Merge branch 'main' into qa-testing

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,21 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Screenshots of backend AND frontend terminal logs**
+If applicable, add screenshots to help explain your problem.

.github/ISSUE_TEMPLATE/custom.md

@@ -0,0 +1,10 @@
+---
+name: Custom issue template
+about: Describe this issue template's purpose here.
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

README.md

@@ -1,6 +1,6 @@
 # screenshot-to-code
 
-A simple tool to convert screenshots, mockups and Figma designs into clean, functional code using AI.
+A simple tool to convert screenshots, mockups and Figma designs into clean, functional code using AI. **Now supporting GPT-4O!**
 
 https://github.com/abi/screenshot-to-code/assets/23818/6cebadae-2fe3-4986-ac6a-8fb9db030045
 
@@ -15,8 +15,10 @@ Supported stacks:
 
 Supported AI models:
 
-- GPT-4 Vision
-- Claude 3 Sonnet (faster, and on par or better than GPT-4 vision for many inputs)
+- GPT-4O - Best model!
+- GPT-4 Turbo (Apr 2024)
+- GPT-4 Vision (Nov 2023)
+- Claude 3 Sonnet
 - DALL-E 3 for image generation
 
 See the [Examples](#-examples) section below for more demos.
@@ -82,7 +84,7 @@ The app will be up and running at http://localhost:5173. Note that you can't dev
 
 - **I'm running into an error when setting up the backend. How can I fix it?** [Try this](https://github.com/abi/screenshot-to-code/issues/3#issuecomment-1814777959). If that still doesn't work, open an issue.
 - **How do I get an OpenAI API key?** See https://github.com/abi/screenshot-to-code/blob/main/Troubleshooting.md
-- **How can I configure an OpenAI proxy?** - you can configure the OpenAI base URL if you need to use a proxy: Set OPENAI_BASE_URL in the `backend/.env` or directly in the UI in the settings dialog
+- **How can I configure an OpenAI proxy?** - If you're not able to access the OpenAI API directly (due to e.g. country restrictions), you can try a VPN or you can configure the OpenAI base URL to use a proxy: Set OPENAI_BASE_URL in the `backend/.env` or directly in the UI in the settings dialog. Make sure the URL has "v1" in the path so it should look like this:  `https://xxx.xxxxx.xxx/v1`
 - **How can I update the backend host that my front-end connects to?** - Configure VITE_HTTP_BACKEND_URL and VITE_WS_BACKEND_URL in front/.env.local For example, set VITE_HTTP_BACKEND_URL=http://124.10.20.1:7001
 - **Seeing UTF-8 errors when running the backend?** - On windows, open the .env file with notepad++, then go to Encoding and select UTF-8. 
 - **How can I provide feedback?** For feedback, feature requests and bug reports, open an issue or ping me on [Twitter](https://twitter.com/_abi_).

Troubleshooting.md

@@ -11,7 +11,8 @@ You don't need a ChatGPT Pro account. Screenshot to code uses API keys from your
 5. Go to Settings > Limits and check at the bottom of the page, your current tier has to be "Tier 1" to have GPT4 access
 <img width="900" alt="285636973-da38bd4d-8a78-4904-8027-ca67d729b933" src="https://github.com/abi/screenshot-to-code/assets/23818/8d07cd84-0cf9-4f88-bc00-80eba492eadf">
 
-6. Go to Screenshot to code and paste it in the Settings dialog under OpenAI key (gear icon). Your key is only stored in your browser. Never stored on our servers.
+6. Navigate to OpenAI [api keys](https://platform.openai.com/api-keys) page and create and copy a new secret key.
+7. Go to Screenshot to code and paste it in the Settings dialog under OpenAI key (gear icon). Your key is only stored in your browser. Never stored on our servers.
 
 ## Still not working?
 

backend/llm.py

@@ -13,6 +13,7 @@ from utils import pprint_prompt
 class Llm(Enum):
     GPT_4_VISION = "gpt-4-vision-preview"
     GPT_4_TURBO_2024_04_09 = "gpt-4-turbo-2024-04-09"
+    GPT_4O_2024_05_13 = "gpt-4o-2024-05-13"
     CLAUDE_3_SONNET = "claude-3-sonnet-20240229"
     CLAUDE_3_OPUS = "claude-3-opus-20240229"
     CLAUDE_3_HAIKU = "claude-3-haiku-20240307"
@@ -47,7 +48,11 @@ async def stream_openai_response(
     }
 
     # Add 'max_tokens' only if the model is a GPT4 vision or Turbo model
-    if model == Llm.GPT_4_VISION or model == Llm.GPT_4_TURBO_2024_04_09:
+    if (
+        model == Llm.GPT_4_VISION
+        or model == Llm.GPT_4_TURBO_2024_04_09
+        or model == Llm.GPT_4O_2024_05_13
+    ):
         params["max_tokens"] = 4096
 
     stream = await client.chat.completions.create(**params)  # type: ignore

backend/routes/evals.py

@@ -7,10 +7,13 @@ from evals.config import EVALS_DIR
 
 router = APIRouter()
 
