Added

README.md

@@ -1,14 +1,205 @@
----
-title: LogicLink Project Space
-emoji: 📊
-colorFrom: indigo
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.29.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: AI Model
+# LogicLink: Version 5
+
+LogicLink is a conversational AI chatbot developed by **Kratu Gautam**, an **AIML Engineer**. Powered by the **TinyLlama-1.1B-Chat-v1.0** model, LogicLink provides an interactive and user-friendly interface for engaging conversations, answering queries, and assisting with tasks like planning, writing, and more. Version 5 introduces a sleek GUI, streaming responses, and enhanced features like conversation management.
+
+## Features
+
+- **Conversational AI**: Built on TinyLlama-1.1B-Chat-v1.0, LogicLink delivers natural and engaging responses to a wide range of user queries.
+- **Streaming Responses**: Utilizes `TextIteratorStreamer` for real-time response generation, providing a smooth user experience.
+- **Customizable GUI**: Features a modern interface with a red/blue/black theme, powered by Gradio and ModelScope Studio components (`pro.Chatbot`, `antdx.Sender`).
+- **Conversation Management**:
+  - **New Chat**: Start fresh conversations with a dedicated button.
+  - **Clear History**: Reset the current conversation’s history.
+  - **Delete Conversations**: Remove individual conversations from the conversation list.
+- **Single Time Stamp**: Responses include a single processing time stamp (e.g., `*(4.50s)*`), fixed to avoid duplication.
+- **CUDA Support**: Optimizes performance on GPU-enabled systems, with fallback to CPU.
+- **Error Handling**: Gracefully handles issues like memory shortages or invalid inputs, displaying user-friendly error messages.
+
+## Installation
+
+### Prerequisites
+
+- Python 3.8+
+- CUDA-enabled GPU (optional, for faster processing)
+- Dependencies:
+
+  ```bash
+  pip install gradio torch transformers modelscope-studio
+  ```
+
+### Setup
+
+1. **Clone the Repository**:
+
+   ```bash
+   git clone Kratugautam99/LogicLink-Project.git
+   cd LogicLink-Project
+   ```
+
+2. **Install Dependencies**:
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. **Directory Structure**: Ensure the following files are present:
+
+   - `app.py`: Main application script.
+   - `config.py`: Configuration for GUI components (ensure `DEFAULT_LOCALE`, `DEFAULT_THEME`, `get_text`, `user_config`, `bot_config`, `welcome_config` are defined).
+   - `ui_components/logo.py`: Logo component for the GUI.
+   - `ui_components/settings_header.py`: Settings header component.
+
+4. **Run the Application**:
+
+   ```bash
+   python app.py
+   ```
+
+   This launches a web interface via Gradio, providing a public URL (e.g., `https://...gradio.live`) if `share=True`.
+
+## Usage
+
+1. **Launch the Chatbot**:
+
+   - Run `app.py` in a Jupyter notebook, Colab, or terminal.
+   - Access the web interface through the provided URL.
+
+2. **Interact with LogicLink**:
+
+   - **Input Queries**: Type questions or tasks in the input field (e.g., "Tell me about Pakistan" or "Who are you?").
+   - **Manage Conversations**:
+     - Click **New Chat** to start a new conversation.
+     - Click **Clear History** to reset the current conversation.
+     - Click the **Delete** menu item in the conversation list to remove a conversation.
+
+3. **Example Interaction**:
+
+   - **Input**: "Who are you?"
+   - **Output**:
+
+     ```
+     I'm LogicLink, Version 5, created by Kratu Gautam, an AIML Engineer. I'm here to help with your questions, so what's up?
+     *(4.50s)*
+     ```
+   - **Input**: "Explain quantum physics briefly"
+   - **Output**: A concise explanation of quantum physics, followed by `*(X.XXs)*`.
+
+4. **Performance**:
+
+   - **Response Time**: \~3–5 seconds per query (faster with CUDA).
+   - **RAM Usage**: \~2–3 GB on CPU, lower on GPU.
+
+## Technical Details
+
+### Model Architecture
+
+- **Base Model**: TinyLlama-1.1B-Chat-v1.0, a lightweight transformer-based language model with 1.1 billion parameters, optimized for chat applications.
+- **Framework**: PyTorch with the Transformers library from Hugging Face.
+- **Tokenizer**: `AutoTokenizer` configured with left-padding and EOS token handling to ensure proper input formatting for chat sequences.
+- **Response Generation**:
+  - Leverages `AutoModelForCausalLM` for next-token prediction.
+  - Implements streaming with `TextIteratorStreamer` to output tokens in real-time, enhancing user experience.
+  - Uses a custom `StopOnTokens` stopping criterion to halt generation at specific tokens (e.g., token ID 2), preventing unnecessary output.
+- **Generation Parameters**:
+  - `max_new_tokens=1024`: Limits response length to 1024 tokens.
+  - `temperature=0.7`: Balances creativity and coherence in responses.
+  - `top_k=50`: Considers the top 50 probable tokens for sampling.
+  - `top_p=0.95`: Applies nucleus sampling to focus on the top 95% probability mass.
+  - `num_beams=1`: Uses greedy decoding for deterministic output.
+
+### Implementation Specifics
+
+- **Prompt Engineering**:
+  - The model is instructed via a system prompt:
+
+    ```
+    You are LogicLink, Version 5, created by Kratu Gautam, an AIML Engineer. Respond to the following user input: {user_input}
+    ```
+  - Conversation history is formatted with `<|user|>` and `<|assistant|>` tags, separated by `</s>`, to maintain context.
+- **Threading**: Response generation runs in a separate thread using Python’s `Thread` module to prevent blocking the Gradio interface.
+- **Time Stamp Handling**:
+  - A regex (`re.sub(r'\*\(\d+\.\d+s\)\*', '', response)`) removes duplicate time stamps, ensuring each response ends with a single `*(X.XXs)*`.
+- **Error Handling**:
+  - Catches exceptions (e.g., memory errors, model incompatibilities) and appends user-friendly messages to the conversation history.
+  - Example: `Generation failed: insufficient memory. Possible causes: ...`
+
+### GUI
+
+- **Framework**: Gradio integrated with ModelScope Studio components for a professional-grade interface.
+- **Components**:
+  - `pro.Chatbot`: Renders conversation history with distinct user (blue bubbles) and assistant (dark gray with red borders) messages.
