Update app.py (#1)

- Update app.py (3e68be8689f57d2586c90334e6162af58747fc27)

app.py

@@ -1,64 +1,104 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+import requests
+import json
+import pytesseract
+from PIL import Image
+import PyPDF2
+from io import BytesIO
+import docx
 
-"""
-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 clients
+API_KEY = os.environ.get("HF_API_KEY")
+client = InferenceClient(token=API_KEY)
 
+def process_file(file):
+    """Handle different file types and extract text"""
+    if file is None:
+        return ""
+        
+    # Get file extension
+    ext = file.name.split('.')[-1].lower()
+    
+    try:
+        if ext in ['png', 'jpg', 'jpeg']:
+            # OCR processing for images
+            image = Image.open(file.name)
+            text = pytesseract.image_to_string(image)
+            return f"IMAGE CONTENT:\n{text}"
+            
+        elif ext == 'pdf':
+            # PDF text extraction
+            pdf_reader = PyPDF2.PdfReader(file.name)
+            text = "\n".join([page.extract_text() for page in pdf_reader.pages])
+            return f"PDF CONTENT:\n{text}"
+            
+        elif ext == 'docx':
+            # Word document processing
+            doc = docx.Document(file.name)
+            text = "\n".join([para.text for para in doc.paragraphs])
+            return f"DOCUMENT CONTENT:\n{text}"
+            
+        else:
+            return "Unsupported file type"
+            
+    except Exception as e:
+        print(f"File processing error: {e}")
+        return "Error reading file"
 
-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})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+def chat(message, history, file):
+    # Process uploaded file
+    file_content = process_file(file) if file else ""
+    
+    # Build enhanced prompt
+    full_prompt = f"""
+    {file_content}
+    
+    User Message: {message}
+    
+    Please respond considering both the message and any attached documents:"""
+    
+    # Configure generation parameters
+    generate_kwargs = dict(
+        temperature=0.7,
+        max_new_tokens=2000,
+        top_p=0.95,
+        repetition_penalty=1.2,
+    )
+    
+    # Generate response
+    stream = client.text_generation(
+        full_prompt,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        details=True,
+        **generate_kwargs
+    )
+    
+    partial_message = ""
+    for response in stream:
+        if response.token.special:
+            continue
+        partial_message += response.token.text
+        yield partial_message
 
+# Create Gradio interface with file upload
+with gr.Blocks(theme="soft") as demo:
+    gr.Markdown("# DeepSeek-R1 Assistant with File Support")
+    gr.Markdown("Upload images, PDFs, or docs and chat about them!")
+    
+    with gr.Row():
+        file_input = gr.File(label="Upload File (PDF/Image/Doc)", type="file")
+        
+    chatbot = gr.ChatInterface(
+        fn=chat,
+        additional_inputs=[file_input],
+        examples=[
+            ["Explain this document", "report.pdf"],
+            ["What's in this image?", "screenshot.png"]
+        ]
+    )
 
-"""
-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)",
-        ),
-    ],
-)
+demo.launch()
 
 
-if __name__ == "__main__":
-    demo.launch()