UniqAI/bolt.new-any-llm
1
0
Fork 0
mirror of https://github.com/coleam00/bolt.new-any-llm synced 2024-12-27 22:33:03 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge pull request #845 from dustinwloring1988/docs/updated-docs

Browse Source 
docs: updated Docs
This commit is contained in:
Cole Medin 2024-12-20 13:37:16 -06:00 committed by GitHub
commit 7afd654210
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 464 additions and 440 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

280
CONTRIBUTING.md
View File

@ -1,217 +1,219 @@
# Contributing to bolt.diy
# Contribution Guidelines
First off, thank you for considering contributing to bolt.diy! This fork aims to expand the capabilities of the original project by integrating multiple LLM providers and enhancing functionality. Every contribution helps make bolt.diy a better tool for developers worldwide.
Welcome! This guide provides all the details you need to contribute effectively to the project. Thank you for helping us make **bolt.diy** a better tool for developers worldwide. 💡
---
## 📋 Table of Contents
- [Code of Conduct](#code-of-conduct)
- [How Can I Contribute?](#how-can-i-contribute)
- [Pull Request Guidelines](#pull-request-guidelines)
- [Coding Standards](#coding-standards)
- [Development Setup](#development-setup)
- [Deploymnt with Docker](#docker-deployment-documentation)
- [Project Structure](#project-structure)
## Code of Conduct
1. [Code of Conduct](#code-of-conduct)
2. [How Can I Contribute?](#how-can-i-contribute)
3. [Pull Request Guidelines](#pull-request-guidelines)
4. [Coding Standards](#coding-standards)
5. [Development Setup](#development-setup)
6. [Testing](#testing)
7. [Deployment](#deployment)
8. [Docker Deployment](#docker-deployment)
9. [VS Code Dev Containers Integration](#vs-code-dev-containers-integration)
This project and everyone participating in it is governed by our Code of Conduct. By participating, you are expected to uphold this code. Please report unacceptable behavior to the project maintainers.
---
## How Can I Contribute?
## 🛡️ Code of Conduct
### 🐞 Reporting Bugs and Feature Requests
- Check the issue tracker to avoid duplicates
- Use the issue templates when available
- Include as much relevant information as possible
- For bugs, add steps to reproduce the issue
This project is governed by our **Code of Conduct**. By participating, you agree to uphold this code. Report unacceptable behavior to the project maintainers.
### 🔧 Code Contributions
1. Fork the repository
2. Create a new branch for your feature/fix
3. Write your code
4. Submit a pull request
---
### ✨ Becoming a Core Contributor
We're looking for dedicated contributors to help maintain and grow this project. If you're interested in becoming a core contributor, please fill out our [Contributor Application Form](https://forms.gle/TBSteXSDCtBDwr5m7).
## 🛠️ How Can I Contribute?
## Pull Request Guidelines
### 1️⃣ Reporting Bugs or Feature Requests
- Check the [issue tracker](#) to avoid duplicates.
- Use issue templates (if available).
- Provide detailed, relevant information and steps to reproduce bugs.
### 📝 PR Checklist
- [ ] Branch from the main branch
- [ ] Update documentation if needed
- [ ] Manually verify all new functionality works as expected
- [ ] Keep PRs focused and atomic
### 2️⃣ Code Contributions
1. Fork the repository.
2. Create a feature or fix branch.
3. Write and test your code.
4. Submit a pull request (PR).
### 👀 Review Process
1. Manually test the changes
2. At least one maintainer review required
3. Address all review comments
4. Maintain clean commit history
### 3️⃣ Join as a Core Contributor
Interested in maintaining and growing the project? Fill out our [Contributor Application Form](https://forms.gle/TBSteXSDCtBDwr5m7).
## Coding Standards
---
### 💻 General Guidelines
- Follow existing code style
- Comment complex logic
- Keep functions focused and small
- Use meaningful variable names
- Lint your code. This repo contains a pre-commit-hook that will verify your code is linted properly,
so set up your IDE to do that for you!
## ✅ Pull Request Guidelines
## Development Setup
### PR Checklist
- Branch from the **main** branch.
- Update documentation, if needed.
- Test all functionality manually.
- Focus on one feature/bug per PR.
### 🔄 Initial Setup
1. Clone the repository:
```bash
git clone https://github.com/coleam00/bolt.new-any-llm.git
```
### Review Process
1. Manual testing by reviewers.
2. At least one maintainer review required.
3. Address review comments.
4. Maintain a clean commit history.
2. Install dependencies:
```bash
pnpm install
```
---
3. Set up environment variables:
- Rename `.env.example` to `.env.local`
- Add your LLM API keys (only set the ones you plan to use):
```bash
GROQ_API_KEY=XXX
HuggingFace_API_KEY=XXX
OPENAI_API_KEY=XXX
ANTHROPIC_API_KEY=XXX
...
```
- Optionally set debug level:
```bash
VITE_LOG_LEVEL=debug
```
## 📏 Coding Standards
- Optionally set context size:
```bash
DEFAULT_NUM_CTX=32768
```
### General Guidelines
- Follow existing code style.
- Comment complex logic.
- Keep functions small and focused.
- Use meaningful variable names.
