### LM Studio Setup Steps

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/🚀 Local Multi-LLM Testing & Performance Tracker.txt

A guide to setting up LM Studio for LLM interactions. Covers installation, updating the base URL, configuring LLM models, and preparing a Google Sheet for results.

```text
## 🏗️Setup Steps
1. **Download and Install LM Studio**: Ensure LM Studio is correctly installed on your machine.
2. **Update the Base URL**: Replace the base URL with the IP address of your LLM instance. Ensure the connection is established.
3. **Configure LLM Settings**: Verify that your LLM models are properly set up and configured in LM Studio.
4. **Create a Google Sheet**: Set up a Google Sheet with the necessary headers (Prompt, Time Sent, Time Received, etc.) to track your testing results.

```

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

### Process Install Node Logic

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Other_Integrations_and_Use_Cases/Bitrix24 Chatbot Application Workflow example with Webhook Integration.txt

Handles the installation of a bot, gathering necessary information such as webhook URLs and authentication credentials. It then formats this data for bot registration.

```javascript
// Process Install Node
const items = $input.all();
const item = items[0];

// Get the webhook URL from input
const handlerBackUrl = item.json.webhookUrl;

// Get auth data directly from item.json
const auth = {
 access_token: item.json.access_token,
 application_token: item.json.application_token,
 domain: item.json.domain
};

return {
 json: {
 handler_back_url: handlerBackUrl,
 CODE: 'LocalExampleBot',
 TYPE: 'B',
 EVENT_MESSAGE_ADD: handlerBackUrl,
 EVENT_WELCOME_MESSAGE: handlerBackUrl,
 EVENT_BOT_DELETE: handlerBackUrl,
 PROPERTIES: {
 NAME: 'Bot',
 LAST_NAME: 'Example',
 COLOR: 'AQUA',
 EMAIL: 'no@example.com',
 PERSONAL_BIRTHDAY: '2020-07-18',
 WORK_POSITION: 'Report on affairs',
 PERSONAL_GENDER: 'M'
 },
 // Use the auth data from item.json
 AUTH: auth.access_token,
 CLIENT_ID: auth.application_token,
 DOMAIN: auth.domain
 }
};
```

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

### Workflow Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Database_and_Storage/Chat with Postgresql Database.txt

These are setup instructions for the n8n workflow. They guide the user on how to add credentials for PostgreSQL and OpenAI, start chatting with the database, and activate the workflow for public access.

```javascript
content: "### 👨‍🎤 Setup\n1. Add your **postgresql** and **OpenAI** credentials.\n2. Click **Chat** button and start asking questions to your database.\n3. Activate the workflow and you can make the chat publicly available."
```

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

### Sticky Note: ChatGPT Example 2

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/OpenAI examples_ ChatGPT, DALLE-2, Whisper-1 – 5-in-1.txt

Describes ChatGPT Example 2, focusing on using system content for general instructions. It highlights the manual setup of both system and user content for controlling the AI's behavior.

```json
{
  "id": "4605be68-4c57-404f-8624-e095c8e86ff9",
  "name": "Sticky Note4",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    900,
    620
  ],
  "parameters": {
    "width": 742.9723747088658,
    "height": 288.18470714667706,
    "content": "## ChatGPT example 2 \n### Use system content to provide general instruction\n### Manual setup of system and user content"
  },
  "typeVersion": 1
}
```

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

### Workflow Overview and Setup

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Spot Workplace Discrimination Patterns with AI.txt

This section provides a high-level overview of how the workflow operates and guides users through the initial setup process. It includes instructions for replacing credentials and selecting target companies.

```n8n-nodes-base.stickyNote
{
  "content": "## How this workflow works\n1. Replace ScrapingBee and OpenAI credentials\n2. Replace company_name with company of choice (workflow performs better with larger US-based organizations)\n3. Preview QuickChart data visualizations and AI data analysis"
}
```

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

### YouTube Integration for Setup Video

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/AI Agent To Chat With Files In Supabase Storage.txt

Includes a markdown link to a YouTube setup video, likely for guiding users through the workflow's implementation.

```markdown
### ... or watch set up video [10 min]
[![Youtube Thumbnail](https://res.cloudinary.com/de9jgixzm/image/upload/v1739773273/Youtube%20Thumbs/Chat%20With%20FIles.png)](https://www.youtube.com/watch?v=glWUkdZe_3w)

```

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

### Sticky Note: Obsidian Integration Guide

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Other_Integrations_and_Use_Cases/Obsidian Notes Read Aloud using AI_ Available as a Podcast Feed.txt

