Show HN: SiteGPT – Create ChatGPT-like chatbots trained on your website content

Hello everyone,

I am the founder of a blogging platform called Feather.so.

People can sign up and create their own blogs using Feather.

Now, with OpenAI releasing their API, they made using AI so accessible for someone like me. So I wanted to add a chatbot functionality to my customer blogs. Basically, I wanted to automatically create a chatbot for each of my customer blogs. That chatbot will be trained on the content on their blog.

When I set out to do this using Open AI, I thought I could do this for every website, not just for my customer blogs.

So I ended up creating an entirely new product called SiteGPT.ai so that it can be used on any website.

The workflow works like this. People login the platform, they enter their website url, and click on a button to start training. Then I start creating a chatbot and train the chatbot will all the content on the website that the user enters.

That chatbot now knows everything about that website. It can answer any questions related to that website.

I have also added a demo chatbot at the bottom right of the sitegpt.ai website. That chatbot is trained on the content of SiteGPT.ai. So it can answer any questions related to its own website.

Please try it out and let me know if you have any feedback. I am also happy to take any other technical questions you may have.

Thanks.

Show HN: SiteGPT – Create ChatGPT-like chatbots trained on your website content
sitegpt.ai

[flagged]

Sorry but I am not going to pay for this before trying it out on my content.

Surely there can be a test function within the website which allows me to see what a user would experience?

Do you simple paste the entire content of a webpage inside a prompt? You prepend the question from an enduser with that content?:i.e. dear chatgpt api, could you answer the following question [user question] based on the following text [website contents]

I guess not. Probably an offline process where they scrape the websites into chunks and build embeddings. At query time first search for the relevant chunks and then put those chunks into the prompt?

Would love more details though from the author!