+  - `antdx.Sender`: Provides an input field with a clear button for user queries.
+  - `antdx.Conversations`: A sidebar for managing multiple conversations, with a context menu for deletion.
+  - `antd.Button`: Implements the "New Chat" button and other interactive elements.
+- **Styling**: Custom CSS defines a red/blue/black theme:
+  - User messages: Blue background for visibility.
+  - Assistant messages: Dark gray with red borders for contrast.
+  - Buttons: Blue with hover effects for interactivity.
+- **Layout**: Uses `antd.Row` and `antd.Col` for responsive design, with a fixed 260px sidebar and flexible chat area.
+
+### Performance Optimization
+
+- **CUDA Support**: Automatically detects CUDA-enabled GPUs via `torch.device('cuda' if torch.cuda.is_available() else 'cpu')`, reducing response times to \~3 seconds on GPU compared to \~5 seconds on CPU.
+- **Memory Efficiency**: TinyLlama’s 1.1B parameters require \~2–3 GB RAM on CPU, making it suitable for consumer hardware.
+- **Threaded Generation**: Offloads model inference to a separate thread, ensuring the GUI remains responsive during processing.
+
+### Key Fixes
+
+- **Single Time Stamp**: Resolved duplicate time stamps using regex to clean responses before appending `*(X.XXs)*`.
+- **Delete Functionality**: Fixed `AntdXConversations` event handling by replacing `select` with `menu_click`, ensuring reliable conversation deletion.
+- **Metadata**: Embedded model identity in the prompt to consistently identify as LogicLink V5 by Kratu Gautam.
+
+## Troubleshooting
+
+- **Double Time Stamps**:
+  - If responses show multiple `*(X.XXs)*`, verify the regex in `logiclink_chat`.
+  - Test with inputs like "Tell me about Pakistan" and share the output.
+- **Slow Responses**:
+  - Use a CUDA-enabled GPU for faster processing.
+  - Reduce `max_new_tokens` to 512 if needed.
+  - Check RAM usage: `!free -h` in Colab.
+- **GUI Issues**:
+  - Ensure `config.py` and `ui_components/` are correctly configured.
+  - Update dependencies: `pip install --force-reinstall gradio modelscope-studio`.
+- **Delete Button Not Working**:
+  - Verify the `menu_click` event handler and JavaScript snippet.
+  - Share any error messages or tracebacks.
+- **Model Errors**:
+  - Check for sufficient RAM (\~2–3 GB) and compatible PyTorch/Transformers versions.
+  - Run a test generation:
+
+    ```python
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+    model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+    inputs = tokenizer(["Hello"], return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=10)
+    print(tokenizer.decode(outputs[0]))
+    ```
+
+## Future Improvements
+
+- Add a welcome message displaying LogicLink’s identity via `welcome_config()`.
+- Enhance prompt engineering for more context-aware responses.
+- Implement persistent storage for conversation history using a database or file system.
+- Add support for multimodal inputs (e.g., images) to expand functionality.
+- Optimize tokenization and generation for lower latency on CPU.
+
+## Credits
+
+- **Developer**: Kratu Gautam, AIML Engineer
+- **Dependencies**:
+  - TinyLlama-1.1B-Chat-v1.0 (Hugging Face)
+  - Gradio
+  - PyTorch
+  - Transformers
+  - ModelScope Studio
+- **Inspiration**: Built to provide an accessible and interactive AI chatbot for students and enthusiasts.
+
+## License
+
+MIT License. See `LICENSE` for details.
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+**LogicLink V5** is a project by Kratu Gautam, showcasing the power of AI in creating intuitive conversational tools. Contributions and feedback are welcome!

app.py

@@ -0,0 +1,391 @@
+import uuid
+import time
+import re
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+import modelscope_studio.components.antd as antd
+import modelscope_studio.components.antdx as antdx
+import modelscope_studio.components.base as ms
+import modelscope_studio.components.pro as pro
+from config import DEFAULT_LOCALE, DEFAULT_THEME, get_text, user_config, bot_config, welcome_config
+from ui_components.logo import Logo
+from ui_components.settings_header import SettingsHeader
+
+# Loading the tokenizer and model from Hugging Face's model hub
+
+tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+
+# Using CUDA for an optimal experience
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+model = model.to(device)
+
+# Defining a custom stopping criteria class for the model's text generation
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [2]  # IDs of tokens where the generation should stop.
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+# Function to generate model predictions with streaming
+
+def generate_response(user_input, history):
+    stop = StopOnTokens()
+    messages = "</s>".join([
+        "</s>".join([
+            "\n<|user|>:" + item["content"] if item["role"] == "user"
+            else "\n<|assistant|>:" + item["content"]
+            for item in history
+        ])
+    ])
+    messages += f"\n<|user|>:{user_input}\n<|assistant|>:"
+    model_inputs = tokenizer([messages], return_tensors="pt").to(device)
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        **model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        do_sample=True,
+        top_p=0.95,
+        top_k=50,
+        temperature=0.7,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()  # Start generation in a separate thread.
+    partial_message = ""
+    for new_token in streamer:
+        partial_message += new_token
+        if '</s>' in partial_message:
+            break
+    return partial_message
+
+# Define the system prompt for seeding the model's context
+
+SYSTEM_PROMPT = (
+    "I am LogicLink, Version 5—a state-of-the-art AI chatbot created by "
+    "Kratu Gautam (A-27) and Geetank Sahare (A-28) from SY CSE(AIML) GHRCEM. "
+    "I am here to assist you with any queries. How can I help you today?"