Provides instructions for integrating Obsidian with n8n using a webhook. It details the setup process, including installing a plugin in Obsidian and configuring the webhook URL and name.

```markdown
## Send Notes to Webhook
**Setup:**
- Install [Post Webhook Plugin](https://github.com/Masterb1234/obsidian-post-webhook/) in Obsidian
- Enter n8n Webhook URL and name in plugin settings

**Usage:**
- Select text or use full note
- Open Command Palette (Ctrl+P)
- Choose 'Send Note/Selection to [name]'
- Audio file appears in Podcast Feed and note
```

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

### Workflow Setup Guide (Sticky Note)

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Telegram/AI-Powered Children_s English Storytelling on Telegram with OpenAI.txt

Provides a detailed guide within the n8n workflow for setting up an 'AI-Powered Children's English Storytelling on Telegram' project. It outlines steps for importing, configuring credentials, setting parameters, and testing the workflow.

```APIDOC
Sticky Note:
  title: Setting Up a Workflow for "AI-Powered Children's English Storytelling on Telegram"
  description: |-
    In this guide, we will walk you through the process of setting up a workflow to create and share captivating children's stories using the provided configuration. Let's dive into the steps required to bring these imaginative tales to life on your Telegram channel:

  steps:
    - title: Import the Workflow
      details: Copy the provided workflow JSON configuration. In your n8n instance, go to Workflows and select "Import from JSON." Paste the configuration and import the workflow.
    - title: Configure Node Credentials
      details: For nodes requiring API credentials (OpenAI and Telegram), create credentials with the appropriate API keys or tokens.
    - title: Set Node Parameters
      details: Modify node parameters as needed, such as chat IDs, prompts, and intervals. Change the chatId in Config node to the ID of the chat you want the story to be posted.
    - title: Ensure Data Flow
      details: Check the connections between nodes to ensure a smooth flow of data and actions.
    - title: Execute Once
      details: Activate the "executeOnce" option in nodes where necessary to trigger actions only once during setup.
    - title: Test the Workflow
      details: Run the workflow to verify that each node functions correctly and data is processed as expected.
    - title: Enable Recurring Triggers
      details: Confirm that the Schedule Trigger node is set to trigger the workflow at the desired interval (every 12 hours).
    - title: Initiate Workflow
      details: Once everything is configured correctly, activate the workflow to start generating and sharing children's stories on Telegram.
  conclusion: |-
    By following these steps meticulously, you can seamlessly establish and operate the workflow designed to create captivating children's stories for your audience. Embrace the power of automation to inspire young minds and foster a love for storytelling through engaging narratives shared on Telegram.
```

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

### n8n Workflow: Quick Start Guide

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/🔥📈🤖 AI Agent for n8n Creators Leaderboard - Find Popular Workflows.txt

This section provides a quick start guide for the n8n Creators Leaderboard Workflow. It outlines prerequisites, how to trigger the workflow via chat, the processing steps involving data fetching and AI report generation, and the final output.

```n8n
{
  "name": "Sticky Note14",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    -2580,
    20
  ],
  "parameters": {
    "width": 480,
    "height": 980,
    "content": "# Quick Start Guide for the n8n Creators Leaderboard Workflow\n\n## Prerequisites\n- Ensure your n8n instance is running.\n- Verify that the GitHub base URL and file variables (for creators and workflows) are correctly set in the Global Variables node.\n- Confirm that your OpenAI credentials are configured for the AI Agent node.\n\n## How to Start the Workflow\n- **Activate the Workflow:** \n Ensure the workflow is active in your n8n environment.\n\n- **Trigger via Chat:** \n The workflow is initiated by the Chat Trigger node. Send a chat message such as: \n `show me stats for username [desired_username]` \n This input provides the required username for filtering.\n\n- **Processing & Report Generation:** \n Once triggered, the workflow fetches aggregated creator and workflow data from GitHub, processes and merges the information, and then uses the AI Agent to generate a Markdown report.\n\n- **Output:** \n The final Markdown report is saved locally as a file (with a timestamp), which you can review to see detailed leaderboard statistics and insights for the specified creator.\n\n## Summary\nBy sending a chat message with the appropriate username command, you can quickly trigger this workflow, which will then fetch, process, and generate dynamic statistics about n8n community creators. Enjoy exploring your community’s leaderboard data!\n"
  },
  "typeVersion": 1
}
```

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

### Pre-workflow Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Database_and_Storage/Generate SQL queries from schema only - AI-powered.txt

