Update app.py

app.py

@@ -1,87 +1,318 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-print(",3521534532")
-print(",350164845646531458641654352648621035421534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-print(",3521534532")
-
-"""
-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")
-
-
-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,
-        stream=True,
-        temperature=temperature,
-        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
-"""
-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)",
-        ),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-    ],
-)
-
-print("016484560164845646531458641654352648621035446531016484564653145864165435264862103544586416543526486210354")
+from gradio import ChatMessage
+from typing import Iterator
+import google.generativeai as genai
+import time # Import time module for potential debugging/delay
 
+print("import library complete")
+print("add API key")
+
+# get Gemini API Key from the environ variable
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+genai.configure(api_key=GEMINI_API_KEY)
+
+print("add API key complete ")
+print("add model")
+
+used_model = "gemini-2.5-pro-exp-03-25"
+
+# we will be using the Gemini 2.0 Flash model with Thinking capabilities
+model = genai.GenerativeModel("gemini-2.0-flash-thinking-exp-01-21")
+
+print(f"add model {used_model} complete\n")
+
+def format_chat_history(messages: list) -> list:
+    print("\nstart format history")
+    """
+    Formats the chat history into a structure Gemini can understand
+    """
+    formatted_history = []
+    for message in messages:
+        #print(f"t1 {message}")
+        # Skip thinking messages (messages with metadata)
+        #if not (message.get("role") == "assistant" and "metadata" in message):
+        #    print(f"t2 {message}")
+        #    formatted_history.append({
+        #        "role": "user" if message.get("role") == "user" else "assistant",
+        #        "parts": [message.get("content", "")]
+        #    })
+            
+        #print(f"t2 {message}")
+
+        if message.get("role") == "user" :
+            formatted_history.append({
+            "role": "user",
+            "parts": [message.get("content", "")]
+            })
+        elif message.get("role") == "assistant" :
+            formatted_history.append({
+            "role": "model",
+            "parts": [message.get("content", "")]
+            })
+        
+    #print(f"t3 {formatted_history}")
+    print("return formatted history")
+    return formatted_history
+
+def stream_gemini_response(user_message: str, messages: list) -> Iterator[list]:
+    print("start model response stream")
+    """
+    Streams thoughts and response with conversation history support for text input only.
+    """
+    if not user_message.strip(): # Robust check: if text message is empty or whitespace
+        messages.append(ChatMessage(role="assistant", content="Please provide a non-empty text message. Empty input is not allowed.")) # More specific message
+        yield messages
+        print("Empty text message")
+        return
+
+    try:
+        print(f"\n=== New Request (Text) ===")
+        print(f"User message: {user_message}")
+
+        # Format chat history for Gemini
+        chat_history = format_chat_history(messages)
+
+        #print(f"hist {chat_history}")
+        
+        # Initialize Gemini chat
+        print("Chat parameter")
+        chat = model.start_chat(history=chat_history)
+        print("Start response")
+        response = chat.send_message(user_message, stream=True)
+
+        # Initialize buffers and flags
+        thought_buffer = ""
+        response_buffer = ""
+        #thinking_complete = False
+
+        # Add initial thinking message
+        #messages.append(
+        #    ChatMessage(
+        #        role="assistant",
+        #        content="",
+        #        metadata={"title": "⚙️ Thinking: *The thoughts produced by the model are experimental"}
+        #    )
+        #)
+        
+        messages.append(
+            ChatMessage(
+                role="assistant",
+                content=response_buffer
+            )
+        )
+        #print(f"mes {messages} \n\nhis {chat_history}")
+        
+        thinking_complete = True
+
+        for chunk in response:
+            print("chunk start")