+)
+
+class Gradio_Events:
+    _generating = False
+
+    @staticmethod
+    def new_chat(state_value):
+        # This is CRITICAL - we DO NOT clean up old conversation
+        # Instead, we leave it in the state to be accessed later
+
+        # Create a fresh conversation
+        new_id = str(uuid.uuid4())
+        state_value["conversation_id"] = new_id
+
+        # Add the new conversation to the list with a default name
+        state_value["conversations"].append({
+            "label": "New Chat",
+            "key": new_id
+        })
+
+        # Seed it with system prompt
+        state_value["conversation_contexts"][new_id] = {
+            "history": [{
+                "role": "system",
+                "content": SYSTEM_PROMPT,
+                "key": str(uuid.uuid4()),
+                "avatar": None
+            }]
+        }
+
+        # Return updates
+        return (
+            gr.update(items=state_value["conversations"]),
+            gr.update(value=state_value["conversation_contexts"][new_id]["history"]),
+            gr.update(value=state_value),
+            gr.update(value="")  # empties input
+        )
+
+    @staticmethod
+    def add_message(input_value, state_value):
+        input_update = gr.update(value="")
+
+        # If input is empty, just return
+        if not input_value.strip():
+            conversation = state_value["conversation_contexts"].get(state_value["conversation_id"], {"history": []})
+            chatbot_update = gr.update(value=conversation["history"])
+            state_update = gr.update(value=state_value)
+            return input_update, chatbot_update, state_update
+
+        # If there's no active conversation, initialize a new one
+        if not state_value["conversation_id"]:
+            random_id = str(uuid.uuid4())
+            state_value["conversation_id"] = random_id
+            state_value["conversation_contexts"][random_id] = {"history": [{
+                "role": "system",
+                "content": SYSTEM_PROMPT,
+                "key": str(uuid.uuid4()),
+                "avatar": None
+            }]}
+
+            # Set the chat name to the first message from user
+            chat_name = input_value[:20] + ("..." if len(input_value) > 20 else "")
+            state_value["conversations"].append({
+                "label": chat_name,
+                "key": random_id
+            })
+        else:
+            # Get current conversation history
+            current_id = state_value["conversation_id"]
+            history = state_value["conversation_contexts"][current_id]["history"]
+
+            # If this is the first user message (after system message), update the label
+            user_messages = [msg for msg in history if msg["role"] == "user"]
+            if len(user_messages) == 0:
+                # This is the first user message - update the chat name
+                chat_name = input_value[:20] + ("..." if len(input_value) > 20 else "")
+                for i, conv in enumerate(state_value["conversations"]):
+                    if conv["key"] == current_id:
+                        state_value["conversations"][i]["label"] = chat_name
+                        break
+
+        # Add the message to history
+        history = state_value["conversation_contexts"][state_value["conversation_id"]]["history"]
+        history.append({
+            "role": "user",
+            "content": input_value,
+            "key": str(uuid.uuid4()),
+            "avatar": None
+        })
+
+        chatbot_update = gr.update(value=history)
+        return input_update, chatbot_update, gr.update(value=state_value)
+
+    @staticmethod
+    def submit(state_value):
+        if Gradio_Events._generating:
+            history = state_value["conversation_contexts"].get(state_value["conversation_id"], {"history": []})["history"]
+            return (
+                gr.update(value=history),
+                gr.update(value=state_value),
+                gr.update(value="Generation in progress, please wait...")
+            )
+
+        Gradio_Events._generating = True
+
+        # Make sure we have a valid conversation ID
+        if not state_value["conversation_id"]:
+            Gradio_Events._generating = False
+            return (
+                gr.update(value=[]),
+                gr.update(value=state_value),
+                gr.update(value="No active conversation")
+            )
+
+        history = state_value["conversation_contexts"][state_value["conversation_id"]]["history"]
+
+        # Assuming the last message is the latest user input
+        user_input = history[-1]["content"] if (history and history[-1]["role"] == "user") else ""
+        if not user_input:
+            Gradio_Events._generating = False
+            return (
+                gr.update(value=history),
+                gr.update(value=state_value),
+                gr.update(value="No user input provided")
+            )
+
+        # Generate the response from the model
+        history, response = Gradio_Events.logiclink_chat(user_input, history)
+        state_value["conversation_contexts"][state_value["conversation_id"]]["history"] = history
+        Gradio_Events._generating = False
+        return (
+            gr.update(value=history),
+            gr.update(value=state_value),
+            gr.update(value=response)
+        )
+
+    @staticmethod
+    def logiclink_chat(user_input, history):
+        if not user_input:
+            return history, "No input provided"
+        try:
+            start = time.time()
+            response = generate_response(user_input, history)
+            elapsed = time.time() - start
+            # Clean and format the response before appending it
+            cleaned_response = re.sub(r'\*\(\d+\.\d+s\)\*', '', response).strip()
+            response_with_time = f"{cleaned_response}\n\n*({elapsed:.2f}s)*"
+            history.append({
+                "role": "assistant",
+                "content": response_with_time,
+                "key": str(uuid.uuid4()),
+                "avatar": None
+            })
+            return history, response_with_time
+        except Exception as e:
+            error_msg = (
+                f"Generation failed: {str(e)}. "
+                "Possible causes: insufficient memory, model incompatibility, or input issues."
+            )
+            history.append({
+                "role": "assistant",
+                "content": error_msg,
+                "key": str(uuid.uuid4()),
+                "avatar": None
+            })
+            return history, error_msg
+
+    @staticmethod
+    def clear_history(state_value):
+        if state_value["conversation_id"]:
+            # Only clear messages after system prompt
+            current_history = state_value["conversation_contexts"][state_value["conversation_id"]]["history"]
+            if len(current_history) > 0 and current_history[0]["role"] == "system":
+                system_message = current_history[0]
+                state_value["conversation_contexts"][state_value["conversation_id"]]["history"] = [system_message]
+            else:
+                state_value["conversation_contexts"][state_value["conversation_id"]]["history"] = []
+
+            # Return the cleared history
+            return (
+                gr.update(value=state_value["conversation_contexts"][state_value["conversation_id"]]["history"]),
+                gr.update(value=state_value),
+                gr.update(value="")
+            )
+        return (
+            gr.update(value=[]),
+            gr.update(value=state_value),
+            gr.update(value="")
+        )
+
+    @staticmethod
+    def delete_conversation(state_value, conversation_key):
+        # Keep a copy of the conversations before removal
+        new_conversations = [conv for conv in state_value["conversations"] if conv["key"] != conversation_key]
+
+        # Remove the conversation from the list
+        state_value["conversations"] = new_conversations
+
+        # Delete the conversation context
+        if conversation_key in state_value["conversation_contexts"]:
+            del state_value["conversation_contexts"][conversation_key]
+
+        # If we're deleting the active conversation
+        if state_value["conversation_id"] == conversation_key:
+            state_value["conversation_id"] = ""
+            return gr.update(items=new_conversations), gr.update(value=[]), gr.update(value=state_value)
+
+        # If deleting another conversation, keep the current one displayed
+        return (
+            gr.update(items=new_conversations),
+            gr.update(value=state_value["conversation_contexts"].get(
+                state_value["conversation_id"], {"history": []}
+            )["history"]),
+            gr.update(value=state_value)
+        )
+
+# (The remainder of your Gradio UI code remains largely unchanged.)
