After sharing my VAPI build, I’ve had a lot of questions about how to ACTUALLY deploy and manage a VAPI deployment to clients. In this video, I’ve shared the different options and pros- and cons as well as broader considerations when starting and running an AI Agency. Please let me know your thoughts - I tried to edit this MUCH faster as last time it took me a silly amount of time. So again, all feedback very much appreciated to help me improve! 🙂

I have been using a technique to improve the accuracy of searches in RAG (Retrieval-Augmented Generation). The process works as follows: I receive data in JSON or XML format, and instead of using it directly, I apply a pre-processing step. To achieve this, I use an AI model to transform the raw data into a structured sentence and a logical natural language representation. This significantly enhances accuracy, as traditional semantic search struggles with retrieving disconnected data points. Example: Suppose I have a JSON file with real estate listings: { "id": 12345, "type": "Apartment", "bedrooms": 3, "bathrooms": 2, "size": 120, "city": "São Paulo", "neighborhood": "Vila Mariana", "price": 950000 } The AI processes this data and generates a structured sentence: "Apartment with 120m², featuring 3 bedrooms and 2 bathrooms, located in Vila Mariana, São Paulo, available for R$ 950,000." It also creates a logical representation for precise searches: "A property of type apartment, located in São Paulo, in the Vila Mariana neighborhood, with 3 bedrooms, 2 bathrooms, and a size of 120m², available for sale at R$ 950,000." Why This Technique Works This approach is particularly useful when searching for highly relevant results within RAG. Instead of relying solely on semantic search—which may struggle with loosely structured data—we provide clear contextual information in advance. Once the model returns a relevant result, I can extract the ID of the property (12345). With this ID, I can perform a direct database query, retrieving all the necessary details accurately. This technique significantly enhances search precision, ensures data reliability, and improves the overall effectiveness of AI-powered retrieval systems.

Learn how to create a powerful Retrieval-Augmented Generation (RAG) system using n8n, Supabase, and Postgres. This system automatically uploads documents to your vector database based on file type and seamlessly updates your records whenever changes are made to your files. Perfect for streamlining data management and enhancing your AI knowledge base.

Can any savvy n8n WINDOWS users help me get webhook triggers working? I've tried using the npm and docker starterkit routes and just cannot get Elevenlabs or Telegram working with n8n. The n8n webhook triggers are not picking up what these APIs are putting down. I know there are a lot of other windows users squirming around this issue but for some reason, there isn't much info out there! @Nate Herk You could do a video on this, you'd pull a good number of views for sure! Thanks in advance!

When I get a warranty registration email, I want chat gpt to extract the information (name, email, product, date) and append it to warranty registration google sheet. This seems like it should be easy, but I'm stuck. Can anyone point me in the right direction or recommend a tutorial? thanks.