('dist/icons'));
+  return gulp.src('nodes/**/*.svg').pipe(gulp.dest('dist/nodes'));
+});

package/icons/openai-compatible.dark.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#1A1F2C"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#E2E8F0" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#6366F1"/>
+  <circle cx="12" cy="11" r="1.5" fill="#22D3EE"/>
+  <circle cx="15" cy="11" r="1.5" fill="#34D399"/>
+</svg>

package/icons/openai-compatible.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#F2F4F7"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#2D3748" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#4F46E5"/>
+  <circle cx="12" cy="11" r="1.5" fill="#06B6D4"/>
+  <circle cx="15" cy="11" r="1.5" fill="#10B981"/>
+</svg>

package/index.ts

@@ -0,0 +1,7 @@
+import { OpenAiCompatibleTrigger } from './nodes/OpenAiCompatible/OpenAiCompatibleTrigger.node';
+import { OpenAiCompatibleResponse } from './nodes/OpenAiCompatible/OpenAiCompatibleResponse.node';
+
+export const nodes = [
+	OpenAiCompatibleTrigger,
+	OpenAiCompatibleResponse,
+];

package/nodes/OpenAiCompatible/OpenAiCompatibleResponse.node.ts

@@ -0,0 +1,215 @@
+import { randomUUID } from 'crypto';
+import {
+	INodeType,
+	INodeTypeDescription,
+	IExecuteFunctions,
+	INodeExecutionData,
+	IDataObject,
+} from 'n8n-workflow';
+
+export class OpenAiCompatibleResponse implements INodeType {
+	description: INodeTypeDescription = {
+		displayName: 'OpenAI Completions Response',
+		name: 'openAiCompatibleResponse',
+		icon: {
+			light: 'file:icons/openai-compatible.svg',
+			dark: 'file:icons/openai-compatible.dark.svg',
+		},
+		group: ['transform'],
+		version: 1,
+		description: 'Formats response text into standard OpenAI-compatible completions format',
+		defaults: {
+			name: 'OpenAI Completions Response',
+		},
+		inputs: ['main'],
+		outputs: ['main'],
+		properties: [
+			{
+				displayName: 'Response Type',
+				name: 'responseType',
+				type: 'options',
+				options: [
+					{
+						name: 'Chat Completions (/v1/chat/completions)',
+						value: 'chatCompletions',
+					},
+					{
+						name: 'Text Completions (/v1/completions)',
+						value: 'textCompletions',
+					},
+				],
+				default: 'chatCompletions',
+				description: 'The OpenAI-compatible format to use for the response',
+			},
+			{
+				displayName: 'Response Text',
+				name: 'text',
+				type: 'string',
+				typeOptions: {
+					rows: 4,
+				},
+				default: '',
+				required: true,
+				description: 'The generated text message to send back to the chat program',
+			},
+			{
+				displayName: 'Model Name',
+				name: 'model',
+				type: 'string',
+				default: 'n8n-bot',
+				description: 'The model name to include in the OpenAI response JSON',
+			},
+			{
+				displayName: 'Message Role',
+				name: 'role',
+				type: 'options',
+				options: [
+					{
+						name: 'Assistant',
+						value: 'assistant',
+					},
+					{
+						name: 'System',
+						value: 'system',
+					},
+					{
+						name: 'User',
+						value: 'user',
+					},
+				],
+				default: 'assistant',
+				displayOptions: {
+					show: {
+						responseType: ['chatCompletions'],
+					},
+				},
+				description: 'The role of the message author',