+# Update this if the number of outputs generated per input changes
+N = 1
+
 
 class Eval(BaseModel):
     input: str
-    output: str
+    outputs: list[str]
 
 
 @router.get("/evals")
@@ -25,21 +28,27 @@ async def get_evals():
             input_file_path = os.path.join(input_dir, file)
             input_file = await image_to_data_url(input_file_path)
 
-            # Construct the corresponding output file name
-            output_file_name = file.replace(".png", ".html")
-            output_file_path = os.path.join(output_dir, output_file_name)
+            # Construct the corresponding output file names
+            output_file_names = [
+                file.replace(".png", f"_{i}.html") for i in range(0, N)
+            ]  # Assuming 3 outputs for each input
 
-            # Check if the output file exists
-            if os.path.exists(output_file_path):
-                with open(output_file_path, "r") as f:
-                    output_file_data = f.read()
-            else:
-                output_file_data = "Output file not found."
+            output_files_data: list[str] = []
+            for output_file_name in output_file_names:
+                output_file_path = os.path.join(output_dir, output_file_name)
+                # Check if the output file exists
+                if os.path.exists(output_file_path):
+                    with open(output_file_path, "r") as f:
+                        output_files_data.append(f.read())
+                else:
+                    output_files_data.append(
+                        "<html><h1>Output file not found.</h1></html>"
+                    )
 
             evals.append(
                 Eval(
                     input=input_file,
-                    output=output_file_data,
+                    outputs=output_files_data,
                 )
             )
 

backend/routes/generate_code.py

@@ -85,7 +85,7 @@ async def stream_code(websocket: WebSocket):
 
     # Read the model from the request. Fall back to default if not provided.
     code_generation_model_str = params.get(
-        "codeGenerationModel", Llm.GPT_4_VISION.value
+        "codeGenerationModel", Llm.GPT_4O_2024_05_13.value
     )
     try:
         code_generation_model = convert_frontend_str_to_llm(code_generation_model_str)
@@ -112,6 +112,7 @@ async def stream_code(websocket: WebSocket):
     if not openai_api_key and (
         code_generation_model == Llm.GPT_4_VISION
         or code_generation_model == Llm.GPT_4_TURBO_2024_04_09
+        or code_generation_model == Llm.GPT_4O_2024_05_13
     ):
         print("OpenAI API key not found")
         await throw_error(

backend/run_evals.py

@@ -13,8 +13,9 @@ from evals.config import EVALS_DIR
 from evals.core import generate_code_core
 from evals.utils import image_to_data_url
 
-STACK = "html_tailwind"
-MODEL = Llm.CLAUDE_3_SONNET
+STACK = "ionic_tailwind"
+MODEL = Llm.GPT_4O_2024_05_13
+N = 1  # Number of outputs to generate
 
 
 async def main():
@@ -28,16 +29,21 @@ async def main():
     for filename in evals:
         filepath = os.path.join(INPUT_DIR, filename)
         data_url = await image_to_data_url(filepath)
-        task = generate_code_core(image_url=data_url, stack=STACK, model=MODEL)
-        tasks.append(task)
+        for _ in range(N):  # Generate N tasks for each input
+            task = generate_code_core(image_url=data_url, stack=STACK, model=MODEL)
+            tasks.append(task)
 
     results = await asyncio.gather(*tasks)
 
     os.makedirs(OUTPUT_DIR, exist_ok=True)
 
-    for filename, content in zip(evals, results):
-        # File name is derived from the original filename in evals
-        output_filename = f"{os.path.splitext(filename)[0]}.html"
+    for i, content in enumerate(results):
+        # Calculate index for filename and output number
+        eval_index = i // N
+        output_number = i % N
+        filename = evals[eval_index]
+        # File name is derived from the original filename in evals with an added output number
+        output_filename = f"{os.path.splitext(filename)[0]}_{output_number}.html"
         output_filepath = os.path.join(OUTPUT_DIR, output_filename)
         with open(output_filepath, "w") as file:
             file.write(content)

backend/test_llm.py

@@ -24,6 +24,11 @@ class TestConvertFrontendStrToLlm(unittest.TestCase):
             Llm.GPT_4_TURBO_2024_04_09,
             "Should convert 'gpt-4-turbo-2024-04-09' to Llm.GPT_4_TURBO_2024_04_09",
         )
+        self.assertEqual(
+            convert_frontend_str_to_llm("gpt-4o-2024-05-13"),
+            Llm.GPT_4O_2024_05_13,
+            "Should convert 'gpt-4o-2024-05-13' to Llm.GPT_4O_2024_05_13",
+        )
 
     def test_convert_invalid_string_raises_exception(self):
         with self.assertRaises(ValueError):

frontend/src/App.tsx

@@ -63,7 +63,7 @@ function App() {
       isImageGenerationEnabled: true,
       editorTheme: EditorTheme.COBALT,
       generatedCodeConfig: Stack.HTML_TAILWIND,
-      codeGenerationModel: CodeGenerationModel.GPT_4_VISION,
+      codeGenerationModel: CodeGenerationModel.GPT_4O_2024_05_13,
       // Only relevant for hosted version
       isTermOfServiceAccepted: false,
     },
@@ -84,6 +84,15 @@ function App() {
 
   const wsRef = useRef<WebSocket>(null);
 