This section provides essential pre-workflow setup instructions, guiding users to connect to a free MySQL server and import their database. It references a tutorial for detailed steps and points to the location of the Chinook data used in the workflow on GitHub.

```javascript
{
  "id": "6606abc9-1dcb-4dba-b7ef-e221f892eed8",
  "name": "Sticky Note1",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    1040,
    -255
  ],
  "parameters": {
    "color": 6,
    "width": 312.47220527158765,
    "height": 174.60585869504342,
    "content": "## Pre-workflow setup \nConnect to a free MySQL server and import your database. Follow Step 1 and 2 in this [tutorial](https://blog.n8n.io/compare-databases/) for more.\n\n*The Chinook data used in this workflow is available on [GitHub](https://github.com/msimanga/chinook/tree/master/mysql).* "
  },
  "typeVersion": 1
}
```

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

### Sticky Note: Whisper-1 Transcription Example

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/OpenAI examples_ ChatGPT, DALLE-2, Whisper-1 – 5-in-1.txt

A sticky note introducing an example for the Whisper-1 model. It advises users to prepare their audio files and send them to the Whisper-1 transcription model, highlighting the setup process.

```json
{
  "id": "3cc74d77-7b02-40fd-83d8-f540d5ff34ab",
  "name": "Sticky Note1",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    -160,
    260
  ],
  "parameters": {
    "width": 428.4578974150008,
    "height": 316.6202633391793,
    "content": "## Whisper-1 example\n### Prepare your audio file and send it to whisper-1 transcription model"
  },
  "typeVersion": 1
}
```

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

### Sticky Note Content - Setup Steps

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Notion/Notion knowledge base AI assistant.txt

Provides a step-by-step guide for setting up the workflow. It covers adding Notion and OpenAI credentials, duplicating a Notion template, configuring nodes, and testing the workflow.

```javascript
{
  "color": 7,
  "width": 461.5634274842711,
  "height": 332.14098134070576,
  "content": "### Written set up steps\n1. Add a Notion credential to your n8n workspace (follow [this Notion guide](https://developers.notion.com/docs/create-a-notion-integration))\n2. [Duplicate Company knowledge base Notion template](https://www.notion.so/templates/knowledge-base-ai-assistant-with-n8n) to your Notion workspace, then make sure to share the new knowledge base with connection you created in Step 1. \n3. Add Notion cred to `Get database details`:`Credential to connect with` parameter, then to `Search notion database`:`Notion API` parameter (same for `Search inside database record`)\n4. Add OpenAI credential to `Open AI Chat Model` node (tested and working with Anthropic Claude 3.5 too)\n5. In `Get database details`, select the db you created from Step 2 in `Database` dropdown.\n6. Click `Chat` button to test the workflow. Then Activate it and copy the `Chat URL` from `When chat message received`."
}
```

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

### Bitrix24 Credentials Setup

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Other_Integrations_and_Use_Cases/Bitrix24 Chatbot Application Workflow example with Webhook Integration.txt

Sets up Bitrix24 API credentials including CLIENT_ID, CLIENT_SECRET, application_token, domain, and access_token. These are dynamically fetched from the incoming webhook payload.

```json
{
  "id": "5676a53e-6758-4ad5-ace6-e494fa10b6c3",
  "name": "Credentials",
  "type": "n8n-nodes-base.set",
  "position": [
    200,
    0
  ],
  "parameters": {
    "options": {},
    "assignments": {
      "assignments": [
        {
          "id": "030f8f90-2669-4c20-9eab-c572c4b7c70c",
          "name": "CLIENT_ID",
          "type": "string",
          "value": "local.6779636e712043.37129431"
        },
        {
          "id": "de9bbb7a-b782-4540-b259-527625db8490",
          "name": "CLIENT_SECRET",
          "type": "string",
          "value": "dTzUfBoTFLxNhuzc1zsnDbCeii98ZaE5By4aQPQEOxLJAS9y6i"
        },
        {
          "id": "86b7aff7-1e25-4b12-a366-23cf34e5a405",
          "name": "application_token",
          "type": "string",
          "value": "={{ $json.body['auth[application_token]'] }}"
        },
        {
          "id": "69bbcb1f-ba6e-42eb-be8a-ee0707ce997d",
          "name": "domain",
          "type": "string",
          "value": "={{ $json.body['auth[domain]'] }}"
        },
        {
          "id": "dc1b0515-f06a-4731-b0dc-912a8d04e56b",
          "name": "access_token",
          "type": "string",
          "value": "={{ $json.body['auth[access_token]'] }}"
        }
      ]
    },
    "includeOtherFields": true
  },
  "typeVersion": 3.4
}
```

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

### Setup and Configuration Guide

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Google_Drive_and_Google_Sheets/Automatic Background Removal for Images in Google Drive.txt

This section outlines the necessary setup and configuration steps for the workflow. It specifies prerequisites like obtaining a Photoroom API Key and setting up Google Drive credentials. It also guides users on configuring the workflow, including selecting Google Drive credentials and referencing the 'Config' node for API key and output settings.

```n8n
## Setup

### Requirements
* Photoroom API Key [Click me](https://docs.photoroom.com/getting-started/how-can-i-get-my-api-key)
* Google Drive Credential Setup


## Config
* Select Google Drive Credentials within the Google Drive Nodes

* **Please refer to the "Config" Node**

For the API Key you can also setup an Header Authentication
```

