hey-llama-code-editor

Running on CPU Upgrade

App Files Files Community

freddyaboulton HF staff commited on 6 days ago

Commit

aca1d5b

•

1 Parent(s): 9cd3f82

Fix errors

Browse files

Files changed (3) hide show

README.md +3 -3
app.py +50 -26
something_happened.html +37 -0

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
-title: Llama Code Editor
-emoji: 🐢
 colorFrom: indigo
 colorTo: pink
 sdk: gradio
@@ -8,7 +8,7 @@ sdk_version: 5.6.0
 app_file: app.py
 pinned: false
 license: mit
-short_description: Create interactive HTML web pages with your voice
 ---
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

 ---
+title: Hello Llama Code Editor
+emoji: 🦙
 colorFrom: indigo
 colorTo: pink
 sdk: gradio
 app_file: app.py
 pinned: false
 license: mit
+short_description: Say "Hello Llama" and start coding with your voice!
 ---
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py CHANGED Viewed

@@ -1,19 +1,29 @@
 import gradio as gr
-from gradio_webrtc import WebRTC, ReplyOnStopWords, AdditionalOutputs, audio_to_bytes, get_twilio_turn_credentials
 import numpy as np
 import base64
 import re
 from groq import Groq
 from dotenv import load_dotenv
 load_dotenv()
 spinner_html = open("spinner.html").read()
 rtc_configuration = get_twilio_turn_credentials()
 import logging
 # Configure the root logger to WARNING to suppress debug messages from other libraries
 logging.basicConfig(level=logging.WARNING)
@@ -36,23 +46,22 @@ groq_client = Groq()
 system_prompt = "You are an AI coding assistant. Your task is to write single-file HTML applications based on a user's request. Only return the necessary code. Include all necessary imports and styles. You may also be asked to edit your original response."
 user_prompt = "Please write a single-file HTML application to fulfill the following request.\nThe message:{user_message}\nCurrent code you have written:{code}"
 def extract_html_content(text):
     """
     Extract content including HTML tags.
     """
-    match = re.search(r'<!DOCTYPE html>.*?</html>', text, re.DOTALL)
     return match.group(0) if match else None
 def display_in_sandbox(code):
-    encoded_html = base64.b64encode(code.encode('utf-8')).decode('utf-8')
     data_uri = f"data:text/html;charset=utf-8;base64,{encoded_html}"
-    return f"<iframe src=\"{data_uri}\" width=\"100%\" height=\"600px\"></iframe>"
-def generate(user_message: tuple[int, np.ndarray],
-             history: list[dict],
-             code: str):
     yield AdditionalOutputs(history, spinner_html)
     sr, audio = user_message
@@ -66,20 +75,24 @@ def generate(user_message: tuple[int, np.ndarray],
     user_msg_formatted = user_prompt.format(user_message=text, code=code)
     history.append({"role": "user", "content": user_msg_formatted})
     print("generating response")
     response = groq_client.chat.completions.create(
         model="llama-3.3-70b-versatile",
         messages=history,
         temperature=1,
-        max_tokens=1024,
         top_p=1,
         stream=False,
     )
     print("finished generating response")
     output = response.choices[0].message.content
-    html_code = extract_html_content(output)
     history.append({"role": "assistant", "content": output})
     yield AdditionalOutputs(history, html_code)
@@ -100,28 +113,39 @@ with gr.Blocks(css=".code-component {max-height: 500px !important}") as demo:
                 Each conversation is limited to 90 seconds. Once the time limit is up you can rejoin the conversation.
                 </p>
                 """
-        )
-            webrtc = WebRTC(rtc_configuration=rtc_configuration,
-                        mode="send", modality="audio")
         with gr.Column(scale=10):
             with gr.Tabs():
                 with gr.Tab("Sandbox"):
-                    sandbox = gr.HTML(value=open("sandbox.html").read())
                 with gr.Tab("Code"):
-                    code = gr.Code(language="html", max_lines=50, interactive=False, elem_classes="code-component")
                 with gr.Tab("Chat"):
                     cb = gr.Chatbot(type="messages")
-    webrtc.stream(ReplyOnStopWords(generate,
-                                   input_sample_rate=16000,
-                                   stop_words=["hello llama", "hello lama", "hello lamma", "hello llamma"]),
-                  inputs=[webrtc, history, code],
-                  outputs=[webrtc], time_limit=90,
-                  concurrency_limit=10)
-    webrtc.on_additional_outputs(lambda history, code: (history, code, history),
-                                 outputs=[history, code, cb])
     code.change(display_in_sandbox, code, sandbox, queue=False)
 if __name__ == "__main__":
     demo.launch()