Some Example Context Values for the qwen2.5-coder:32b models are.
---
* DEFAULT_NUM_CTX=32768 - Consumes 36GB of VRAM
* DEFAULT_NUM_CTX=24576 - Consumes 32GB of VRAM
* DEFAULT_NUM_CTX=12288 - Consumes 26GB of VRAM
* DEFAULT_NUM_CTX=6144 - Consumes 24GB of VRAM
## 🖥️ Development Setup
**Important**: Never commit your `.env.local` file to version control. It's already included in .gitignore.
### 1️⃣ Initial Setup
- Clone the repository:
```bash
git clone https://github.com/stackblitz-labs/bolt.diy.git
```
- Install dependencies:
```bash
pnpm install
```
- Set up environment variables:
1. Rename `.env.example` to `.env.local`.
2. Add your API keys:
```bash
GROQ_API_KEY=XXX
HuggingFace_API_KEY=XXX
OPENAI_API_KEY=XXX
...
```
3. Optionally set:
- Debug level: `VITE_LOG_LEVEL=debug`
- Context size: `DEFAULT_NUM_CTX=32768`
### 🚀 Running the Development Server
**Note**: Never commit your `.env.local` file to version control. It’s already in `.gitignore`.
### 2️⃣ Run Development Server
```bash
pnpm run dev
```
**Tip**: Use **Google Chrome Canary** for local testing.
**Note**: You will need Google Chrome Canary to run this locally if you use Chrome! It's an easy install and a good browser for web development anyway.
---
## Testing
## 🧪 Testing
Run the test suite with:
```bash
pnpm test
```
## Deployment
---
To deploy the application to Cloudflare Pages:
## 🚀 Deployment
### Deploy to Cloudflare Pages
```bash
pnpm run deploy
```
Ensure you have required permissions and that Wrangler is configured.
Make sure you have the necessary permissions and Wrangler is correctly configured for your Cloudflare account.
---
# Docker Deployment Documentation
## 🐳 Docker Deployment
This guide outlines various methods for building and deploying the application using Docker.
This section outlines the methods for deploying the application using Docker. The processes for **Development** and **Production** are provided separately for clarity.
## Build Methods
---
### 1. Using Helper Scripts
### 🧑‍💻 Development Environment
NPM scripts are provided for convenient building:
#### Build Options
**Option 1: Helper Scripts**
```bash
# Development build
npm run dockerbuild
```
**Option 2: Direct Docker Build Command**
```bash
docker build . --target bolt-ai-development
```
**Option 3: Docker Compose Profile**
```bash
docker-compose --profile development up
```
#### Running the Development Container
```bash
docker run -p 5173:5173 --env-file .env.local bolt-ai:development
```
---
### 🏭 Production Environment
#### Build Options
**Option 1: Helper Scripts**
```bash
# Production build
npm run dockerbuild:prod
```
### 2. Direct Docker Build Commands
You can use Docker's target feature to specify the build environment:
**Option 2: Direct Docker Build Command**
```bash
# Development build
docker build . --target bolt-ai-development
# Production build
docker build . --target bolt-ai-production
```
### 3. Docker Compose with Profiles
Use Docker Compose profiles to manage different environments:
**Option 3: Docker Compose Profile**
```bash
# Development environment
docker-compose --profile development up
# Production environment
docker-compose --profile production up
```
## Running the Application
After building using any of the methods above, run the container with:
#### Running the Production Container
```bash
# Development
docker run -p 5173:5173 --env-file .env.local bolt-ai:development
# Production
docker run -p 5173:5173 --env-file .env.local bolt-ai:production
```
## Deployment with Coolify
---
[Coolify](https://github.com/coollabsio/coolify) provides a straightforward deployment process:
### Coolify Deployment
1. Import your Git repository as a new project
2. Select your target environment (development/production)
3. Choose "Docker Compose" as the Build Pack
4. Configure deployment domains
5. Set the custom start command:
For an easy deployment process, use [Coolify](https://github.com/coollabsio/coolify):
1. Import your Git repository into Coolify.
2. Choose **Docker Compose** as the build pack.
3. Configure environment variables (e.g., API keys).
4. Set the start command:
```bash
docker compose --profile production up
```
6. Configure environment variables
- Add necessary AI API keys
- Adjust other environment variables as needed
7. Deploy the application
## VS Code Integration
---
The `docker-compose.yaml` configuration is compatible with VS Code dev containers:
## 🛠️ VS Code Dev Containers Integration
1. Open the command palette in VS Code
2. Select the dev container configuration
3. Choose the "development" profile from the context menu
The `docker-compose.yaml` configuration is compatible with **VS Code Dev Containers**, making it easy to set up a development environment directly in Visual Studio Code.
## Environment Files
### Steps to Use Dev Containers
Ensure you have the appropriate `.env.local` file configured before running the containers. This file should contain:
- API keys
- Environment-specific configurations
- Other required environment variables
1. Open the command palette in VS Code (`Ctrl+Shift+P` or `Cmd+Shift+P` on macOS).
2. Select **Dev Containers: Reopen in Container**.
3. Choose the **development** profile when prompted.
4. VS Code will rebuild the container and open it with the pre-configured environment.
## Notes
---
- Port 5173 is exposed and mapped for both development and production environments
- Environment variables are loaded from `.env.local`
- Different profiles (development/production) can be used for different deployment scenarios
- The configuration supports both local development and production deployment
## 🔑 Environment Variables
Ensure `.env.local` is configured correctly with:
- API keys.