+
+css = """
+:root {
+--color-red: #ff4444;
+--color-blue: #1e88e5;
+--color-black: #000000;
+--color-dark-gray: #121212;
+}
+.gradio-container { background: var(--color-black) !important; color: white !important; }
+.gr-textbox textarea, .ms-gr-ant-input-textarea { background: var(--color-dark-gray) !important; border: 2px solid var(--color-blue) !important; color: white !important; }
+.gr-chatbot { background: var(--color-dark-gray) !important; border: 2px solid var(--color-red) !important; }
+.gr-textbox.output-textbox { background: var(--color-dark-gray) !important; border: 2px solid var(--color-red) !important; color: white !important; margin-bottom: 10px; }
+.gr-chatbot .user { background: var(--color-blue) !important; border-color: var(--color-blue) !important; }
+.gr-chatbot .bot { background: var(--color-dark-gray) !important; border: 1px solid var(--color-red) !important; }
+.gr-button { background: var(--color-blue) !important; border-color: var(--color-blue) !important; }
+.gr-chatbot .tool { background: var(--color-dark-gray) !important; border: 1px solid var(--color-red) !important; }
+"""
+
+with gr.Blocks(css=css, fill_width=True, title="LogicLinkV5") as demo:
+    state = gr.State({
+        "conversation_contexts": {},
+        "conversations": [],
+        "conversation_id": "",
+    })
+    with ms.Application(), antdx.XProvider(theme=DEFAULT_THEME, locale=DEFAULT_LOCALE), ms.AutoLoading():
+        with antd.Row(gutter=[20, 20], wrap=False, elem_id="chatbot"):
+            # Left Column
+            with antd.Col(md=dict(flex="0 0 260px", span=24, order=0), span=0, order=1):
+                with ms.Div(elem_classes="chatbot-conversations"):
+                    with antd.Flex(vertical=True, gap="small", elem_style=dict(height="100%")):
+                        Logo()
+                        with antd.Button(color="primary", variant="filled", block=True, elem_classes="new-chat-btn") as new_chat_btn:
+                            ms.Text(get_text("New Chat", "新建对话"))
+                            with ms.Slot("icon"):
+                                antd.Icon("PlusOutlined")
+                        with antdx.Conversations(elem_classes="chatbot-conversations-list") as conversations:
+                            with ms.Slot('menu.items'):
+                                with antd.Menu.Item(label="Delete", key="delete", danger=True) as conversation_delete_menu_item:
+                                    with ms.Slot("icon"):
+                                        antd.Icon("DeleteOutlined")
+            # Right Column
+            with antd.Col(flex=1, elem_style=dict(height="100%")):
+                with antd.Flex(vertical=True, gap="small", elem_classes="chatbot-chat"):
+                    chatbot = pro.Chatbot(elem_classes="chatbot-chat-messages", height=600,
+                                         welcome_config=welcome_config(), user_config=user_config(),
+                                         bot_config=bot_config())
+                    output_textbox = gr.Textbox(label="LatestOutputTextbox", lines=1,
+                                              elem_classes="output-textbox", interactive=True)
+                    with antdx.Suggestion(items=[]):
+                        with ms.Slot("children"):
+                            with antdx.Sender(placeholder="Type your message...", elem_classes="chat-input") as input:
+                                with ms.Slot("prefix"):
+                                    with antd.Flex(gap=4):
+                                        with antd.Button(type="text", elem_classes="clear-btn") as clear_btn:
+                                            with ms.Slot("icon"):
+                                                antd.Icon("ClearOutlined")
+    # Event Handlers
+    input.submit(fn=Gradio_Events.add_message, inputs=[input, state],
+                outputs=[input, chatbot, state]).then(
+        fn=Gradio_Events.submit, inputs=[state],
+        outputs=[chatbot, state, output_textbox]
+    )
+    new_chat_btn.click(fn=Gradio_Events.new_chat,
+                     inputs=[state],
+                     outputs=[conversations, chatbot, state, input],
+                     queue=False)
+    clear_btn.click(fn=Gradio_Events.clear_history, inputs=[state],
+                   outputs=[chatbot, state, output_textbox])
+    conversations.menu_click(
+        fn=lambda state_value, e: (
+            # If there's no payload, skip
+            gr.skip() if (e is None or not isinstance(e, dict) or 'key' not in e._data['payload'][0] or 'menu_key' not in e._data['payload'][1])
+            else (
+                # Extract keys
+                (lambda conv_key, action_key: (
+                    # If "delete", remove that convo
+                    Gradio_Events.delete_conversation(state_value, conv_key)
+                    if action_key == "delete"
+                    # If other action, do nothing
+                    else (
+                        gr.update(items=state_value["conversations"]),