+            parts = chunk.candidates[0].content.parts
+            current_chunk = parts[0].text
+
+            print(f"\n=========\nparts len: {len(parts)}\n\nparts: {parts}\n\ncurrent chunk: {current_chunk}\n=========\n")
+            
+            if len(parts) == 2 and not thinking_complete:
+                # Complete thought and start response
+                thought_buffer += current_chunk
+                print(f"\n=== Complete Thought ===\n{thought_buffer}")
+
+                messages[-1] = ChatMessage(
+                    role="assistant",
+                    content=thought_buffer,
+                    metadata={"title": "⚙️ Thinking: *The thoughts produced by the model are experimental"}
+                )
+                yield messages
+
+                # Start response
+                response_buffer = parts[1].text
+                print(f"\n=== Starting Response ===\n{response_buffer}")
+
+                messages.append(
+                    ChatMessage(
+                        role="assistant",
+                        content=response_buffer
+                    )
+                )
+                thinking_complete = True
+
+            elif thinking_complete:
+                # Stream response
+                response_buffer += current_chunk
+                print(f"\n=== Response Chunk ===\n{current_chunk}")
+
+                messages[-1] = ChatMessage(
+                    role="assistant",
+                    content=response_buffer
+                )
+
+            else:
+                # Stream thinking
+                thought_buffer += current_chunk
+                print(f"\n=== Thinking Chunk ===\n{current_chunk}")
+
+                messages[-1] = ChatMessage(
+                    role="assistant",
+                    content=thought_buffer,
+                    metadata={"title": "⚙️ Thinking: *The thoughts produced by the model are experimental"}
+                )
+            #time.sleep(0.05) #Optional: Uncomment this line to add a slight delay for debugging/visualization of streaming. Remove for final version
+            print("Response end")
+            yield messages
+
+        print(f"\n=== Final Response ===\n{response_buffer}")
+
+    except Exception as e:
+        print(f"\n=== Error ===\n{str(e)}")
+        messages.append(
+            ChatMessage(
+                role="assistant",
+                content=f"I apologize, but I encountered an error: {str(e)}"
+            )
+        )
+        yield messages
+
+def user_message(msg: str, history: list) -> tuple[str, list]:
+    """Adds user message to chat history"""
+    history.append(ChatMessage(role="user", content=msg))
+    return "", history
+
+
+# Create the Gradio interface
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="teal", secondary_hue="slate", neutral_hue="neutral")) as demo: # Using Soft theme with adjusted hues for a refined look
+    gr.Markdown("# Chat with " + used_model)
+
+    
+    gr.HTML("""<a href="https://visitorbadge.io/status?path=https%3A%2F%2Fhuggingface.co%2Fspaces%2Fzelk12%2FGemini-2">
+               <img src="https://api.visitorbadge.io/api/combined?path=https%3A%2F%2Fhuggingface.co%2Fspaces%2Fzelk12%2FGemini-2&countColor=%23263759" />
+               </a>""")
+
+    
+    chatbot = gr.Chatbot(
+        type="messages",
+        label=used_model + " Chatbot (Streaming Output)", #Label now indicates streaming
+        render_markdown=True,
+        scale=1,
+        editable="all",
+        avatar_images=(None,"https://lh3.googleusercontent.com/oxz0sUBF0iYoN4VvhqWTmux-cxfD1rxuYkuFEfm1SFaseXEsjjE4Je_C_V3UQPuJ87sImQK3HfQ3RXiaRnQetjaZbjJJUkiPL5jFJ1WRl5FKJZYibUA=w214-h214-n-nu")
+    )
+
+    with gr.Row(equal_height=True):
+        input_box = gr.Textbox(
+            lines=1,
+            label="Chat Message",
+            placeholder="Type your message here...",
+            scale=4
+        )
+
+        with gr.Column(scale=1):
+            submit_button = gr.Button("Submit", scale=1)
+            clear_button = gr.Button("Clear Chat", scale=1)
+
+    with gr.Row(equal_height=True):
+        test_button = gr.Button("test", scale=1)
+        test1_button = gr.Button("test1", scale=1)
+        test2_button = gr.Button("test2", scale=1)
+        test3_button = gr.Button("test3", scale=1)
+
+    # Add example prompts - removed file upload examples. Kept text focused examples.