- Context-specific configurations.
Example for the `DEFAULT_NUM_CTX` variable:
```bash
DEFAULT_NUM_CTX=24576 # Uses 32GB VRAM
```

84
FAQ.md
View File

@ -1,8 +1,7 @@
[![bolt.diy: AI-Powered Full-Stack Web Development in the Browser](./public/social_preview_index.jpg)](https://bolt.diy)
# Frequently Asked Questions (FAQ)
# bolt.diy
## Recommended Models for bolt.diy
<details>
<summary><strong>What are the best models for bolt.diy?</strong></summary>
For the best experience with bolt.diy, we recommend using the following models:
@ -13,51 +12,80 @@ For the best experience with bolt.diy, we recommend using the following models:
- **Qwen 2.5 Coder 32b**: Best model for self-hosting with reasonable hardware requirements
**Note**: Models with less than 7b parameters typically lack the capability to properly interact with bolt!
</details>
## FAQ
<details>
<summary><strong>How do I get the best results with bolt.diy?</strong></summary>
### How do I get the best results with bolt.diy?
- **Be specific about your stack**:
Mention the frameworks or libraries you want to use (e.g., Astro, Tailwind, ShadCN) in your initial prompt. This ensures that bolt.diy scaffolds the project according to your preferences.
- **Be specific about your stack**: If you want to use specific frameworks or libraries (like Astro, Tailwind, ShadCN, or any other popular JavaScript framework), mention them in your initial prompt to ensure bolt scaffolds the project accordingly.
- **Use the enhance prompt icon**:
Before sending your prompt, click the *enhance* icon to let the AI refine your prompt. You can edit the suggested improvements before submitting.
- **Use the enhance prompt icon**: Before sending your prompt, try clicking the 'enhance' icon to have the AI model help you refine your prompt, then edit the results before submitting.
- **Scaffold the basics first, then add features**:
Ensure the foundational structure of your application is in place before introducing advanced functionality. This helps bolt.diy establish a solid base to build on.
- **Scaffold the basics first, then add features**: Make sure the basic structure of your application is in place before diving into more advanced functionality. This helps Bolt.diy understand the foundation of your project and ensure everything is wired up right before building out more advanced functionality.
- **Batch simple instructions**:
Combine simple tasks into a single prompt to save time and reduce API credit consumption. For example:
*"Change the color scheme, add mobile responsiveness, and restart the dev server."*
</details>
- **Batch simple instructions**: Save time by combining simple instructions into one message. For example, you can ask Bolt.diy to change the color scheme, add mobile responsiveness, and restart the dev server, all in one go saving you time and reducing API credit consumption significantly.
<details>
<summary><strong>How do I contribute to bolt.diy?</strong></summary>
### Why are there so many open issues/pull requests?
Check out our [Contribution Guide](CONTRIBUTING.md) for more details on how to get involved!
</details>
bolt.diy was started simply to showcase how to edit an open source project and to do something cool with local LLMs on my (@ColeMedin) YouTube channel! However, it quickly grew into a massive community project that I am working hard to keep up with the demand of by forming a team of maintainers and getting as many people involved as I can. That effort is going well and all of our maintainers are ABSOLUTE rockstars, but it still takes time to organize everything so we can efficiently get through all the issues and PRs. But rest assured, we are working hard and even working on some partnerships behind the scenes to really help this project take off!
<details>
<summary><strong>What are the future plans for bolt.diy?</strong></summary>
### How do local LLMs fair compared to larger models like Claude 3.5 Sonnet for bolt.diy/bolt.new?
Visit our [Roadmap](https://roadmap.sh/r/ottodev-roadmap-2ovzo) for the latest updates.
New features and improvements are on the way!
</details>
As much as the gap is quickly closing between open source and massive close source models, you’re still going to get the best results with the very large models like GPT-4o, Claude 3.5 Sonnet, and DeepSeek Coder V2 236b. This is one of the big tasks we have at hand - figuring out how to prompt better, use agents, and improve the platform as a whole to make it work better for even the smaller local LLMs!
<details>
<summary><strong>Why are there so many open issues/pull requests?</strong></summary>
### I'm getting the error: "There was an error processing this request"
bolt.diy began as a small showcase project on @ColeMedin's YouTube channel to explore editing open-source projects with local LLMs. However, it quickly grew into a massive community effort!
If you see this error within bolt.diy, that is just the application telling you there is a problem at a high level, and this could mean a number of different things. To find the actual error, please check BOTH the terminal where you started the application (with Docker or pnpm) and the developer console in the browser. For most browsers, you can access the developer console by pressing F12 or right clicking anywhere in the browser and selecting “Inspect”. Then go to the “console” tab in the top right.
We're forming a team of maintainers to manage demand and streamline issue resolution. The maintainers are rockstars, and we're also exploring partnerships to help the project thrive.