+                        gr.update(value=state_value["conversation_contexts"]
+                        .get(state_value["conversation_id"], {"history": []})
+                        ["history"]),
+                        gr.update(value=state_value)
+                    )
+                ))(
+                    e._data['payload'][0]['key'],
+                    e._data['payload'][1]['key']
+                )
+            )
+        ),
+        inputs=[state],
+        outputs=[conversations, chatbot, state],
+        queue=False
+    )
+
+demo.queue().launch(share=True, debug=True)

config.py

@@ -0,0 +1,228 @@
+import os
+from modelscope_studio.components.pro.chatbot import ChatbotActionConfig, ChatbotBotConfig, ChatbotUserConfig, ChatbotWelcomeConfig
+
+# Env
+is_cn = os.getenv('MODELSCOPE_ENVIRONMENT') == 'studio'
+api_key = os.getenv('API_KEY')
+
+
+def get_text(text: str, cn_text: str):
+    return text
+
+
+# Save history in browser
+save_history = True
+
+
+# Chatbot Config
+def user_config(disabled_actions=None):
+    return ChatbotUserConfig(
+        class_names=dict(content="user-message-content"),
+        actions=[
+            "copy", "edit",
+            ChatbotActionConfig(
+                action="delete",
+                popconfirm=dict(title=get_text("Delete the message", "删除消息"),
+                                description=get_text(
+                                    "Are you sure to delete this message?",
+                                    "确认删除该消息？"),
+                                okButtonProps=dict(danger=True)))
+        ],
+        disabled_actions=disabled_actions)
+
+
+def bot_config(disabled_actions=None):
+    return ChatbotBotConfig(actions=[
+        "copy", "edit",
+        ChatbotActionConfig(
+            action="retry",
+            popconfirm=dict(
+                title=get_text("Regenerate the message", "重新生成消息"),
+                description=get_text(
+                    "Regenerate the message will also delete all subsequent messages.",
+                    "重新生成消息会删除所有后续消息。"),
+                okButtonProps=dict(danger=True))),
+        ChatbotActionConfig(action="delete",
+                            popconfirm=dict(
+                                title=get_text("Delete the message", "删除消息"),
+                                description=get_text(
+                                    "Are you sure to delete this message?",
+                                    "确认删除该消息？"),
+                                okButtonProps=dict(danger=True)))
+    ],
+                            avatar="./assets/lll.jpg",
+                            disabled_actions=disabled_actions)
+
+
+def welcome_config():
+    return ChatbotWelcomeConfig(
+        variant="borderless",
+        icon="./assets/lll.jpg",
+        title=get_text("Hello, I'm LogicLink5", "你好，我是 LogicLink5"),
+        description=get_text("Select a model and enter text to get started.",
+                             "选择模型并输入文本，开始对话吧。"),
+        prompts=dict(
+            title=get_text("How can I help you today?", "有什么我能帮助你的吗?"),
+            styles={
+                "list": {
+                    "width": '100%',
+                },
+                "item": {
+                    "flex": 1,
+                },
+            },
+            items=[{
+                "label":
+                get_text("📅 Make a plan", "📅 制定计划"),
+                "children": [{
+                    "description":
+                    get_text("Help me with a plan to start a business",
+                             "帮助我制定一个创业计划")
+                }, {
+                    "description":
+                    get_text("Help me with a plan to achieve my goals",
+                             "帮助我制定一个实现目标的计划")
+                }, {
+                    "description":
+                    get_text("Help me with a plan for a successful interview",
+                             "帮助我制定一个成功的面试计划")
+                }]
+            }, {
+                "label":
+                get_text("🖋 Help me write", "🖋 帮我写"),
+                "children": [{
+                    "description":
+                    get_text("Help me write a story with a twist ending",
+                             "帮助我写一个带有意外结局的故事")
+                }, {
+                    "description":
+                    get_text("Help me write a blog post on mental health",
+                             "帮助我写一篇关于心理健康的博客文章")
+                }, {
+                    "description":
+                    get_text("Help me write a letter to my future self",
+                             "帮助我写一封给未来自己的信")
+                }]
+            }]),
+    )
+
+
+DEFAULT_SUGGESTIONS = [{
+    "label":
+    get_text('Make a plan', '制定计划'),
+    "value":
+    get_text('Make a plan', '制定计划'),
+    "children": [{
+        "label":
+        get_text("Start a business", "开始创业"),
+        "value":
+        get_text("Help me with a plan to start a business", "帮助我制定一个创业计划")
+    }, {
+        "label":
+        get_text("Achieve my goals", "实现我的目标"),
+        "value":
