Airtable node
+3

Generate AI Prompts with Google Gemini and store them in Airtable

Published 14 days ago

Created by

imperolq
Imperol

Categories

Template description

This workflow is designed to generate prompts for AI agents and store them in Airtable.

It starts by receiving a chat message, processes it to create a structured prompt, categorizes the prompt, and finally stores it in Airtable.

2. Setup Instructions

Prerequisites

  • AI model eg Gemini, openAI etc
  • Airtable base and table or other storage tool

Step-by-Step Guide

  1. Clone the Workflow
  • Copy the provided workflow JSON and import it into your n8n instance.
  1. Configure Credentials
  • Set up the Google Gemini(PaLM) API account credentials.
  • Set up the Airtable Personal Access Token account credentials.
  1. Map Airtable Base and Table
  • Create a copy of the Prompt Library in Airtable.
  • Map the Airtable base and table in the Airtable node.
  1. Customize Prompt Template
  • Edit the 'Create prompt' node to customize the prompt template as needed.

Configuration Options

  • Prompt Template: Customize the prompt template in the 'Create prompt' node to fit your specific use case.
  • Airtable Mapping: Ensure the Airtable base and table are correctly mapped in the Airtable node.

4. Running and Troubleshooting

Running the Workflow

  1. Trigger the Workflow: Send a chat message to trigger the workflow.
  2. Monitor Execution: Use the n8n interface to monitor the workflow execution.
  3. Check Completion: Verify that the prompt is stored in Airtable and check the chat interface for the result.

Troubleshooting Tips

  • API Issues: Ensure that the APIs and Airtable credentials are correctly configured.
  • Data Mapping: Verify that the Airtable base and table are correctly mapped.
  • Prompt Template: Check the prompt template for any errors or inconsistencies.
  1. Use Case Examples

This workflow is particularly useful in scenarios where you want to automate the generation and management of AI agent prompts.

Here are some examples:

Rapid Prototyping of AI Agents:

Quickly generate and test different prompts for AI agents in various applications.

  • Content Creation: Generate prompts for AI models that create blog posts, articles, or social media content.
  • Customer Service Automation: Develop prompts for AI-powered chatbots to handle customer inquiries and support requests.
  • Educational Tools: Create prompts for AI tutors or learning assistants.

Industries/Professionals:

  • Software Development: Developers building AI-powered applications.

  • Marketing: Marketers automating content creation and social media management.

  • Customer Service: Customer service managers implementing AI-driven chatbots.

  • Education: Educators creating AI-based learning tools.

Practical Value:

  • Time Savings: Automates the prompt generation process, saving significant time and effort.

  • Improved Prompt Quality: Leverages Google Gemini and structured prompt engineering principles to generate more effective prompts.

  • Centralized Prompt Management: Stores prompts in Airtable for easy access, organization, and reuse.

4. Running and Troubleshooting

  • Running the Workflow:
  1. Activate the workflow in n8n.
  2. Send a chat message to the webhook URL configured in the "When chat message received" node.
  3. Monitor the workflow execution in the n8n editor.
  • Monitoring Execution:

  • Check the execution log in n8n to see the data flowing through each node and identify any errors.

  • Checking for Successful Completion:

  • Verify that a new record is created in your Airtable base with the generated prompt, name, and category.

  • Confirm that the "Return results" node sends back confirmation of the prompt in the chat interface.

  • Troubleshooting Tips:

  • Error: 400: Bad Request in the Google Gemini nodes:

  • Cause: Invalid API key or insufficient permissions.

  • Solution: Double-check your Google Gemini API key and ensure that the API is enabled for your project.

  • Error: Airtable node fails to create a record:

  • Cause: Invalid Airtable credentials, incorrect Base ID or Table ID, or mismatched column names.

  • Solution: Verify your Airtable API key, Base ID, Table ID, and column names. Ensure that the data types in n8n match the data types in your Airtable columns.

Follow me on Linkedin for more

Share Template

More AI workflow templates

OpenAI Chat Model node
SerpApi (Google Search) node

AI agent chat

This workflow employs OpenAI's language models and SerpAPI to create a responsive, intelligent conversational agent. It comes equipped with manual chat triggers and memory buffer capabilities to ensure seamless interactions. To use this template, you need to be on n8n version 1.50.0 or later.
n8n-team
n8n Team
HTTP Request node
Merge node
+7

Scrape and summarize webpages with AI

This workflow integrates both web scraping and NLP functionalities. It uses HTML parsing to extract links, HTTP requests to fetch essay content, and AI-based summarization using GPT-4o. It's an excellent example of an end-to-end automated task that is not only efficient but also provides real value by summarizing valuable content. Note that to use this template, you need to be on n8n version 1.50.0 or later.
n8n-team
n8n Team
HTTP Request node
WhatsApp Business Cloud node
+10

Building Your First WhatsApp Chatbot

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 intended to help introduce n8n users interested in building with WhatsApp. How it works 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. How to use Once you've setup and configured your WhatsApp account and credentials First, populate the vector store by clicking the "Test Workflow" button. Next, activate the workflow to enable the WhatsApp chatbot. Message your designated WhatsApp number and you should receive a message from the AI sales agent. Tweak datasource and behaviour as required. Requirements WhatsApp Business Account OpenAI for LLM Customising this workflow Upgrade the vector store to Qdrant for persistance and production use-cases. Handle different WhatsApp message types for a more rich and engaging experience for customers.
jimleuk
Jimleuk
HTTP Request node
Markdown node
+5

AI agent that can scrape webpages

⚙️🛠️🚀🤖🦾 This template is a PoC of a ReAct AI Agent capable of fetching random pages (not only Wikipedia or Google search results). On the top part there's a manual chat node connected to a LangChain ReAct Agent. The agent has access to a workflow tool for getting page content. The page content extraction starts with converting query parameters into a JSON object. There are 3 pre-defined parameters: url** – an address of the page to fetch method** = full / simplified maxlimit** - maximum length for the final page. For longer pages an error message is returned back to the agent Page content fetching is a multistep process: An HTTP Request mode tries to get the page content. If the page content was successfuly retrieved, a series of post-processing begin: Extract HTML BODY; content Remove all unnecessary tags to recude the page size Further eliminate external URLs and IMG scr values (based on the method query parameter) Remaining HTML is converted to Markdown, thus recuding the page lengh even more while preserving the basic page structure The remaining content is sent back to an Agent if it's not too long (maxlimit = 70000 by default, see CONFIG node). NB: You can isolate the HTTP Request part into a separate workflow. Check the Workflow Tool description, it guides the agent to provide a query string with several parameters instead of a JSON object. Please reach out to Eduard is you need further assistance with you n8n workflows and automations! Note that to use this template, you need to be on n8n version 1.19.4 or later.
eduard
Eduard
Merge node
Telegram node
Telegram Trigger node
+2

Telegram AI Chatbot

The workflow starts by listening for messages from Telegram users. The message is then processed, and based on its content, different actions are taken. If it's a regular chat message, the workflow generates a response using the OpenAI API and sends it back to the user. If it's a command to create an image, the workflow generates an image using the OpenAI API and sends the image to the user. If the command is unsupported, an error message is sent. Throughout the workflow, there are additional nodes for displaying notes and simulating typing actions.
eduard
Eduard
Google Drive node
Binary Input Loader node
Embeddings OpenAI node
OpenAI Chat Model node
+5

Ask questions about a PDF using AI

The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.
davidn8n
David Roberts

Implement complex processes faster with n8n

red icon yellow icon red icon yellow icon