</details>
### I'm getting the error: "x-api-key header missing"
<details>
<summary><strong>How do local LLMs compare to larger models like Claude 3.5 Sonnet for bolt.diy?</strong></summary>
We have seen this error a couple times and for some reason just restarting the Docker container has fixed it. This seems to be Ollama specific. Another thing to try is try to run bolt.diy with Docker or pnpm, whichever you didn’t run first. We are still on the hunt for why this happens once and a while!
While local LLMs are improving rapidly, larger models like GPT-4o, Claude 3.5 Sonnet, and DeepSeek Coder V2 236b still offer the best results for complex applications. Our ongoing focus is to improve prompts, agents, and the platform to better support smaller local LLMs.
</details>
### I'm getting a blank preview when bolt.diy runs my app!
<details>
<summary><strong>Common Errors and Troubleshooting</strong></summary>
We promise you that we are constantly testing new PRs coming into bolt.diy and the preview is core functionality, so the application is not broken! When you get a blank preview or don’t get a preview, this is generally because the LLM hallucinated bad code or incorrect commands. We are working on making this more transparent so it is obvious. Sometimes the error will appear in developer console too so check that as well.
### **"There was an error processing this request"**
This generic error message means something went wrong. Check both:
- The terminal (if you started the app with Docker or `pnpm`).
- The developer console in your browser (press `F12` or right-click > *Inspect*, then go to the *Console* tab).
### Everything works but the results are bad
### **"x-api-key header missing"**
This error is sometimes resolved by restarting the Docker container.
If that doesn't work, try switching from Docker to `pnpm` or vice versa. We're actively investigating this issue.
This goes to the point above about how local LLMs are getting very powerful but you still are going to see better (sometimes much better) results with the largest LLMs like GPT-4o, Claude 3.5 Sonnet, and DeepSeek Coder V2 236b. If you are using smaller LLMs like Qwen-2.5-Coder, consider it more experimental and educational at this point. It can build smaller applications really well, which is super impressive for a local LLM, but for larger scale applications you want to use the larger LLMs still!
### **Blank preview when running the app**
A blank preview often occurs due to hallucinated bad code or incorrect commands.
To troubleshoot:
- Check the developer console for errors.
- Remember, previews are core functionality, so the app isn't broken! We're working on making these errors more transparent.
### Received structured exception #0xc0000005: access violation
### **"Everything works, but the results are bad"**
Local LLMs like Qwen-2.5-Coder are powerful for small applications but still experimental for larger projects. For better results, consider using larger models like GPT-4o, Claude 3.5 Sonnet, or DeepSeek Coder V2 236b.
### **"Received structured exception #0xc0000005: access violation"**
If you are getting this, you are probably on Windows. The fix is generally to update the [Visual C++ Redistributable](https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170)
### How to add an LLM:
### **"Miniflare or Wrangler errors in Windows"**
You will need to make sure you have the latest version of Visual Studio C++ installed (14.40.33816), more information here https://github.com/stackblitz-labs/bolt.diy/issues/19.
</details>
To make new LLMs available to use in this version of bolt.new, head on over to `app/utils/constants.ts` and find the constant MODEL_LIST. Each element in this array is an object that has the model ID for the name (get this from the provider's API documentation), a label for the frontend model dropdown, and the provider.
---
By default, many providers are already implemented, but the YouTube video for this repo covers how to extend this to work with more providers if you wish!
When you add a new model to the MODEL_LIST array, it will immediately be available to use when you run the app locally or reload it.
Got more questions? Feel free to reach out or open an issue in our GitHub repo!

4
README.md
View File

@ -93,6 +93,7 @@ Let's get you up and running with the stable version of Bolt.DIY!
[![Download Latest Release](https://img.shields.io/github/v/release/stackblitz-labs/bolt.diy?label=Download%20Bolt&sort=semver)](https://github.com/stackblitz-labs/bolt.diy/releases/latest/download/bolt.diy.zip) ← Click here to download the latest version!
## Prerequisites
Before you begin, you'll need to install two important pieces of software:
@ -199,8 +200,6 @@ For providers that support custom base URLs (such as Ollama or LM Studio), follo
- LM Studio
- OpenAILike
## Setup Using Git (For Developers only)
This method is recommended for developers who want to:
@ -229,7 +228,6 @@ This method is recommended for developers who want to:
```bash
git checkout main
```
4. **Install Dependencies**:
```bash
pnpm install

285
docs/docs/CONTRIBUTING.md
View File

@ -1,246 +1,219 @@
# Contribution Guidelines
Welcome! This guide provides all the details you need to contribute effectively to the project. Thank you for helping us make **bolt.diy** a better tool for developers worldwide. 💡
---
## 📋 Table of Contents
- [Code of Conduct](#code-of-conduct)
- [How Can I Contribute?](#how-can-i-contribute)
- [Pull Request Guidelines](#pull-request-guidelines)
- [Coding Standards](#coding-standards)
- [Development Setup](#development-setup)
- [Deploymnt with Docker](#docker-deployment-documentation)
1. [Code of Conduct](#code-of-conduct)
2. [How Can I Contribute?](#how-can-i-contribute)
3. [Pull Request Guidelines](#pull-request-guidelines)
4. [Coding Standards](#coding-standards)
5. [Development Setup](#development-setup)
6. [Testing](#testing)
7. [Deployment](#deployment)
8. [Docker Deployment](#docker-deployment)
9. [VS Code Dev Containers Integration](#vs-code-dev-containers-integration)
---
## Code of Conduct
## 🛡️ Code of Conduct
This project and everyone participating in it is governed by our Code of Conduct. By participating, you are expected to uphold this code. Please report unacceptable behavior to the project maintainers.