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

### Workflow Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Airtable/AI Agent to chat with Airtable and analyze data.txt

Provides instructions for setting up the workflow, including separating workflows, replacing credentials, and starting the chat interaction by mentioning the required base name.

```n8n
### Set up steps

1. **Separate workflows**:
	- Create additional workflow and move there Workflow 2.

2. **Replace credentials**:
	- Replace connections and credentials in all nodes.

3. **Start chat**:
	- Ask questions and don't forget to mention required base name.
```

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

### Sticky Note: OpenAI Key and Assistant Setup

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Make OpenAI Citation for File Retrieval RAG.txt

A sticky note guiding the user to configure their OpenAI API key and use a pre-created assistant with a vector store for file retrieval.

```javascript
{
  "id": "1817b673-6cb3-49aa-9f38-a5876eb0e6fa",
  "name": "Sticky Note1",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    560,
    -680
  ],
  "parameters": {
    "width": 300,
    "content": "## Setup\n\n- Configure OpenAI Key\n\n### In this step, we will use an assistant created within the OpenAI platform that contains a vector store a.k.a file retrieval"
  },
  "typeVersion": 1
}
```

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

### Project Description and Setup - Sticky Note

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/AI Agent to chat with you Search Console Data, using OpenAI and Postgres.txt

Content for an n8n sticky note node, providing a detailed description of an AI Agent project that interacts with Search Console data. It includes setup instructions, OAuth configuration guidance, webhook authentication advice, and examples of the agent's capabilities.

```markdown
# AI Agent to Chat with Your Search Console Data

This **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**.

Follow this **[n8n documentation](https://docs.n8n.io/integrations/builtin/credentials/google/oauth-generic/#configure-your-oauth-consent-screen)** to set up the OAuth credentials.

## Important Notes

### Correctly Configure Scopes for Search Console API Calls
- It’s 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**:
![Search Console API oAuth2 config 1](https://i.imgur.com/vVLM7gG.png)
![Search Console API oAuth2 config 2](https://i.imgur.com/naT1NaX.png)

Of 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.

### Configure Authentication for the Webhook

Since the **webhook will be publicly accessible**, don’t forget to **set up authentication**. I’ve used **Basic Auth**, but feel free to **choose the method that best meets your security requirements**.

## 🤩💖 Example of awesome things you can do with this AI Agent
![Example of chat with this AI Agent](https://i.imgur.com/jbfsYvT.png)



```

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

### OpenRouter API Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Open Deep Research - AI-Powered Autonomous Research Workflow.txt

Outlines the process for setting up OpenRouter API integration in n8n. It guides users to acquire an API key from OpenRouter's settings and configure the credential securely.

```markdown
## OpenRouter API Setup Instructions
1. Obtain your API key from https://openrouter.ai/settings/keys.
2. Set up your OpenRouter credential in n8n for secure integration.
```

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

### Workflow Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/WhatsApp/Building Your First WhatsApp Chatbot (1).txt

Provides guidance on setting up and running the n8n workflow. It highlights the one-time setup for populating the product catalog vector store and the need to activate the workflow for the WhatsApp chatbot to function.

```n8n
## Try It Out!

### This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions.

* This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot.
* A product brochure is imported via HTTP request node and its text contents extracted.
* The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot.
* A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out.
* The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool.
* The Agent's response is sent back to the user via the WhatsApp node.

### Need Help?
Join the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!
```

```n8n
### You only have to run this part once!
Run this step to populate our product catalogue vector. Run again if you want to update the vector store with a new version.
```

```n8n
### Activate your workflow to use!
To start using the WhatsApp chatbot, you'll need to activate the workflow. If you are self-hosting ensure WhatsApp is able to connect to your server.
```

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

### Workflow Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/WhatsApp/Building Your First WhatsApp Chatbot.txt

Provides guidance on setting up and running the n8n workflow. It highlights the one-time setup for populating the product catalog vector store and the need to activate the workflow for the WhatsApp chatbot to function.

```n8n
## Try It Out!

### This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions.

* This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot.
* A product brochure is imported via HTTP request node and its text contents extracted.
* The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot.
* A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out.
* The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool.
* The Agent's response is sent back to the user via the WhatsApp node.

### Need Help?
Join the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!
```

```n8n
### You only have to run this part once!
Run this step to populate our product catalogue vector. Run again if you want to update the vector store with a new version.
```

```n8n
### Activate your workflow to use!
To start using the WhatsApp chatbot, you'll need to activate the workflow. If you are self-hosting ensure WhatsApp is able to connect to your server.
```

