Update app.py

app.py

@@ -42,7 +42,7 @@ def generate_response(
     message: str, 
     history: list, 
     system_prompt: str, 
-    temperature: float = 0.7, 
+    temperature: float = 0.5, 
     max_tokens: int = 512
 ):
     conversation = [
@@ -50,27 +50,24 @@ def generate_response(
     ]
     for prompt, answer in history:
         conversation.extend([
-            {"role": "user", "content": str(prompt)},
-            {"role": "assistant", "content": str(answer)},
+            {"role": "user", "content": prompt},
+            {"role": "assistant", "content": answer},
         ])
-    conversation.append({"role": "user", "content": str(message)})
+    conversation.append({"role": "user", "content": message})
 
-    try:
-        response = client.chat.completions.create(
-            model="llama-3.1-8B-Instant",
-            messages=conversation,
-            temperature=temperature,
-            max_tokens=max_tokens,
-            stream=True
-        )
+    response = client.chat.completions.create(
+        model="llama-3.1-8B-Instant",
+        messages=conversation,
+        temperature=temperature,
+        max_tokens=max_tokens,
+        stream=True
+    )
 
-        partial_message = ""
-        for chunk in response:
-            if chunk.choices[0].delta.content is not None:
-                partial_message += chunk.choices[0].delta.content
-                yield partial_message
-    except Exception as e:
-        yield f"An error occurred: {str(e)}"
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+            partial_message += chunk.choices[0].delta.content
+            yield partial_message
 
 def clear_conversation():
     return [], None
@@ -83,12 +80,27 @@ with gr.Blocks(css=CSS, theme="GSW") as demo:
         fn=generate_response,
         chatbot=chatbot,
         fill_height=True,
-        textbox=gr.Textbox(
-            placeholder="Type a message",
-            container=False,
-            scale=7,
-            lines=3
-        ),
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False),
+        additional_inputs=[
+            gr.Textbox(
+                value="You are a helpful coding assistant, specialized in code completion, debugging, and analysis. Provide concise and accurate responses.",
+                label="System Prompt",
+            ),
+            gr.Slider(
+                minimum=0,
+                maximum=1,
+                step=0.1,
+                value=0.5,
+                label="Temperature",
+            ),
+            gr.Slider(
+                minimum=50,
+                maximum=1024,
+                step=1,
+                value=512,
+                label="Max tokens",
+            ),
+        ],
         examples=[
             ["What are Python generators, and how do I use them effectively in my code?"],
             ["Can you explain the different types of SQL joins with examples?"],
@@ -100,28 +112,6 @@ with gr.Blocks(css=CSS, theme="GSW") as demo:
     
     clear_btn = gr.Button("Clear Conversation")
     clear_btn.click(clear_conversation, outputs=[chatbot, chatbot])
-
-    with gr.Accordion("⚙️ Parameters", open=False):
-        system_prompt = gr.Textbox(
-            value="You are a helpful coding assistant, specialized in code completion, debugging, and analysis. Provide concise and accurate responses.",
-            label="System Prompt",
-        )
-        temperature = gr.Slider(
-            minimum=0,
-            maximum=1,
-            step=0.1,
-            value=0.5,
-            label="Temperature",
-        )
-        max_tokens = gr.Slider(
-            minimum=50,
-            maximum=1024,
-            step=1,
-            value=512,
-            label="Max tokens",
-        )
-    
-    chat_interface.additional_inputs = [system_prompt, temperature, max_tokens]
     
     gr.HTML(FOOTER_TEXT)