This project is governed by our **Code of Conduct**. By participating, you agree to uphold this code. Report unacceptable behavior to the project maintainers.
---
## How Can I Contribute?
## 🛠️ How Can I Contribute?
### 🐞 Reporting Bugs and Feature Requests
- Check the issue tracker to avoid duplicates
- Use the issue templates when available
- Include as much relevant information as possible
- For bugs, add steps to reproduce the issue
### 1️⃣ Reporting Bugs or Feature Requests
- Check the [issue tracker](#) to avoid duplicates.
- Use issue templates (if available).
- Provide detailed, relevant information and steps to reproduce bugs.
### 🔧 Code Contributions
1. Fork the repository
2. Create a new branch for your feature/fix
3. Write your code
4. Submit a pull request
### 2️⃣ Code Contributions
1. Fork the repository.
2. Create a feature or fix branch.
3. Write and test your code.
4. Submit a pull request (PR).
### ✨ Becoming a Core Contributor
We're looking for dedicated contributors to help maintain and grow this project. If you're interested in becoming a core contributor, please fill out our [Contributor Application Form](https://forms.gle/TBSteXSDCtBDwr5m7).
### 3️⃣ Join as a Core Contributor
Interested in maintaining and growing the project? Fill out our [Contributor Application Form](https://forms.gle/TBSteXSDCtBDwr5m7).
---
## Pull Request Guidelines
## ✅ Pull Request Guidelines
### 📝 PR Checklist
- [ ] Branch from the main branch
- [ ] Update documentation if needed
- [ ] Manually verify all new functionality works as expected
- [ ] Keep PRs focused and atomic
### PR Checklist
- Branch from the **main** branch.
- Update documentation, if needed.
- Test all functionality manually.
- Focus on one feature/bug per PR.
### 👀 Review Process
1. Manually test the changes
2. At least one maintainer review required
3. Address all review comments
4. Maintain clean commit history
### Review Process
1. Manual testing by reviewers.
2. At least one maintainer review required.
3. Address review comments.
4. Maintain a clean commit history.
---
## Coding Standards
## 📏 Coding Standards
### 💻 General Guidelines
- Follow existing code style
- Comment complex logic
- Keep functions focused and small
- Use meaningful variable names
### General Guidelines
- Follow existing code style.
- Comment complex logic.
- Keep functions small and focused.
- Use meaningful variable names.
---
## Development Setup
## 🖥️ Development Setup
### 🔄 Initial Setup
1. Clone the repository:
```bash
git clone https://github.com/stackblitz-labs/bolt.diy.git
```
### 1️⃣ Initial Setup
- Clone the repository:
```bash
git clone https://github.com/stackblitz-labs/bolt.diy.git
```
- Install dependencies:
```bash
pnpm install
```
- Set up environment variables:
1. Rename `.env.example` to `.env.local`.
2. Add your API keys:
```bash
GROQ_API_KEY=XXX
HuggingFace_API_KEY=XXX
OPENAI_API_KEY=XXX
...
```
3. Optionally set:
- Debug level: `VITE_LOG_LEVEL=debug`
- Context size: `DEFAULT_NUM_CTX=32768`
2. Install dependencies:
```bash
pnpm install
```
**Note**: Never commit your `.env.local` file to version control. It’s already in `.gitignore`.
3. Set up environment variables:
- Rename `.env.example` to `.env.local`
- Add your LLM API keys (only set the ones you plan to use):
```bash
GROQ_API_KEY=XXX
HuggingFace_API_KEY=XXX
OPENAI_API_KEY=XXX
ANTHROPIC_API_KEY=XXX
...
```
- Optionally set debug level:
```bash
VITE_LOG_LEVEL=debug
```
- Optionally set context size:
```bash
DEFAULT_NUM_CTX=32768
```
Some Example Context Values for the qwen2.5-coder:32b models are.
* DEFAULT_NUM_CTX=32768 - Consumes 36GB of VRAM
* DEFAULT_NUM_CTX=24576 - Consumes 32GB of VRAM
* DEFAULT_NUM_CTX=12288 - Consumes 26GB of VRAM
* DEFAULT_NUM_CTX=6144 - Consumes 24GB of VRAM
**Important**: Never commit your `.env.local` file to version control. It's already included in .gitignore.
### 🚀 Running the Development Server
### 2️⃣ Run Development Server
```bash
pnpm run dev
```
**Note**: You will need Google Chrome Canary to run this locally if you use Chrome! It's an easy install and a good browser for web development anyway.
**Tip**: Use **Google Chrome Canary** for local testing.
---
## Testing
## 🧪 Testing
Run the test suite with:
```bash
pnpm test
```
---
## Deployment
To deploy the application to Cloudflare Pages:
## 🚀 Deployment
### Deploy to Cloudflare Pages
```bash
pnpm run deploy
```
Make sure you have the necessary permissions and Wrangler is correctly configured for your Cloudflare account.