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

### n8n Workflow Setup Guide

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Telegram/Telegram Bot with Supabase memory and OpenAI assistant integration.txt

A comprehensive setup guide for the n8n workflow. It covers creating a Telegram bot, setting up Supabase with a specific table, configuring OpenAI, and integrating these services within n8n by setting credentials and triggers.

```n8n
### Set up steps
1. **Create a Telegram Bot** using the [Botfather](https://t.me/botfather) and obtain the bot token.
2. **Set up Supabase:**
	1. Create a new project and generate a ```SUPABASE_URL``` and ```SUPABASE_KEY```.
	2. Create a new table named ```telegram_users``` with the following SQL query:
```
create table
 public.telegram_users (
 id uuid not null default gen_random_uuid (),
 date_created timestamp with time zone not null default (now() at time zone 'utc'::text),
 telegram_id bigint null,
 openai_thread_id text null,
 constraint telegram_users_pkey primary key (id)
 ) tablespace pg_default;
```
3. **OpenAI Setup:**
	1. Create an OpenAI assistant and obtain the ```OPENAI_API_KEY```.
	2. Customize your assistant’s personality or use cases according to your requirements.
4. **Environment Configuration in n8n:**
	1. Configure the Telegram, Supabase, and OpenAI nodes with the appropriate credentials.
	2. Set up triggers for receiving messages and handling conversation logic.
	3. Set up OpenAI assistant ID in "++OPENAI - Run assistant++" node.
```

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

### Workflow Execution Path: Get Audio

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/YouTube_Music_Video_Generator_with_AI.txt

This snippet details the execution path starting from the 'Get Audio' node. It shows that after 'Get Audio', the workflow proceeds to 'Google Drive Save Audio' and 'Write Audio'.

```json
{
  "node": "Get Audio",
  "type": "main",
  "index": 0
}
```

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

### Workflow Pin Data Example

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Autonomous AI crawler.txt

Example of pin data used in the workflow, specifically for 'Get companies', providing a list of company names and their corresponding websites.

```javascript
{
  "pinData": {
    "Get companies": [
      {
        "id": 1,
        "name": "n8n",
        "website": "https://n8n.io"
      }
    ]
  }
}
```

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

### Workflow: 8 Minutes

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/AI_Faceless_Shorts_Creator.txt

This workflow starts with 'Get Videos (Kling)'.

```json
{
  "8 Minutes": {
    "main": [
      [
        {
          "node": "Get Videos (Kling)",
          "type": "main",
          "index": 0
        }
      ]
    ]
  }
}
```

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

### Brave Search API Key Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Intelligent Web Query and Semantic Re-Ranking Flow using Brave and Google Gemini.txt

Provides step-by-step instructions for obtaining and configuring a Brave Search API key. This is crucial for enabling the web search functionality within the workflow.

```markdown
## Step 1. Set Up a Free Brave Web Search Query API Key

To attain the free web search API tier from Brave, follow these steps:

1. Visit api.search.brave.com
2. Create an account
3. Subscribe to the free plan (no charge)
4. Navigate to the API Keys section
5. Generate an API key. For the subscription type, choose "Free".
6. Go to the "Query" Nodes and change the "X-Subscription-Token" value to your API Key.

```

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

### Sticky Note Content - Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/HR_and_Recruitment/CV Screening with OpenAI.txt

Provides setup instructions for the CV screening workflow, detailing steps for downloading, extracting, analyzing with OpenAI, and saving results.

```markdown
### Setup

1. **Download File**: Fetch the CV using its direct URL.
2. **Extract Data**: Use N8N’s PDF or text extraction nodes to retrieve text from the CV.
3. **Send to OpenAI**:
 - **URL**: POST to OpenAI’s API for analysis.
 - **Parameters**:
 - Include the extracted CV data and job description.
 - Use JSON Schema to structure the response.
4. **Save Results**:
 - Store the extracted data and OpenAI's analysis in Supabase for further use.
```

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

### Workflow Trigger Input Example

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Other_Integrations_and_Use_Cases/Using External Workflows as Tools in n8n.txt

An example of the input expected by the 'Execute Workflow Trigger' node. It should be a JSON object containing a 'query' field with the 'url' to be scraped.

```json
{
  "query": {
    "url": "https://en.wikipedia.org/wiki/Linux"
  }
}
```

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

### n8n Node Configuration: Sticky Note (Setup)

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Intelligent Web Query and Semantic Re-Ranking Flow using Brave and Google Gemini.txt

