Update app.py

app.py

@@ -1,32 +1,36 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer
+import torch
 
-"""
-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")
+# Initialize model and tokenizer
+model_name = "erikbeltran/pydiff"
+client = InferenceClient(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
+def format_diff_response(response):
+    """Format the response to look like a diff output"""
+    lines = response.split('\n')
+    formatted = []
+    for line in lines:
+        if line.startswith('+'):
+            formatted.append(f'<span style="color: green">{line}</span>')
+        elif line.startswith('-'):
+            formatted.append(f'<span style="color: red">{line}</span>')
+        else:
+            formatted.append(line)
+    return '<br>'.join(formatted)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
+def respond(request, file_content, system_message, max_tokens, temperature, top_p):
+    messages = [
+        {"role": "system", "content": system_message},
+        {"role": "user", "content": f"""<request>{request}</request>
+<file>
+{file_content}
+</file>"""}
+    ]
+    
     response = ""
-
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,30 +39,69 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
-        yield response
-
+        # Format as diff and yield
+        yield format_diff_response(response)
 
-"""
-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(
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Code Review Assistant")
+    
+    with gr.Row():
+        with gr.Column():
+            request_input = gr.Textbox(
+                label="Request",
+                placeholder="Enter your request (e.g., 'fix the function', 'add error handling')",
+                lines=3
+            )
+            file_input = gr.Code(
+                label="File Content",
+                language="python",
+                lines=10
+            )
+        with gr.Column():
+            output = gr.HTML(label="Diff Output")
+    
+    with gr.Accordion("Advanced Settings", open=False):
+        system_msg = gr.Textbox(
+            value="You are a code review assistant. Analyze the code and provide suggestions in diff format. Use '+' for additions and '-' for deletions.",
+            label="System Message"
+        )
+        max_tokens = gr.Slider(
+            minimum=1,
+            maximum=2048,
+            value=512,
+            step=1,
+            label="Max Tokens"
+        )
+        temperature = gr.Slider(
+            minimum=0.1,
+            maximum=4.0,
+            value=0.7,
+            step=0.1,
+            label="Temperature"
+        )
+        top_p = gr.Slider(
             minimum=0.1,
             maximum=1.0,
             value=0.95,
             step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+            label="Top-p"
+        )
 
+    submit_btn = gr.Button("Submit")
+    submit_btn.click(
+        fn=respond,
+        inputs=[
+            request_input,
+            file_input,
+            system_msg,
+            max_tokens,
+            temperature,
+            top_p
+        ],
+        outputs=output
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()