Ensure you have required permissions and that Wrangler is configured.
---
# Docker Deployment Documentation
## 🐳 Docker Deployment
This guide outlines various methods for building and deploying the application using Docker.
This section outlines the methods for deploying the application using Docker. The processes for **Development** and **Production** are provided separately for clarity.
## Build Methods
---
### 1. Using Helper Scripts
### 🧑‍💻 Development Environment
NPM scripts are provided for convenient building:
#### Build Options
**Option 1: Helper Scripts**
```bash
# Development build
npm run dockerbuild
```
**Option 2: Direct Docker Build Command**
```bash
docker build . --target bolt-ai-development
```
**Option 3: Docker Compose Profile**
```bash
docker-compose --profile development up
```
#### Running the Development Container
```bash
docker run -p 5173:5173 --env-file .env.local bolt-ai:development
```
---
### 🏭 Production Environment
#### Build Options
**Option 1: Helper Scripts**
```bash
# Production build
npm run dockerbuild:prod
```
### 2. Direct Docker Build Commands
You can use Docker's target feature to specify the build environment:
**Option 2: Direct Docker Build Command**
```bash
# Development build
docker build . --target bolt-ai-development
# Production build
docker build . --target bolt-ai-production
```
### 3. Docker Compose with Profiles
Use Docker Compose profiles to manage different environments:
**Option 3: Docker Compose Profile**
```bash
# Development environment
docker-compose --profile development up
# Production environment
docker-compose --profile production up
```
---
## Running the Application
After building using any of the methods above, run the container with:
#### Running the Production Container
```bash
# Development
docker run -p 5173:5173 --env-file .env.local bolt-ai:development
# Production
docker run -p 5173:5173 --env-file .env.local bolt-ai:production
```
---
## Deployment with Coolify
### Coolify Deployment
[Coolify](https://github.com/coollabsio/coolify) provides a straightforward deployment process:
1. Import your Git repository as a new project
2. Select your target environment (development/production)
3. Choose "Docker Compose" as the Build Pack
4. Configure deployment domains
5. Set the custom start command:
For an easy deployment process, use [Coolify](https://github.com/coollabsio/coolify):
1. Import your Git repository into Coolify.
2. Choose **Docker Compose** as the build pack.
3. Configure environment variables (e.g., API keys).
4. Set the start command:
```bash
docker compose --profile production up
```
6. Configure environment variables
- Add necessary AI API keys
- Adjust other environment variables as needed
7. Deploy the application
---
## VS Code Integration
## 🛠️ VS Code Dev Containers Integration
The `docker-compose.yaml` configuration is compatible with VS Code dev containers:
The `docker-compose.yaml` configuration is compatible with **VS Code Dev Containers**, making it easy to set up a development environment directly in Visual Studio Code.
1. Open the command palette in VS Code
2. Select the dev container configuration
3. Choose the "development" profile from the context menu
### Steps to Use Dev Containers
1. Open the command palette in VS Code (`Ctrl+Shift+P` or `Cmd+Shift+P` on macOS).
2. Select **Dev Containers: Reopen in Container**.
3. Choose the **development** profile when prompted.
4. VS Code will rebuild the container and open it with the pre-configured environment.
---
## Environment Files
## 🔑 Environment Variables
Ensure you have the appropriate `.env.local` file configured before running the containers. This file should contain:
- API keys
- Environment-specific configurations
- Other required environment variables
Ensure `.env.local` is configured correctly with:
- API keys.
- Context-specific configurations.
---
## DEFAULT_NUM_CTX
The `DEFAULT_NUM_CTX` environment variable can be used to limit the maximum number of context values used by the qwen2.5-coder model. For example, to limit the context to 24576 values (which uses 32GB of VRAM), set `DEFAULT_NUM_CTX=24576` in your `.env.local` file.
First off, thank you for considering contributing to bolt.diy! This fork aims to expand the capabilities of the original project by integrating multiple LLM providers and enhancing functionality. Every contribution helps make bolt.diy a better tool for developers worldwide.