Configuration for a 'Sticky Note' node providing setup instructions for Brave Search API key.

```APIDOC
Sticky Note4:
  type: n8n-nodes-base.stickyNote
  position: [-640, -620]
  parameters:
    color: 5
    width: 1172
    height: 970
    content: "## Step 1. Set Up a Free Brave Web Search Query API Key\n\nTo attain the free web search API tier from Brave, follow these steps:\n\n1. Visit api.search.brave.com\n2. Create an account\n3. Subscribe to the free plan (no charge)\n4. Navigate to the API Keys section\n5. Generate an API key. For the subscription type, choose \"Free\".\n6. Go to the \"Query\" Nodes and change the \"X-Subscription-Token\" value to your API Key."
  typeVersion: 1

```

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

### Sticky Note: ChatGPT Examples 1.1 & 1.2

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/OpenAI examples_ ChatGPT, DALLE-2, Whisper-1 – 5-in-1.txt

This sticky note outlines two ChatGPT examples (1.1 and 1.2). It details tasks such as writing a TL;DR of input text and translating it to German, emphasizing the use of only user content.

```json
{
  "id": "c71001e6-b80f-41dd-bcdd-10927014b374",
  "name": "Sticky Note3",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    900,
    280
  ],
  "parameters": {
    "width": 747.8556016477869,
    "height": 288.18470714667706,
    "content": "## ChatGPT example 1.1 and 1.2 \n### Write a Tl;dr of the text input\n### Translate it to German\n### only user content provided"
  },
  "typeVersion": 1
}
```

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

### Workflow: 30 Seconds

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/AI_Faceless_Shorts_Creator.txt

This workflow starts with a 'Get Images' node and proceeds to 'Generate Videos'.

```json
{
  "30 Seconds": {
    "main": [
      [
        {
          "node": "Get Images",
          "type": "main",
          "index": 0
        }
      ]
    ]
  }
}
```

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

### Setup Instructions Sticky Note

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Google_Drive_and_Google_Sheets/RAG Chatbot for Company Documents using Google Drive and Gemini.txt

A detailed sticky note providing step-by-step instructions for setting up the workflow, including Google Cloud, API keys, Pinecone, Google Drive, and n8n credentials.

```json
{
  "id": "578deb96-8393-4850-9757-fa97b2bc9992",
  "name": "Sticky Note1",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    -540,
    220
  ],
  "parameters": {
    "width": 420,
    "height": 720,
    "content": "## Set up steps\n\n1. Google Cloud Project and Vertex AI API:\n* Create a Google Cloud project.\n* Enable the Vertex AI API for your project.\n2. Google AI API Key:\n* Obtain a Google AI API key from Google AI Studio.\n3. Pinecone Account:\n* Create a free account on the Pinecone website.\nObtain your API key from your Pinecone dashboard.\n* Create an index named company-files in your Pinecone project.\n4. Google Drive:\n* Create a dedicated folder in your Google Drive where company documents will be stored.\n5. Credentials in n8n: Configure credentials in your n8n environment for:\n* Google Drive OAuth2\n* Google Gemini(PaLM) Api (using your Google AI API key)\n* Pinecone API (using your Pinecone API key)\n5. Import the Workflow:\n* Import this workflow into your n8n instance.\n6. Configure the Workflow:\n* Update both Google Drive Trigger nodes to watch the specific folder you created in your Google Drive.\n* Configure the Pinecone Vector Store nodes to use your company-files index."
  },
  "typeVersion": 1
}
```

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

### YouTube AI Agent Setup Steps

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Extract insights & analyse YouTube comments via AI Agent chat.txt

Detailed setup instructions for the YouTube AI Agent workflow, covering API key generation for Google Cloud, Apify, and OpenAI, as well as credential setup within n8n.

```n8n
### Set up steps

1. **API Setup**:
 - Create a [Google Cloud](https://console.cloud.google.com/apis/dashboard) project and enable the YouTube Data API.
 - Generate an API key for [Apify](https://www.apify.com?fpr=ujogj).
 - Generate API key for [OpenAI](https://platform.openai.com)
 - Create all credentials in N8N - OpenAI, Apify, Google Cloud.

2. **YouTube Creator and Video Selection**:
 - Start by defining a request to identify top creators based on their video views.
 - Capture the YouTube video IDs for further analysis of comments and other video metrics.

3. **Comment Analysis**:
 - Gather comments associated with the selected videos and analyze them for user insights.
 - Implement pagination to handle the maximum comment retrieval limits in API requests.

4. **Video Transcription**:
 - Request transcriptions for videos of interest, ensuring to manage potential costs associated with longer video processing.
 - Utilize the insights from transcriptions to formulate content plans.

5. **Thumbnail Analysis**:
 - Evaluate your video thumbnails by submitting the URL through the OpenAI API to gain insights into their effectiveness.

6. **Data Management**:
 - Incorporate a database agent to organize video data and metrics, allowing efficient record management and future content planning.
```