+  const showReactWarning =
+    selectedCodeGenerationModel ===
+      CodeGenerationModel.GPT_4_TURBO_2024_04_09 &&
+    settings.generatedCodeConfig === Stack.REACT_TAILWIND;
+
+  const showGpt4OMessage =
+    selectedCodeGenerationModel !== CodeGenerationModel.GPT_4O_2024_05_13 &&
+    appState === AppState.INITIAL;
+
   // Indicate coding state using the browser tab's favicon and title
   useBrowserTabIndicator(appState === AppState.CODING);
 
@@ -391,6 +400,22 @@ function App() {
             }
           />
 
+          {showReactWarning && (
+            <div className="text-sm bg-yellow-200 rounded p-2">
+              Sorry - React is not currently working with GPT-4 Turbo. Please
+              use GPT-4 Vision or Claude Sonnet. We are working on a fix.
+            </div>
+          )}
+
+          {showGpt4OMessage && (
+            <div className="rounded-lg p-2 bg-fuchsia-200">
+              <p className="text-gray-800 text-sm">
+                Now supporting GPT-4o. Higher quality and 2x faster. Give it a
+                try!
+              </p>
+            </div>
+          )}
+
           {appState !== AppState.CODE_READY && <TipLink />}
 
           {IS_RUNNING_ON_CLOUD && !settings.openAiApiKey && <OnboardingNote />}

frontend/src/components/evals/EvalsPage.tsx

@@ -4,7 +4,7 @@ import RatingPicker from "./RatingPicker";
 
 interface Eval {
   input: string;
-  output: string;
+  outputs: string[];
 }
 
 function EvalsPage() {
@@ -38,18 +38,22 @@ function EvalsPage() {
       <div className="flex flex-col gap-y-4 mt-4 mx-auto justify-center">
         {evals.map((e, index) => (
           <div className="flex flex-col justify-center" key={index}>
-            <div className="flex gap-x-2 justify-center">
+            <h2 className="font-bold text-lg ml-4">{index}</h2>
+            <div className="flex gap-x-2 justify-center ml-4">
+              {/* Update w if N changes to a fixed number like w-[600px] */}
               <div className="w-1/2 p-1 border">
-                <img src={e.input} />
-              </div>
-              <div className="w-1/2 p-1 border">
-                {/* Put output into an iframe */}
-                <iframe
-                  srcDoc={e.output}
-                  className="w-[1200px] h-[800px] transform scale-[0.60]"
-                  style={{ transformOrigin: "top left" }}
-                ></iframe>
+                <img src={e.input} alt={`Input for eval ${index}`} />
               </div>
+              {e.outputs.map((output, outputIndex) => (
+                <div className="w-1/2 p-1 border" key={outputIndex}>
+                  {/* Put output into an iframe */}
+                  <iframe
+                    srcDoc={output}
+                    className="w-[1200px] h-[800px] transform scale-[0.60]"
+                    style={{ transformOrigin: "top left" }}
+                  ></iframe>
+                </div>
+              ))}
             </div>
             <div className="ml-8 mt-4 flex justify-center">
               <RatingPicker

frontend/src/lib/models.ts

@@ -1,7 +1,9 @@
 // Keep in sync with backend (llm.py)
+// Order here matches dropdown order
 export enum CodeGenerationModel {
-  GPT_4_VISION = "gpt_4_vision",
+  GPT_4O_2024_05_13 = "gpt-4o-2024-05-13",
   GPT_4_TURBO_2024_04_09 = "gpt-4-turbo-2024-04-09",
+  GPT_4_VISION = "gpt_4_vision",
   CLAUDE_3_SONNET = "claude_3_sonnet",
 }
 
@@ -9,7 +11,8 @@ export enum CodeGenerationModel {
 export const CODE_GENERATION_MODEL_DESCRIPTIONS: {
   [key in CodeGenerationModel]: { name: string; inBeta: boolean };
 } = {
+  "gpt-4o-2024-05-13": { name: "GPT-4o 🌟", inBeta: false },
+  "gpt-4-turbo-2024-04-09": { name: "GPT-4 Turbo (Apr 2024)", inBeta: false },
   gpt_4_vision: { name: "GPT-4 Vision (Nov 2023)", inBeta: false },
   claude_3_sonnet: { name: "Claude 3 Sonnet", inBeta: false },
-  "gpt-4-turbo-2024-04-09": { name: "GPT-4 Turbo (Apr 2024)", inBeta: false },
 };