Update app.py

app.py

@@ -1,32 +1,43 @@
 import gradio as gr
 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("Qwen/Qwen2.5-Coder-32B-Instruct")
 
-
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
+    file=None
 ):
+    # Initialize messages with the system message
     messages = [{"role": "system", "content": system_message}]
 
+    # Read file content if a file is uploaded
+    if file:
+        try:
+            file_content = file.read().decode('utf-8')  # Read and decode bytes to string
+            print("File content:", file_content)  # Debug print
+            message = f"{file_content}\n\n{message}"  # Append file content to message
+        except Exception as e:
+            print("Error reading file:", e)
+            message = f"(Error reading file: {e})\n\n{message}"
+
+    # Append conversation history
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
+    # Append the latest user message
     messages.append({"role": "user", "content": message})
 
     response = ""
 
+    # Stream response from the model
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,16 +46,12 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Set up the Gradio interface
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=32000, value=2048, step=1, label="Max new tokens"),
@@ -54,11 +61,11 @@ demo = gr.ChatInterface(
             maximum=1.0,
             value=0.95,
             step=0.05,
-            label="Top-p (nucleus sampling)",
+            label="Top-p (nucleus sampling)"
         ),
+        gr.File(label="Upload a text file", file_types=[".txt"])
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()