After import of bolt.new project getting errors with Failed to load resource: net::ERR_BLOCKED_BY_RESPONSE

net::ERR_BLOCKED_BY_RESPONSE.NotSameOriginAfterDefaultedToSameOriginByCoep

After loading a Bolt.new project to work on, missing images and graphics getting the following…

Errors…

Any ideas on some simple prompts that may help reset this ??

I bet there is some magic out there by now :rofl: :rofl: :rofl:

I think I had the same and deleting the “.bolt” folder first, before importing, fixed it for me.

Ah sry, think mixed it up. You have some problems with your images at all. As far as I know, Images are still not working within bolt if they are not SVGs (they work at least in my project).

Check below - works well in Bolt.new but once downloading project vfrom Bolt.new then uploading folder to Bolt.diy, it looses some functionality. I accept that but I think we can find a way of ‘refactoring’ a project so certain resources and authorizations can be resynced. If that makes sense as I’m sure this is a real thing.

See below as it works well but I’m getting several issues with Bolt.diy that don’t exist with Bolt.new. And, yes I really want to find a way to help you guys over here to improve your project - all this stuff is hard to deal with I know and you’re having a hard time but that’s where amazing things happen when you dig deep…

One question I have is once I receive an error like this below, I have to reload the browser as it seems to be a persistent issue and will continue to reoccur.

I want to help you guys make this the best thing out there. And I know it’s not going to be easy. :wink:

Thanks for the detailed post.

Do you see an error in the terminal where bolt is running? This message can come from different things.

I have this e.g. at the moment, because my project is to big and the output (completion tokens) reach a limit, what I can see in the terminal:

usage { promptTokens: 161779, completionTokens: 8204, totalTokens: 169983 }
Reached max token limit (8000): Continuing message (1 switches left)

Edit: This depends on the Provider and/or the Model you are using. So you need to figure out if there is another good model/provider with higher rate limits.

More on this…

Bolt.new provides functionality that I’m not seeing with Bolt.diy yet and I have asked simple prompts.

Using Bolt.diy I get…

Please help me keep enthusiasm as I’ve spent 3 days chasing my tail now.

You cant compare it like this, because you are not using the same Model/Provider as bolt.new does.
If you want to compare, you have to at least Claude 3.5 Sonnet (old) as Model, what is quite expensive in my view, but otherwise you cant compare :slight_smile:

But Qwen2.5 32B is meant to be so good according to @ColeMedin and I’m getting nothing when using…
image

Let me show you some simple requests back-to-back with bolt.new. Something is wrong here.

Try on Bolt.diy

Getting an error but unknown and F12 dev console doesn’t really help.

Please help me understand the difference between the two. I really want to start using Bolt.diy and happy to spend money using the product but I don’t see anything worth my time as yet. Seems there’s too much needing fixing right now.

A few things. I think you are getting a combination of CORS and mixed-content (mixing http and https content) errors as the images are likely from the web, and not in the project itself (neither Bolt.diy/Bolt.new generally bring in their own images). As for Qwen2.5 Coder 32B (open source/free model) being good, it is for simple things as long as you guide it, but it’s not going to one-shot things like Sonnet (commercial/pricy). Heck o1 doesn’t even seem to be as good!

For one, you are running locally, not behind HTTPS… this will cause all sorts of issues when trying to access web resources. Maybe try my tutorial on Deploying Bolt.diy with Cloudflare Pages (the easy way!). This would fix the HTTPS and mixed-content issues, but I’m not sure about the CORS problem. You could also always modify the code to load the images from the project (but you’d have to put them in it).

If you need better debugging, there is an option in the Bolt.diy settings, but I’m not sure it would have helped much in this case.

And while saying “there’s too much needing fixing right now” is fine, but part of it is understanding the thing you are using (differences and limitations), and not assuming it’s a bug. It’s not. But it is what it is.

Good luck!

P.S. Also @shawn, if you don’t mind a little experimentation, maybe try Qwen2.5 72B Instruct and Llama3.3 through HuggingFace for free. Or Google Gemini exp-1206 through Google Studio for free. You can also get 4o for free through GitHub, but Bolt.diy support is kind of pending.

2 Likes

Thanks and yes I know - new stuff is what it is. Takes time to get it up to speed. Let’s ride the wave and see how far we get. LOL.

1 Like

Yes. It’s a brave new world. Let’s see where it leads us…

1 Like