+        get_text("Help me with a plan to achieve my goals", "帮助我制定一个实现目标的计划")
+    }, {
+        "label":
+        get_text("Successful interview", "成功的面试"),
+        "value":
+        get_text("Help me with a plan for a successful interview",
+                 "帮助我制定一个成功的面试计划")
+    }]
+}, {
+    "label":
+    get_text('Help me write', '帮我写'),
+    "value":
+    get_text("Help me write", '帮我写'),
+    "children": [{
+        "label":
+        get_text("Story with a twist ending", "带有意外结局的故事"),
+        "value":
+        get_text("Help me write a story with a twist ending",
+                 "帮助我写一个带有意外结局的故事")
+    }, {
+        "label":
+        get_text("Blog post on mental health", "关于心理健康的博客文章"),
+        "value":
+        get_text("Help me write a blog post on mental health",
+                 "帮助我写一篇关于心理健康的博客文章")
+    }, {
+        "label":
+        get_text("Letter to my future self", "给未来自己的信"),
+        "value":
+        get_text("Help me write a letter to my future self", "帮助我写一封给未来自己的信")
+    }]
+}]
+
+DEFAULT_SYS_PROMPT = "You are a helpful and harmless assistant."
+
+MIN_THINKING_BUDGET = 1
+
+MAX_THINKING_BUDGET = 38
+
+DEFAULT_THINKING_BUDGET = 38
+
+DEFAULT_MODEL = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+
+MODEL_OPTIONS = [
+    {
+        "label": get_text("Qwen3-235B-A22B", "通义千问3-235B-A22B"),
+        "modelId": "Qwen/Qwen3-235B-A22B",
+        "value": "qwen3-235b-a22b"
+    },
+    {
+        "label": get_text("Qwen3-32B", "通义千问3-32B"),
+        "modelId": "Qwen/Qwen3-32B",
+        "value": "qwen3-32b"
+    },
+    {
+        "label": get_text("Qwen3-30B-A3B", "通义千问3-30B-A3B"),
+        "modelId": "Qwen/Qwen3-30B-A3B",
+        "value": "qwen3-30b-a3b"
+    },
+    {
+        "label": get_text("Qwen3-14B", "通义千问3-14B"),
+        "modelId": "Qwen/Qwen3-14B",
+        "value": "qwen3-14b"
+    },
+    {
+        "label": get_text("Qwen3-8B", "通义千问3-8B"),
+        "modelId": "Qwen/Qwen3-8B",
+        "value": "qwen3-8b"
+    },
+    {
+        "label": get_text("Qwen3-4B", "通义千问3-4B"),
+        "modelId": "Qwen/Qwen3-4B",
+        "value": "qwen3-4b"
+    },
+    {
+        "label": get_text("Qwen3-1.7B", "通义千问3-1.7B"),
+        "modelId": "Qwen/Qwen3-1.7B",
+        "value": "qwen3-1.7b"
+    },
+    {
+        "label": get_text("Qwen3-0.6B", "通义千问3-0.6B"),
+        "modelId": "Qwen/Qwen3-0.6B",
+        "value": "qwen3-0.6b"
+    },
+]
+
+for model in MODEL_OPTIONS:
+    model[
+        "link"] = is_cn and f"https://modelscope.cn/models/{model['modelId']}" or f"https://huggingface.co/{model['modelId']}"
+
+MODEL_OPTIONS_MAP = {model["value"]: model for model in MODEL_OPTIONS}
+
+DEFAULT_LOCALE = 'en_US'
+
+DEFAULT_THEME = {
+    "token": {
+        "colorPrimary": "#6A57FF",
+    }
+}
+
+DEFAULT_SETTINGS = {
+    "model": DEFAULT_MODEL,
+    "sys_prompt": DEFAULT_SYS_PROMPT,
+    "thinking_budget": DEFAULT_THINKING_BUDGET
+}

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/qwen.png filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,627 @@
+absl-py==1.4.0
+accelerate==1.6.0
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.15
+aiosignal==1.3.2
+alabaster==1.0.0
+albucore==0.0.24
+albumentations==2.0.6
+ale-py==0.11.0
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.9.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+array_record==0.7.2
+arviz==0.21.0
+astropy==7.0.1
+astropy-iers-data==0.2025.4.28.0.37.27
+astunparse==1.6.3
+atpublic==5.1
+attrs==25.3.0
+audioread==3.0.1
+autograd==1.7.0
+babel==2.17.0
+backcall==0.2.0
+backports.tarfile==1.2.0
+beautifulsoup4==4.13.4
+betterproto==2.0.0b6
+bigframes==2.1.0
+bigquery-magics==0.9.0
+bleach==6.2.0
+blinker==1.9.0
+blis==1.3.0
+blosc2==3.3.2
+bokeh==3.7.2
+Bottleneck==1.4.2
+bqplot==0.12.44
+branca==0.8.1
+build==1.2.2.post1
+CacheControl==0.14.3
+cachetools==5.5.2
+catalogue==2.0.10
+certifi==2025.4.26
+cffi==1.17.1
+chardet==5.2.0
+charset-normalizer==3.4.1
+chex==0.1.89
+clarabel==0.10.0
+click==8.1.8
+cloudpathlib==0.21.0
+cloudpickle==3.1.1
+cmake==3.31.6
+cmdstanpy==1.2.5
+colorcet==3.1.0
+colorlover==0.3.0
+colour==0.1.5
+community==1.0.0b1
+confection==0.1.5
+cons==0.4.6
+contourpy==1.3.2
+cramjam==2.10.0
+cryptography==43.0.3
+cuda-python==12.6.2.post1
+cudf-cu12 @ https://pypi.nvidia.com/cudf-cu12/cudf_cu12-25.2.1-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
+cudf-polars-cu12==25.2.2
+cufflinks==0.17.3
+cuml-cu12==25.2.1
+cupy-cuda12x==13.3.0
+cuvs-cu12==25.2.1
+cvxopt==1.3.2
+cvxpy==1.6.5
+cycler==0.12.1
+cyipopt==1.5.0
+cymem==2.0.11
+Cython==3.0.12
+dashscope==1.23.2
+dask==2024.12.1
+dask-cuda==25.2.0
+dask-cudf-cu12==25.2.2
+dask-expr==1.1.21
+dataproc-spark-connect==0.7.2
+datascience==0.17.6
+datasets==3.5.1
+db-dtypes==1.4.2
+dbus-python==1.2.18
+debugpy==1.8.0
+decorator==4.4.2
+defusedxml==0.7.1
+Deprecated==1.2.18
+diffusers==0.33.1
+dill==0.3.8
+distributed==2024.12.1
+distributed-ucxx-cu12==0.42.0
+distro==1.9.0
+dlib==19.24.6
+dm-tree==0.1.9
+docker-pycreds==0.4.0
+docstring_parser==0.16
+docutils==0.21.2
+dopamine_rl==4.1.2
+duckdb==1.2.2