+    example_prompts = [
+        ["Write a short poem about the sunset."],
+        ["Explain the theory of relativity in simple terms."],
+        ["If a train leaves Chicago at 6am traveling at 60mph, and another train leaves New York at 8am traveling at 80mph, at what time will they meet?"],
+        ["Summarize the plot of Hamlet."],
+        ["Write a haiku about a cat."]
+    ]
+
+    gr.Examples(
+        examples=example_prompts,
+        inputs=input_box,
+        label="Examples: Try these prompts to see Gemini's thinking!",
+        examples_per_page=5 # Adjust as needed
+    )
+
+# Created by gemini-2.5-pro-exp-03-25
+#def process_message(msg):
+#    """Обрабатывает сообщение пользователя: сохраняет, отображает и генерирует ответ."""
+#    msg_store_val, _, _ = lambda msg: (msg, msg, "")(msg) # Store message and clear input (inline lambda)
+#    input_box_val, chatbot_val = user_message(msg_store_val, chatbot) # Add user message to chat
+#    chatbot_val_final = stream_gemini_response(msg_store_val, chatbot_val) # Generate and stream response
+#    return msg_store_val, input_box_val, chatbot_val_final
+#
+#input_box.submit(
+#    process_message,
+#    inputs=[input_box],
+#    outputs=[msg_store, input_box, chatbot],  # Исправлены outputs, чтобы включать chatbot
+#    queue=False
+#)
+
+#submit_button.click(
+#    process_message,
+#    inputs=[input_box],
+#    outputs=[msg_store, input_box, chatbot],  # Исправлены outputs, чтобы включать chatbot
+#    queue=False
+#)
+    
+    # Set up event handlers
+    msg_store = gr.State("")  # Store for preserving user message
+
+    input_box.submit(
+        lambda msg: (msg, msg, ""),  # Store message and clear input
+        inputs=[input_box],
+        outputs=[msg_store, input_box, input_box],
+        queue=False
+    ).then(
+        user_message,  # Add user message to chat
+        inputs=[msg_store, chatbot],
+        outputs=[input_box, chatbot],
+        queue=False
+    ).then(
+        stream_gemini_response,  # Generate and stream response
+        inputs=[msg_store, chatbot],
+        outputs=chatbot
+    )
+
+    submit_button.click(
+        lambda msg: (msg, msg, ""),  # Store message and clear input
+        inputs=[input_box],
+        outputs=[msg_store, input_box, input_box],
+        queue=False
+    ).then(
+        user_message,  # Add user message to chat
+        inputs=[msg_store, chatbot],
+        outputs=[input_box, chatbot],
+        queue=False
+    ).then(
+        stream_gemini_response,  # Generate and stream response
+        inputs=[msg_store, chatbot],
+        outputs=chatbot
+    )
+
+    clear_button.click(
+        lambda: ([], "", ""),
+        outputs=[chatbot, input_box, msg_store],
+        queue=False
+    )
+
+    gr.Markdown(  # Description moved to the bottom - updated for text-only
+        """
+        <br><br><br>  <!-- Add some vertical space -->
+        ---
+        ### About this Chatbot
+        **Try out the example prompts below to see Gemini in action!**
+        **Key Features:**
+        *   Powered by Google's **Gemini 2.0 Flash** model.
+        *   Supports **conversation history** for multi-turn chats.
+        *   Uses **streaming** for a more interactive experience.
+        **Instructions:**
+        1.  Type your message in the input box below or select an example.
+        2.  Press Enter or click Submit to send.
+        3.  Observe the chatbot's "Thinking" process followed by the final response.
+        4.  Use the "Clear Chat" button to start a new conversation.
+        """
+    )
+
+
+# Launch the interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(debug=True)