---
## Notes
- Port 5173 is exposed and mapped for both development and production environments
- Environment variables are loaded from `.env.local`
- Different profiles (development/production) can be used for different deployment scenarios
- The configuration supports both local development and production deployment
Example for the `DEFAULT_NUM_CTX` variable:
```bash
DEFAULT_NUM_CTX=24576 # Uses 32GB VRAM
```

243
docs/docs/index.md
View File

@ -3,14 +3,17 @@ bolt.diy allows you to choose the LLM that you use for each prompt! Currently, y
## Table of Contents
- [Join the community!](#join-the-community)
- [What's bolt.diy](#whats-boltdiy)
- [What Makes bolt.diy Different](#what-makes-boltdiy-different)
- [Features](#features)
- [Setup](#setup)
- [Run with Docker](#run-with-docker)
- [Using Helper Scripts](#1a-using-helper-scripts)
- [Direct Docker Build Commands](#1b-direct-docker-build-commands-alternative-to-using-npm-scripts)
- [Docker Compose with Profiles](#2-docker-compose-with-profiles-to-run-the-container)
- [Run Without Docker](#run-without-docker)
- [Prerequisites](#prerequisites)
- [Clone the Repository](#clone-the-repository)
- [Entering API Keys](#entering-api-keys)
- [1. Set API Keys in the `.env.local` File](#1-set-api-keys-in-the-envlocal-file)
- [2. Configure API Keys Directly in the Application](#2-configure-api-keys-directly-in-the-application)
- [Run the Application](#run-the-application)
- [Option 1: Without Docker](#option-1-without-docker)
- [Option 2: With Docker](#option-2-with-docker)
- [Update Your Local Version to the Latest](#update-your-local-version-to-the-latest)
- [Adding New LLMs](#adding-new-llms)
- [Available Scripts](#available-scripts)
- [Development](#development)
@ -24,72 +27,65 @@ bolt.diy allows you to choose the LLM that you use for each prompt! Currently, y
---
## Whats bolt.diy
## Features
bolt.diy is an AI-powered web development agent that allows you to prompt, run, edit, and deploy full-stack applications directly from your browser—no local setup required. If you're here to build your own AI-powered web dev agent using the Bolt open source codebase, [click here to get started!](./CONTRIBUTING.md)
---
## What Makes bolt.diy Different
Claude, v0, etc are incredible- but you can't install packages, run backends, or edit code. That’s where bolt.diy stands out:
- **Full-Stack in the Browser**: bolt.diy integrates cutting-edge AI models with an in-browser development environment powered by **StackBlitz’s WebContainers**. This allows you to:
- Install and run npm tools and libraries (like Vite, Next.js, and more)
- Run Node.js servers
- Interact with third-party APIs
- Deploy to production from chat
- Share your work via a URL
- **AI with Environment Control**: Unlike traditional dev environments where the AI can only assist in code generation, bolt.diy gives AI models **complete control** over the entire environment including the filesystem, node server, package manager, terminal, and browser console. This empowers AI agents to handle the whole app lifecycle—from creation to deployment.
Whether you’re an experienced developer, a PM, or a designer, bolt.diy allows you to easily build production-grade full-stack applications.
For developers interested in building their own AI-powered development tools with WebContainers, check out the open-source Bolt codebase in this repo!
- **AI-powered full-stack web development** directly in your browser.
- **Support for multiple LLMs** with an extensible architecture to integrate additional models.
- **Attach images to prompts** for better contextual understanding.
- **Integrated terminal** to view output of LLM-run commands.
- **Revert code to earlier versions** for easier debugging and quicker changes.
- **Download projects as ZIP** for easy portability.
- **Integration-ready Docker support** for a hassle-free setup.
---
## Setup
Many of you are new users to installing software from Github. If you have any installation troubles reach out and submit an "issue" using the links above, or feel free to enhance this documentation by forking, editing the instructions, and doing a pull request.
If you're new to installing software from GitHub, don't worry! If you encounter any issues, feel free to submit an "issue" using the provided links or improve this documentation by forking the repository, editing the instructions, and submitting a pull request. The following instruction will help you get the stable branch up and running on your local machine in no time.
1. [Install Git from](https://git-scm.com/downloads)
### Prerequisites
2. [Install Node.js from](https://nodejs.org/en/download/)
1. **Install Git**: [Download Git](https://git-scm.com/downloads)
2. **Install Node.js**: [Download Node.js](https://nodejs.org/en/download/)
Pay attention to the installer notes after completion.
- After installation, the Node.js path is usually added to your system automatically. To verify:
- **Windows**: Search for "Edit the system environment variables," click "Environment Variables," and check if `Node.js` is in the `Path` variable.
- **Mac/Linux**: Open a terminal and run:
```bash
echo $PATH
```
Look for `/usr/local/bin` in the output.
On all operating systems, the path to Node.js should automatically be added to your system path. But you can check your path if you want to be sure. On Windows, you can search for "edit the system environment variables" in your system, select "Environment Variables..." once you are in the system properties, and then check for a path to Node in your "Path" system variable. On a Mac or Linux machine, it will tell you to check if /usr/local/bin is in your $PATH. To determine if usr/local/bin is included in $PATH open your Terminal and run:
### Clone the Repository
```
echo $PATH .
Alternatively, you can download the latest version of the project directly from the [Releases Page](https://github.com/stackblitz-labs/bolt.diy/releases/latest). Simply download the .zip file, extract it, and proceed with the setup instructions below. If you are comfertiable using git then run the command below.
Clone the repository using Git:
```bash
git clone -b stable https://github.com/stackblitz-labs/bolt.diy
```
If you see usr/local/bin in the output then you're good to go.
---
3. Clone the repository (if you haven't already) by opening a Terminal window (or CMD with admin permissions) and then typing in this:
### Entering API Keys
```
git clone https://github.com/stackblitz-labs/bolt.diy.git
```
There are two ways to configure your API keys in bolt.diy:
3. Rename .env.example to .env.local and add your LLM API keys. You will find this file on a Mac at "[your name]/bolt.diy/.env.example". For Windows and Linux the path will be similar.