+earthengine-api==1.5.13
+easydict==1.13
+editdistance==0.8.1
+eerepr==0.1.1
+einops==0.8.1
+en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl#sha256=1932429db727d4bff3deed6b34cfc05df17794f4a52eeb26cf8928f7c1a0fb85
+entrypoints==0.4
+et_xmlfile==2.0.0
+etils==1.12.2
+etuples==0.3.9
+Farama-Notifications==0.0.4
+fastai==2.7.19
+fastapi==0.115.12
+fastcore==1.7.29
+fastdownload==0.0.7
+fastjsonschema==2.21.1
+fastprogress==1.0.3
+fastrlock==0.8.3
+ffmpy==0.5.0
+filelock==3.18.0
+firebase-admin==6.8.0
+Flask==3.1.0
+flatbuffers==25.2.10
+flax==0.10.6
+folium==0.19.5
+fonttools==4.57.0
+frozendict==2.4.6
+frozenlist==1.6.0
+fsspec==2025.3.0
+future==1.0.0
+gast==0.6.0
+gcsfs==2025.3.2
+GDAL==3.6.4
+gdown==5.2.0
+geemap==0.35.3
+geocoder==1.38.1
+geographiclib==2.0
+geopandas==1.0.1
+geopy==2.4.1
+gin-config==0.5.0
+gitdb==4.0.12
+GitPython==3.1.44
+glob2==0.7
+google==2.0.3
+google-ai-generativelanguage==0.6.15
+google-api-core==2.24.2
+google-api-python-client==2.169.0
+google-auth==2.38.0
+google-auth-httplib2==0.2.0
+google-auth-oauthlib==1.2.2
+google-cloud-aiplatform==1.91.0
+google-cloud-bigquery==3.31.0
+google-cloud-bigquery-connection==1.18.2
+google-cloud-bigquery-storage==2.31.0
+google-cloud-bigtable==2.30.1
+google-cloud-core==2.4.3
+google-cloud-dataproc==5.18.1
+google-cloud-datastore==2.21.0
+google-cloud-firestore==2.20.2
+google-cloud-functions==1.20.3
+google-cloud-iam==2.19.0
+google-cloud-language==2.17.1
+google-cloud-pubsub==2.25.0
+google-cloud-resource-manager==1.14.2
+google-cloud-spanner==3.54.0
+google-cloud-storage==2.19.0
+google-cloud-translate==3.20.2
+google-colab @ file:///colabtools/dist/google_colab-1.0.0.tar.gz
+google-crc32c==1.7.1
+google-genai==1.13.0
+google-generativeai==0.8.5
+google-pasta==0.2.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.70.0
+googledrivedownloader==1.1.0
+gradio==5.29.0
+gradio_client==1.10.0
+graphviz==0.20.3
+greenlet==3.2.1
+groovy==0.1.2
+grpc-google-iam-v1==0.14.2
+grpc-interceptor==0.15.4
+grpcio==1.71.0
+grpcio-status==1.71.0
+grpclib==0.4.7
+gspread==6.2.0
+gspread-dataframe==4.0.0
+gym==0.25.2
+gym-notices==0.0.8
+gymnasium==1.1.1
+h11==0.16.0
+h2==4.2.0
+h5netcdf==1.6.1
+h5py==3.13.0
+hdbscan==0.8.40
+highspy==1.10.0
+holidays==0.71
+holoviews==1.20.2
+hpack==4.1.0
+html5lib==1.1
+httpcore==1.0.9
+httpimport==1.4.1
+httplib2==0.22.0
+httpx==0.28.1
+huggingface-hub==0.30.2
+humanize==4.12.3
+hyperframe==6.1.0
+hyperopt==0.2.7
+ibis-framework==9.5.0
+idna==3.10
+imageio==2.37.0
+imageio-ffmpeg==0.6.0
+imagesize==1.4.1
+imbalanced-learn==0.13.0
+immutabledict==4.2.1
+importlib_metadata==8.7.0
+importlib_resources==6.5.2
+imutils==0.5.4
+inflect==7.5.0
+iniconfig==2.1.0
+intel-cmplr-lib-ur==2025.1.1
+intel-openmp==2025.1.1
+ipyevents==2.0.2
+ipyfilechooser==0.6.0
+ipykernel==6.17.1
+ipyleaflet==0.19.2
+ipyparallel==8.8.0
+ipython==7.34.0
+ipython-genutils==0.2.0
+ipython-sql==0.5.0
+ipytree==0.2.2
+ipywidgets==7.7.1
+itsdangerous==2.2.0
+jaraco.classes==3.4.0
+jaraco.context==6.0.1
+jaraco.functools==4.1.0
+jax==0.5.2
+jax-cuda12-pjrt==0.5.1
+jax-cuda12-plugin==0.5.1
+jaxlib==0.5.1
+jeepney==0.9.0
+jieba==0.42.1
+Jinja2==3.1.6
+jiter==0.9.0
+joblib==1.4.2
+jsonpatch==1.33
+jsonpickle==4.0.5
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2025.4.1
+jupyter-client==6.1.12
+jupyter-console==6.1.0
+jupyter-leaflet==0.19.2
+jupyter-server==1.16.0
+jupyter_core==5.7.2
+jupyter_kernel_gateway @ git+https://github.com/googlecolab/kernel_gateway@b134e9945df25c2dcb98ade9129399be10788671
+jupyterlab_pygments==0.3.0
+jupyterlab_widgets==3.0.14
+kaggle==1.7.4.2
+kagglehub==0.3.12
+keras==3.8.0
+keras-hub==0.18.1
+keras-nlp==0.18.1
+keyring==25.6.0
+keyrings.google-artifactregistry-auth==1.1.2
+kiwisolver==1.4.8
+langchain==0.3.24
+langchain-core==0.3.56
+langchain-text-splitters==0.3.8
+langcodes==3.5.0
+langsmith==0.3.39
+language_data==1.3.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+lazy_loader==0.4
+libclang==18.1.1
+libcudf-cu12 @ https://pypi.nvidia.com/libcudf-cu12/libcudf_cu12-25.2.1-py3-none-manylinux_2_28_x86_64.whl
+libcugraph-cu12==25.2.0
+libcuml-cu12==25.2.1
+libcuvs-cu12==25.2.1
+libkvikio-cu12==25.2.1
+libraft-cu12==25.2.0
+librosa==0.11.0
+libucx-cu12==1.18.1
+libucxx-cu12==0.42.0
+lightgbm @ file:///tmp/lightgbm/LightGBM/dist/lightgbm-4.5.0-py3-none-linux_x86_64.whl
+linkify-it-py==2.0.3
+llvmlite==0.43.0
+locket==1.0.0
+logical-unification==0.4.6
+lxml==5.4.0
+Mako==1.1.3
+marisa-trie==1.2.1
+Markdown==3.8
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.10.0
+matplotlib-inline==0.1.7
+matplotlib-venn==1.1.2
+mdit-py-plugins==0.4.2
+mdurl==0.1.2
+miniKanren==1.0.3
+missingno==0.5.2
+mistune==3.1.3
+mizani==0.13.3
+mkl==2025.0.1
+ml-dtypes==0.4.1
+mlxtend==0.23.4
+modelscope_studio==1.2.4
+more-itertools==10.7.0
+moviepy==1.0.3
+mpmath==1.3.0
+msgpack==1.1.0
+multidict==6.4.3
+multipledispatch==1.0.0
+multiprocess==0.70.16
+multitasking==0.0.11
+murmurhash==1.0.12
+music21==9.3.0
+namex==0.0.9
+narwhals==1.37.1
+natsort==8.4.0
+nbclassic==1.3.0
+nbclient==0.10.2