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

### OpenAI Chat Completion (Translate)

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/OpenAI examples_ ChatGPT, DALLE-2, Whisper-1 – 5-in-1.txt

This example demonstrates using the chat completion API to translate text. It includes a system message to guide the AI and a user message with the text to be translated.

```javascript
{
  "prompt": {
    "messages": [
      {
        "content": "=Translate to German the following text: {{ $json.message.content }}"
      }
    ]
  },
  "options": {
    "maxTokens": 500
  },
  "resource": "chat"
}
```

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

### Sticky Note - RAG System Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/Personal Shopper Chatbot for WooCommerce with RAG using Google Drive and openAI.txt

A sticky note providing instructions for setting up a basic RAG system, including creating a collection in Qdrant, uploading documents to Google Drive, and embedding them into the Qdrant vector database.

```json
{
"id": "17015f50-a3a8-4e62-9816-7e71127c1ea1",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-220,
-640
],
"parameters": {
"color": 3,
"width": 1301.621262458471,
"height": 105.6212624584717,
"content": "## Step 1 \nCreate a collectiopn on your Qdrant instance. Then create a basic RAG system with documents uploaded to Google Drive and embedded in the Qdrant vector database"
},
"typeVersion": 1
}
```

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

### Workflow Description and Setup Guide

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Notion/Store Notion_s Pages as Vector Documents into Supabase with OpenAI.txt

Provides a high-level overview of the workflow's purpose and steps. It also includes a crucial guide for setting up Supabase vector columns, which is a prerequisite for the workflow.

```markdown
## Store Notion's Pages as Vector Documents into Supabase

**This workflow assumes you have a Supabase project with a table that has a vector column. If you don't have it, follow the instructions here:** [Supabase Vector Columns Guide](https://supabase.com/docs/guides/ai/vector-columns)

## Workflow Description

This workflow automates the process of storing Notion pages as vector documents in a Supabase database with a vector column. The steps are as follows:

1. **Notion Page Added Trigger**:
 - Monitors a specified Notion database for newly added pages. You can create a specific Notion database where you copy the pages you want to store in Supabase.
 - Node: `Page Added in Notion Database`

2. **Retrieve Page Content**:
 - Fetches all block content from the newly added Notion page.
 - Node: `Get Blocks Content`

3. **Filter Non-Text Content**:
 - Excludes blocks of type "image" and "video" to focus on textual content.
 - Node: `Filter - Exclude Media Content`

4. **Summarize Content**:
 - Concatenates the Notion blocks content to create a single text for embedding.
 - Node: `Summarize - Concatenate Notion's blocks content`

5. **Store in Supabase**:
 - Stores the processed documents and their embeddings into a Supabase table with a vector column.
 - Node: `Store Documents in Supabase`

6. **Generate Embeddings**:
 - Utilizes OpenAI's API to generate embeddings for the textual content.
 - Node: `Generate Text Embeddings`


7. **Create Metadata and Load Content**:
 - Loads the block content and creates associated metadata, such as page ID and block ID.
 - Node: `Load Block Content & Create Metadata`

8. **Split Content into Chunks**:
 - Divides the text into smaller chunks for easier processing and embedding generation.
 - Node: `Token Splitter`




```

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

### SerpAPI Setup Instructions

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/AI_Research_RAG_and_Data_Analysis/Open Deep Research - AI-Powered Autonomous Research Workflow.txt

Provides guidance on setting up SerpAPI integration within n8n. It emphasizes obtaining an API key and storing it securely in n8n credentials, rather than using plain text.

```markdown
## SerpAPI Setup Instructions
1. Obtain your API key from https://serpapi.com/manage-api-key.
2. Save your API key securely in n8n credentials (do not use plain text).
```

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

### LM Studio Setup and Configuration Guide

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/🚀 Local Multi-LLM Testing & Performance Tracker.txt

This section provides guidance on setting up LM Studio and configuring local LLM servers. It emphasizes updating the base URL to match the LM Studio server's IP and explains how to load models for testing. It also details parameters like Temperature, Top P, and Presence Penalty for fine-tuning model behavior.

```APIDOC
LM Studio Setup:
  - Download and install LM Studio.
  - Identify and load desired LLM models.
  - Start the LM Studio server.

Workflow Configuration:
  - Update the 'Base URL' in the HTTP Request node to your LM Studio server's IP (e.g., http://192.168.1.1:1234/v1/models).
  - Rerun the 'Get Models' node after changing or adding models in LM Studio.

Model Parameter Tuning:
  - Temperature: Controls randomness. Higher values (e.g., 1.0) increase diversity; lower values (e.g., 0.2) increase focus.
  - Top P: Adjusts nucleus sampling. Lower values (e.g., 0.5) narrow the response range.
  - Presence Penalty: Penalizes new tokens based on their presence, encouraging varied responses.

Text Analysis - Readability Score Ranges:
  - 90–100: Very easy (5th grade or below)
  - 80–89: Easy (6th grade)
  - 70–79: Fairly easy (7th grade)
  - 60–69: Standard (8th-9th grade)
  - 50–59: Fairly difficult (10th-12th grade)
  - 30–49: Difficult (College)
  - 0–29: Very difficult (College graduate)
  - Below 0: Extremely difficult (Post-graduate)
```