+			},
+			{
+				displayName: 'Finish Reason',
+				name: 'finishReason',
+				type: 'options',
+				options: [
+					{
+						name: 'Stop',
+						value: 'stop',
+					},
+					{
+						name: 'Length',
+						value: 'length',
+					},
+					{
+						name: 'Content Filter',
+						value: 'content_filter',
+					},
+				],
+				default: 'stop',
+				description: 'The reason the model stopped generating tokens',
+			},
+			{
+				displayName: 'Additional Fields',
+				name: 'additionalFields',
+				type: 'collection',
+				placeholder: 'Add Field',
+				default: {},
+				options: [
+					{
+						displayName: 'Custom ID',
+						name: 'customId',
+						type: 'string',
+						default: '',
+						description: 'Override the auto-generated response ID',
+					},
+					{
+						displayName: 'Custom Created Timestamp',
+						name: 'customCreated',
+						type: 'number',
+						default: 0,
+						description: 'Override the auto-generated creation timestamp (Unix epoch in seconds)',
+					},
+				],
+			},
+		],
+	};
+
+	async execute(this: IExecuteFunctions): Promise<INodeExecutionData[][]> {
+		const items = this.getInputData();
+		const returnData: INodeExecutionData[] = [];
+
+		for (let i = 0; i < items.length; i++) {
+			try {
+				const responseType = this.getNodeParameter('responseType', i) as string;
+				const text = this.getNodeParameter('text', i) as string;
+				const model = this.getNodeParameter('model', i) as string;
+				const role = this.getNodeParameter('role', i, 'assistant') as string;
+				const finishReason = this.getNodeParameter('finishReason', i, 'stop') as string;
+				const additionalFields = this.getNodeParameter('additionalFields', i, {}) as IDataObject;
+
+				const id = (additionalFields.customId as string) || (responseType === 'chatCompletions' ? `chatcmpl-${randomUUID()}` : `cmpl-${randomUUID()}`);
+				const created = (additionalFields.customCreated as number) || Math.floor(Date.now() / 1000);
+
+				let formattedResponse: IDataObject = {};
+
+				if (responseType === 'chatCompletions') {
+					formattedResponse = {
+						id,
+						object: 'chat.completion',
+						created,
+						model,
+						choices: [
+							{
+								index: 0,
+								message: {
+									role,
+									content: text,
+								},
+								finish_reason: finishReason,
+							},
+						],
+						usage: {
+							prompt_tokens: 0,
+							completion_tokens: 0,
+							total_tokens: 0,
+						},
+					};
+				} else {
+					formattedResponse = {
+						id,
+						object: 'text_completion',
+						created,
+						model,
+						choices: [
+							{
+								text,
+								index: 0,
+								logprobs: null,
+								finish_reason: finishReason,
+							},
+						],
+						usage: {
+							prompt_tokens: 0,
+							completion_tokens: 0,
+							total_tokens: 0,
+						},
+					};
+				}
+
+				returnData.push({
+					json: formattedResponse,
+					pairedItem: { item: i },
+				});
+			} catch (error) {
+				if (this.continueOnFail()) {
+					returnData.push({
+						json: { error: (error as any).message },
+						pairedItem: { item: i },
+					});
+				} else {
+					throw error;
+				}
+			}
+		}
+
+		return [returnData];
+	}
+}