#### 1. Set API Keys in the `.env.local` File
![image](https://github.com/user-attachments/assets/7e6a532c-2268-401f-8310-e8d20c731328)
When setting up the application, you will need to add your API keys for the LLMs you wish to use. You can do this by renaming the `.env.example` file to `.env.local` and adding your API keys there.
If you can't see the file indicated above, its likely you can't view hidden files. On Mac, open a Terminal window and enter this command below. On Windows, you will see the hidden files option in File Explorer Settings. A quick Google search will help you if you are stuck here.
- On **Mac**, you can find the file at `[your name]/bolt.diy/.env.example`.
- On **Windows/Linux**, the path will be similar.
```
If you can't see the file, it's likely because hidden files are not being shown. On **Mac**, open a Terminal window and enter the following command to show hidden files:
```bash
defaults write com.apple.finder AppleShowAllFiles YES
```
**NOTE**: you only have to set the ones you want to use and Ollama doesn't need an API key because it runs locally on your computer:
[Get your GROQ API Key here](https://console.groq.com/keys)
[Get your Open AI API Key by following these instructions](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)
Get your Anthropic API Key in your [account settings](https://console.anthropic.com/settings/keys)
Make sure to add your API keys for each provider you want to use, for example:
```
GROQ_API_KEY=XXX
@ -97,81 +93,108 @@ OPENAI_API_KEY=XXX
ANTHROPIC_API_KEY=XXX
```
Optionally, you can set the debug level:
Once you've set your keys, you can proceed with running the app. You will set these keys up during the initial setup, and you can revisit and update them later after the app is running.
```
VITE_LOG_LEVEL=debug
```
**Note**: Never commit your `.env.local` file to version control. It’s already included in the `.gitignore`.
**Important**: Never commit your `.env.local` file to version control. It's already included in .gitignore.
#### 2. Configure API Keys Directly in the Application
## Run with Docker
Alternatively, you can configure your API keys directly in the application once it's running. To do this:
Prerequisites:
1. Launch the application and navigate to the provider selection dropdown.
2. Select the provider you wish to configure.
3. Click the pencil icon next to the selected provider.
4. Enter your API key in the provided field.
Git and Node.js as mentioned above, as well as Docker: https://www.docker.com/
This method allows you to easily add or update your keys without needing to modify files directly.
### 1a. Using Helper Scripts
Once you've configured your keys, the application will be ready to use the selected LLMs.
NPM scripts are provided for convenient building:
```bash
# Development build
npm run dockerbuild
# Production build
npm run dockerbuild:prod
```
### 1b. Direct Docker Build Commands (alternative to using NPM scripts)
You can use Docker's target feature to specify the build environment instead of using NPM scripts if you wish:
```bash
# Development build
docker build . --target bolt-ai-development
# Production build
docker build . --target bolt-ai-production
```
### 2. Docker Compose with Profiles to Run the Container
Use Docker Compose profiles to manage different environments:
```bash
# Development environment
docker-compose --profile development up
# Production environment
docker-compose --profile production up
```
When you run the Docker Compose command with the development profile, any changes you
make on your machine to the code will automatically be reflected in the site running
on the container (i.e. hot reloading still applies!).
---
## Run Without Docker
## Run the Application
1. Install dependencies using Terminal (or CMD in Windows with admin permissions):
### Option 1: Without Docker
```
pnpm install
```
1. **Install Dependencies**:
```bash
pnpm install
```
If `pnpm` is not installed, install it using:
```bash
sudo npm install -g pnpm
```
If you get an error saying "command not found: pnpm" or similar, then that means pnpm isn't installed. You can install it via this:
2. **Start the Application**:
```bash
pnpm run dev
```
This will start the Remix Vite development server. You will need Google Chrome Canary to run this locally if you use Chrome! It's an easy install and a good browser for web development anyway.
```
sudo npm install -g pnpm
```
### Option 2: With Docker
2. Start the application with the command:
#### Prerequisites
- Ensure Git, Node.js, and Docker are installed: [Download Docker](https://www.docker.com/)
```bash
pnpm run dev
```
#### Steps
1. **Build the Docker Image**:
Use the provided NPM scripts:
```bash
npm run dockerbuild
```
Alternatively, use Docker commands directly:
```bash
docker build . --target bolt-ai-development
```
2. **Run the Container**:
Use Docker Compose profiles to manage environments:
```bash
docker-compose --profile development up
```
- With the development profile, changes to your code will automatically reflect in the running container (hot reloading).
---
### Update Your Local Version to the Latest
To keep your local version of bolt.diy up to date with the latest changes, follow these steps for your operating system:
#### 1. **Navigate to your project folder**
Navigate to the directory where you cloned the repository and open a terminal:
#### 2. **Fetch the Latest Changes**
Use Git to pull the latest changes from the main repository:
```bash
git pull origin main
```
#### 3. **Update Dependencies**
After pulling the latest changes, update the project dependencies by running the following command:
```bash
pnpm install
```
#### 4. **Rebuild and Start the Application**
- **If using Docker**, ensure you rebuild the Docker image to avoid using a cached version:
```bash
docker-compose --profile development up --build
```
- **If not using Docker**, you can start the application as usual with:
```bash
pnpm run dev
```
This ensures that you're running the latest version of bolt.diy and can take advantage of all the newest features and bug fixes.
---