Init

app.py

@@ -1,64 +1,61 @@
 import gradio as gr
+import os
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Get the token from the "HF_TOKEN" environment variable
+token = os.getenv("HF_TOKEN")
 
+# Create a client for the Salesforce/codet5-large model using the token
+client = InferenceClient("Salesforce/codet5-large", token=token)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+
+def generate_code(
+        task_description,
+        max_tokens,
+        temperature,
+        top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    # 2. Create a prompt using task description
+    prompt = task_description
+
+    # 3. Generate code based on the description
+    response = client.text_generation(
+        prompt,
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+    )
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Since the response is already a string, just return it
+    generated_code = response
+    return generated_code
 
-    messages.append({"role": "user", "content": message})
 
-    response = ""
+# 4. Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# 🚀 CodeT5 Code Generator")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    with gr.Row():
+        task_input = gr.Textbox(
+            lines=3, placeholder="Describe the task in natural language...", label="Task Description"
+        )
 
-        response += token
-        yield response
+    with gr.Row():
+        max_tokens = gr.Slider(1, 2048, value=100, step=1, label="Max Tokens")
+        temperature = gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature")
+        top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
 
+    with gr.Row():
+        submit_button = gr.Button("Generate Code 🚀")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    output = gr.Textbox(lines=10, label="Generated Code")
 
+    # 5. Button click triggers code generation
+    submit_button.click(
+        generate_code,
+        inputs=[task_input, max_tokens, temperature, top_p],
+        outputs=output,
+    )
 
 if __name__ == "__main__":
     demo.launch()