package/nodes/OpenAiCompatible/OpenAiCompatibleTrigger.node.ts

@@ -0,0 +1,198 @@
+import {
+	INodeType,
+	INodeTypeDescription,
+	IWebhookFunctions,
+	IWebhookResponseData,
+	IDataObject,
+} from 'n8n-workflow';
+
+export class OpenAiCompatibleTrigger implements INodeType {
+	description: INodeTypeDescription = {
+		displayName: 'OpenAI-Compatible Chat Trigger',
+		name: 'openAiCompatibleTrigger',
+		icon: {
+			light: 'file:icons/openai-compatible.svg',
+			dark: 'file:icons/openai-compatible.dark.svg',
+		},
+		group: ['trigger'],
+		version: 1,
+		description: 'Starts workflow on OpenAI-compatible API requests (e.g. /v1/chat/completions)',
+		defaults: {
+			name: 'OpenAI-Compatible Chat Trigger',
+		},
+		inputs: [],
+		outputs: ['main'],
+		webhooks: [
+			{
+				name: 'default',
+				httpMethod: 'POST',
+				responseMode: '={{$parameter["responseMode"]}}',
+				path: '={{$parameter["path"]}}/*',
+			},
+			{
+				name: 'setup',
+				httpMethod: 'GET',
+				responseMode: 'onReceived',
+				path: '={{$parameter["path"]}}/*',
+			},
+		],
+		properties: [
+			{
+				displayName: 'Webhook Path Prefix',
+				name: 'path',
+				type: 'string',
+				default: 'openai-compatible',
+				placeholder: 'openai-compatible',
+				required: true,
+				description: 'The prefix for the webhook path. The endpoints /v1/chat/completions, /v1/completions, and /v1/models will be registered under this prefix.',
+			},
+			{
+				displayName: 'Response Mode',
+				name: 'responseMode',
+				type: 'options',
+				options: [
+					{
+						name: 'When Last Node Finishes',
+						value: 'lastNode',
+						description: 'Returns data of the last-executed node',
+					},
+					{
+						name: 'Using Respond to Webhook Node',
+						value: 'responseNode',
+						description: 'Defines response in Respond to Webhook node',
+					},
+				],
+				default: 'lastNode',
+				description: 'How to respond to the HTTP request for completions',
+			},
+			{
+				displayName: 'Authentication',
+				name: 'authentication',
+				type: 'options',
+				options: [
+					{
+						name: 'None',
+						value: 'none',
+					},
+					{
+						name: 'Header (Bearer Token)',
+						value: 'headerAuth',
+					},
+				],
+				default: 'none',
+				description: 'Whether to require authorization header',
+			},
+			{
+				displayName: 'API Key',
+				name: 'apiKey',
+				type: 'string',
+				typeOptions: {
+					password: true,
+				},
+				default: '',
+				displayOptions: {
+					show: {
+						authentication: ['headerAuth'],
+					},
+				},
+				required: true,
+				description: 'The Bearer API key that clients must provide in the Authorization header',
+			},
+			{
+				displayName: 'Mock Models',
+				name: 'mockModels',
+				type: 'string',
+				default: 'gpt-3.5-turbo, gpt-4o, n8n-bot',
+				description: 'Comma-separated list of models to return from the /v1/models endpoint',
+			},
+		],
+	};
+
+	async webhook(this: IWebhookFunctions): Promise<IWebhookResponseData> {
+		const req = this.getRequestObject();
+		const url = req.originalUrl || req.url || '';
+		const method = req.method || 'POST';
+
+		// 1. Verify Authorization Header if required
+		const authentication = this.getNodeParameter('authentication', 'none') as string;
+		if (authentication === 'headerAuth') {
+			const authHeader = req.headers['authorization'];
+			const expectedApiKey = this.getNodeParameter('apiKey', '') as string;
+			if (!authHeader || authHeader !== `Bearer ${expectedApiKey}`) {
+				return {
+					webhookResponse: {
+						statusCode: 401,
+						body: {
+							error: {
+								message: 'Unauthorized: Invalid API key',
+								type: 'invalid_request_error',
+								code: 'invalid_api_key',
+							},
+						},
+					},
+				};
+			}
+		}
+
+		// 2. Handle /v1/models endpoint (GET)
+		if (method === 'GET' || url.endsWith('/v1/models') || url.endsWith('/models') || url.includes('/models')) {
+			const mockModelsStr = this.getNodeParameter('mockModels', 'gpt-3.5-turbo, gpt-4o, n8n-bot') as string;
+			const modelsList = mockModelsStr.split(',').map((m) => m.trim()).filter((m) => m !== '');
+			const responseData = {
+				object: 'list',
+				data: modelsList.map((modelId) => ({
+					id: modelId,
+					object: 'model',
+					created: Math.floor(Date.now() / 1000),
+					owned_by: 'n8n',
+				})),
+			};
+			return {
+				webhookResponse: {
+					body: responseData,
+				},
+			};
+		}
+
+		// 3. Process chat completions or completions (POST)
+		const body = this.getBodyData() as IDataObject;
+		const query = this.getQueryData() as IDataObject;
+		const headers = this.getHeaderData() as IDataObject;
+
+		let messageContent = '';
+		let messagesArray: any[] = [];
+		let modelName = '';
+		let webhookType = 'chatCompletions';
+
+		const isCompletions = url.endsWith('/v1/completions') || url.endsWith('/completions');
+
+		if (isCompletions) {
+			messageContent = (body.prompt || '') as string;
+			modelName = (body.model || '') as string;
+			webhookType = 'completions';
+		} else {
+			// default to chatCompletions
+			messagesArray = (body.messages || []) as any[];
+			if (messagesArray.length > 0) {
+				const lastMsg = messagesArray[messagesArray.length - 1];
+				messageContent = lastMsg.content || '';
+			}
+			modelName = (body.model || '') as string;
+		}
+
+		return {
+			workflowData: [
+				this.helpers.returnJsonArray({
+					message: messageContent,
+					messages: messagesArray.length > 0 ? messagesArray : undefined,
+					model: modelName || undefined,
+					body: body,
+					headers: headers,
+					query: query,
+					webhookType: webhookType,
+				}),
+			],
+		};
+
+	}
+}