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

### Google Calendar - Get Events Configuration

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/AI Agent _ Google calendar assistant using OpenAI.txt

The 'Google Calendar - Get Events' node is used to retrieve event data from Google Calendar. It uses parameters like `timeMax` and `timeMin` which can be dynamically set, for example, using `$fromAI` to get date information from the AI's response.

```n8n
{
  "id": "5cdece35-bd69-4c77-b240-963df8781d64",
  "name": "Google Calendar - Get Events",
  "type": "n8n-nodes-base.googleCalendarTool",
  "position": [
    960,
    800
  ],
  "parameters": {
    "options": {
      "timeMax": "={{ $fromAI('end_date') }}",
      "timeMin": "={{ $fromAI('start_date') }}"
    },
    "calendar": {
      "__rl": true,
      "mode": "list",
      "value": "",
      "cachedResultName": ""
    },
    "operation": "getAll",
    "descriptionType": "manual",
    "toolDescription": "Use this tool when you’re asked to retrieve events data."
  },
  "credentials": {
    "googleCalendarOAuth2Api": {
      "id": "",
      "name": "Google Calendar account"
    }
  },
  "typeVersion": 1.2
}
```

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

### Workflow Setup Notes

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Discord/Share YouTube Videos with AI Summaries on Discord.txt

Provides essential setup instructions for the n8n workflow. It guides users on how to configure the YouTube channel ID in the RSS feed trigger and emphasizes the need for YouTube API authorization.

```javascript
{
  "type": "n8n-nodes-base.stickyNote",
  "parameters": {
    "width": 448.11859838274916,
    "height": 417.2722371967648,
    "content": "### Summarise Your YouTube Videos with AI for Discord\n\n📽️ [Watch the Video Tutorial](https://mrc.fm/ai2d)\n\n* Add your [YouTube channel ID](https://www.youtube.com/account_advanced) to the URL in the first node: `https://www.youtube.com/feeds/videos.xml?channel_id=YOUR_CHANNEL_ID`.\n\n* Ensure authorization with the YouTube channel that you want to download captions from."
  }
}
```

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

### n8n Sticky Note - LinkedIn API Setup

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/Instagram_Twitter_Social_Media/Social Media Analysis and Automated Email Generation.txt

A sticky note in n8n explaining the setup for the Fresh LinkedIn Profile Data API via RapidAPI. It guides users to create a RapidAPI account, subscribe to the API, and configure header authentication with 'x-rapidapi-key'.

```json
{
  "id": "42df4665-2d46-4020-938c-f082db6f09d0",
  "name": "Sticky Note4",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    1220,
    -300
  ],
  "parameters": {
    "color": 4,
    "width": 280,
    "height": 480,
    "content": "## Call RapidAPI Fresh Linkedin Profile Data\nYou have to create an account in [RapidAPI](https://rapidapi.com) and subscribe to Fresh LinkedIn Profile Data. With a free account you will be able to scrape 100 profile / month.\nAfter your subscription you will have to choose as Generic Auth Type: Header Auth and then put as header name: \"x-rapidapi-key\" and the value given in the RapidAPI interface\n"
  },
  "typeVersion": 1
}
```

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

### Sticky Note: Setup Video Link

Source: https://github.com/djeknet/n8n-master-workflows/blob/master/OpenAI_and_LLMs/Flux AI Image Generator.txt

A sticky note containing an embedded link to a setup video for the Flux Generator project, presented with a thumbnail image to encourage user engagement.

```n8n
{
  "id": "e740dd3c-e23e-485b-bb4c-bb0515897a08",
  "name": "Sticky Note5",
  "type": "n8n-nodes-base.stickyNote",
  "position": [
    -880,
    600
  ],
  "parameters": {
    "color": 7,
    "width": 506.8102696237577,
    "height": 337.24177957113216,
    "content": "### Watch Set Up Video 👇\n[![Flux Generator](https://uploads.n8n.io/devrel/fluxgenerator.png#full-width)](https://youtu.be/Rv_1jt5WvtY)\n\n"
  },
  "typeVersion": 1
}
```