 import gradio as gr
+from gradio_webrtc import (
+    WebRTC,
+    ReplyOnStopWords,
+    AdditionalOutputs,
+    audio_to_bytes,
+    get_twilio_turn_credentials,
+)
 import numpy as np
 import base64
 import re
 from groq import Groq
 from dotenv import load_dotenv
 load_dotenv()
 spinner_html = open("spinner.html").read()
+sandbox_html = open("sandbox.html").read()
+something_happened_html = open("something_happened.html").read()
 rtc_configuration = get_twilio_turn_credentials()
 import logging
 # Configure the root logger to WARNING to suppress debug messages from other libraries
 logging.basicConfig(level=logging.WARNING)
 system_prompt = "You are an AI coding assistant. Your task is to write single-file HTML applications based on a user's request. Only return the necessary code. Include all necessary imports and styles. You may also be asked to edit your original response."
 user_prompt = "Please write a single-file HTML application to fulfill the following request.\nThe message:{user_message}\nCurrent code you have written:{code}"
 def extract_html_content(text):
     """
     Extract content including HTML tags.
     """
+    match = re.search(r"<!DOCTYPE html>.*?</html>", text, re.DOTALL)
     return match.group(0) if match else None
 def display_in_sandbox(code):
+    encoded_html = base64.b64encode(code.encode("utf-8")).decode("utf-8")
     data_uri = f"data:text/html;charset=utf-8;base64,{encoded_html}"
+    return f'<iframe src="{data_uri}" width="100%" height="600px"></iframe>'
+def generate(user_message: tuple[int, np.ndarray], history: list[dict], code: str):
     yield AdditionalOutputs(history, spinner_html)
     sr, audio = user_message
     user_msg_formatted = user_prompt.format(user_message=text, code=code)
     history.append({"role": "user", "content": user_msg_formatted})
     print("generating response")
     response = groq_client.chat.completions.create(
         model="llama-3.3-70b-versatile",
         messages=history,
         temperature=1,
+        max_tokens=2048,
         top_p=1,
         stream=False,
     )
     print("finished generating response")
     output = response.choices[0].message.content
+    try:
+        html_code = extract_html_content(output)
+    except Exception as e:
+        html_code = something_happened_html
+        print(e)
     history.append({"role": "assistant", "content": output})
     yield AdditionalOutputs(history, html_code)
                 Each conversation is limited to 90 seconds. Once the time limit is up you can rejoin the conversation.
                 </p>
                 """
+            )
+            webrtc = WebRTC(
+                rtc_configuration=rtc_configuration, mode="send", modality="audio"
+            )
         with gr.Column(scale=10):
             with gr.Tabs():
                 with gr.Tab("Sandbox"):
+                    sandbox = gr.HTML(value=sandbox_html)
                 with gr.Tab("Code"):
+                    code = gr.Code(
+                        language="html",
+                        max_lines=50,
+                        interactive=False,
+                        elem_classes="code-component",
+                    )
                 with gr.Tab("Chat"):
                     cb = gr.Chatbot(type="messages")
+    webrtc.stream(
+        ReplyOnStopWords(
+            generate,
+            input_sample_rate=16000,
+            stop_words=["hello llama", "hello lama", "hello lamma", "hello llamma"],
+        ),
+        inputs=[webrtc, history, code],
+        outputs=[webrtc],
+        time_limit=90,
+        concurrency_limit=10,
+    )
+    webrtc.on_additional_outputs(
+        lambda history, code: (history, code, history), outputs=[history, code, cb]
+    )
     code.change(display_in_sandbox, code, sandbox, queue=False)
 if __name__ == "__main__":
     demo.launch()

something_happened.html ADDED Viewed

	@@ -0,0 +1,37 @@

+<div style="
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  min-height: 400px;
+  background: linear-gradient(135deg, #f5f7fa 0%, #e4e8ec 100%);
+  border-radius: 8px;
+  border: 2px dashed #cbd5e1;
+  padding: 2rem;
+  text-align: center;
+  color: #64748b;
+  font-family: system-ui, -apple-system, sans-serif;
+">
+  <div style="
+    width: 80px;
+    height: 80px;
+    margin-bottom: 1.5rem;
+    border: 3px solid #cbd5e1;
+    border-radius: 12px;
+    position: relative;
+  ">
+    <div style="
+      position: absolute;
+      top: 50%;
+      left: 50%;
+      transform: translate(-50%, -50%);
+      font-size: 2rem;
+    ">😬</div>
+  </div>
+  <h2 style="
+    margin: 0 0 0.5rem 0;
+    font-size: 1.5rem;
+    font-weight: 600;
+    color: #475569;
+  ">Error generating the page, see Chat tab to see the model's response</h2>
+</div>