package/nodes/OpenAiCompatible/icons/openai-compatible.dark.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#1A1F2C"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#E2E8F0" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#6366F1"/>
+  <circle cx="12" cy="11" r="1.5" fill="#22D3EE"/>
+  <circle cx="15" cy="11" r="1.5" fill="#34D399"/>
+</svg>

package/nodes/OpenAiCompatible/icons/openai-compatible.svg

@@ -0,0 +1,7 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="24" height="24">
+  <rect width="24" height="24" rx="6" fill="#F2F4F7"/>
+  <path d="M12 4C7.58 4 4 7.13 4 11c0 2.2 1.15 4.18 3 5.46V19l2.7-1.62c.73.17 1.49.26 2.3.26 4.42 0 8-3.13 8-7s-3.58-7-8-7z" fill="none" stroke="#2D3748" stroke-width="2" stroke-linejoin="round"/>
+  <circle cx="9" cy="11" r="1.5" fill="#4F46E5"/>
+  <circle cx="12" cy="11" r="1.5" fill="#06B6D4"/>
+  <circle cx="15" cy="11" r="1.5" fill="#10B981"/>
+</svg>

package/package.json

@@ -0,0 +1,33 @@
+{
+  "name": "n8n-nodes-openai-compatible-chat-trigger",
+  "version": "1.0.0",
+  "description": "OpenAI-compatible chat trigger and helper nodes for n8n.",
+  "main": "dist/index.js",
+  "scripts": {
+    "build": "tsc && gulp copy-icons",
+    "prepublishOnly": "npm run build"
+  },
+  "keywords": [
+    "n8n-community-node-package"
+  ],
+  "author": "Dan Even Segler",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/DanEvenSegler/n8n-nodes-openai-compatible-chat-trigger.git"
+  },
+  "n8n": {
+    "n8nNodesApiVersion": 1,
+    "nodes": [
+      "dist/nodes/OpenAiCompatible/OpenAiCompatibleTrigger.node.js",
+      "dist/nodes/OpenAiCompatible/OpenAiCompatibleResponse.node.js"
+    ]
+  },
+  "devDependencies": {
+    "@types/node": "^20.11.0",
+    "gulp": "^5.0.0",
+    "n8n-workflow": "^1.36.0",
+    "rimraf": "^5.0.5",
+    "typescript": "^5.3.3"
+  }
+}

package/tsconfig.json

@@ -0,0 +1,22 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "commonjs",
+    "lib": ["es2022"],
+    "declaration": true,
+    "outDir": "./dist",
+    "rootDir": "./",
+    "strict": true,
+    "esModuleInterop": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "moduleResolution": "node"
+  },
+  "include": [
+    "nodes/**/*"
+  ],
+  "exclude": [
+    "node_modules",
+    "dist"
+  ]
+}