+nbconvert==7.16.6
+nbformat==5.10.4
+ndindex==1.9.2
+nest-asyncio==1.6.0
+networkx==3.4.2
+nibabel==5.3.2
+nltk==3.9.1
+notebook==6.5.7
+notebook_shim==0.2.4
+numba==0.60.0
+numba-cuda==0.2.0
+numexpr==2.10.2
+numpy==2.0.2
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvcc-cu12==12.5.82
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-ml-py==12.570.86
+nvidia-nccl-cu12==2.21.5
+nvidia-nvcomp-cu12==4.2.0.11
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+nvtx==0.2.11
+nx-cugraph-cu12 @ https://pypi.nvidia.com/nx-cugraph-cu12/nx_cugraph_cu12-25.2.0-py3-none-any.whl
+oauth2client==4.1.3
+oauthlib==3.2.2
+openai==1.76.2
+opencv-contrib-python==4.11.0.86
+opencv-python==4.11.0.86
+opencv-python-headless==4.11.0.86
+openpyxl==3.1.5
+opentelemetry-api==1.16.0
+opentelemetry-sdk==1.16.0
+opentelemetry-semantic-conventions==0.37b0
+opt_einsum==3.4.0
+optax==0.2.4
+optree==0.15.0
+orbax-checkpoint==0.11.13
+orjson==3.10.18
+osqp==1.0.3
+packaging==24.2
+pandas==2.2.2
+pandas-datareader==0.10.0
+pandas-gbq==0.28.0
+pandas-stubs==2.2.2.240909
+pandocfilters==1.5.1
+panel==1.6.3
+param==2.2.0
+parso==0.8.4
+parsy==2.1
+partd==1.4.2
+pathlib==1.0.1
+patsy==1.0.1
+peewee==3.18.1
+peft==0.15.2
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==11.2.1
+platformdirs==4.3.7
+plotly==5.24.1
+plotnine==0.14.5
+pluggy==1.5.0
+ply==3.11
+polars==1.21.0
+pooch==1.8.2
+portpicker==1.5.2
+preshed==3.0.9
+prettytable==3.16.0
+proglog==0.1.11
+progressbar2==4.5.0
+prometheus_client==0.21.1
+promise==2.3
+prompt_toolkit==3.0.51
+propcache==0.3.1
+prophet==1.1.6
+proto-plus==1.26.1
+protobuf==5.29.4
+psutil==5.9.5
+psycopg2==2.9.10
+ptyprocess==0.7.0
+py-cpuinfo==9.0.0
+py4j==0.10.9.7
+pyarrow==18.1.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pycairo==1.28.0
+pycocotools==2.0.8
+pycparser==2.22
+pydantic==2.11.4
+pydantic_core==2.33.2
+pydata-google-auth==1.9.1
+pydot==3.0.4
+pydotplus==2.0.2
+PyDrive==1.3.1
+PyDrive2==1.21.3
+pydub==0.25.1
+pyerfa==2.0.1.5
+pygame==2.6.1
+pygit2==1.18.0
+Pygments==2.19.1
+PyGObject==3.42.0
+PyJWT==2.10.1
+pylibcudf-cu12 @ https://pypi.nvidia.com/pylibcudf-cu12/pylibcudf_cu12-25.2.1-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
+pylibcugraph-cu12==25.2.0
+pylibraft-cu12==25.2.0
+pymc==5.22.0
+pymystem3==0.2.0
+pynndescent==0.5.13
+pynvjitlink-cu12==0.5.2
+pynvml==12.0.0
+pyogrio==0.10.0
+pyomo==6.9.2
+PyOpenGL==3.1.9
+pyOpenSSL==24.2.1
+pyparsing==3.2.3
+pyperclip==1.9.0
+pyproj==3.7.1
+pyproject_hooks==1.2.0
+pyshp==2.3.1
+PySocks==1.7.1
+pyspark==3.5.1
+pytensor==2.30.3
+pytest==8.3.5
+python-apt==0.0.0
+python-box==7.3.2
+python-dateutil==2.9.0.post0
+python-louvain==0.16
+python-multipart==0.0.20
+python-slugify==8.0.4
+python-snappy==0.7.3
+python-utils==3.9.1
+pytz==2025.2
+pyviz_comms==3.0.4
+PyYAML==6.0.2
+pyzmq==24.0.1
+raft-dask-cu12==25.2.0
+rapids-dask-dependency==25.2.0
+ratelim==0.1.6
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+requirements-parser==0.9.0
+rich==13.9.4
+rmm-cu12==25.2.0
+roman-numerals-py==3.1.0
+rpds-py==0.24.0
+rpy2==3.5.17
+rsa==4.9.1
+ruff==0.11.8
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-image==0.25.2
+scikit-learn==1.6.1
+scipy==1.15.2
+scooby==0.10.1
+scs==3.2.7.post2
+seaborn==0.13.2
+SecretStorage==3.3.3
+semantic-version==2.10.0
+Send2Trash==1.8.3
+sentence-transformers==3.4.1
+sentencepiece==0.2.0
+sentry-sdk==2.27.0
+setproctitle==1.3.6
+shap==0.47.2
+shapely==2.1.0
+shellingham==1.5.4
+simple-parsing==0.1.7
+simplejson==3.20.1
+simsimd==6.2.1
+six==1.17.0
+sklearn-compat==0.1.3
+sklearn-pandas==2.2.0
+slicer==0.0.8
+smart-open==7.1.0
+smmap==5.0.2
+sniffio==1.3.1
+snowballstemmer==2.2.0
+sortedcontainers==2.4.0
+soundfile==0.13.1
+soupsieve==2.7
+soxr==0.5.0.post1
+spacy==3.8.5
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spanner-graph-notebook==1.1.6
+Sphinx==8.2.3
+sphinxcontrib-applehelp==2.0.0
+sphinxcontrib-devhelp==2.0.0
+sphinxcontrib-htmlhelp==2.1.0
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==2.0.0
+sphinxcontrib-serializinghtml==2.0.0
+SQLAlchemy==2.0.40
+sqlglot==25.20.2
+sqlparse==0.5.3
+srsly==2.5.1
+stanio==0.5.1
+starlette==0.46.2
+statsmodels==0.14.4
+stringzilla==3.12.5
+sympy==1.13.1
+tables==3.10.2
+tabulate==0.9.0
+tbb==2022.1.0
+tblib==3.1.0
+tcmlib==1.3.0
+tenacity==9.1.2
+tensorboard==2.18.0
+tensorboard-data-server==0.7.2
+tensorflow==2.18.0
+tensorflow-datasets==4.9.8
+tensorflow-hub==0.16.1
+tensorflow-io-gcs-filesystem==0.37.1
+tensorflow-metadata==1.17.1
+tensorflow-probability==0.25.0
+tensorflow-text==2.18.1
+tensorflow_decision_forests==1.11.0
+tensorstore==0.1.74
+termcolor==3.1.0
+terminado==0.18.1
+text-unidecode==1.3
+textblob==0.19.0
+tf-slim==1.1.0
+tf_keras==2.18.0
+thinc==8.3.6
+threadpoolctl==3.6.0
+tifffile==2025.3.30
+timm==1.0.15
+tinycss2==1.4.0
+tokenizers==0.21.1
+toml==0.10.2
+tomlkit==0.13.2
+toolz==0.12.1
+torch @ https://download.pytorch.org/whl/cu124/torch-2.6.0%2Bcu124-cp311-cp311-linux_x86_64.whl
+torchaudio @ https://download.pytorch.org/whl/cu124/torchaudio-2.6.0%2Bcu124-cp311-cp311-linux_x86_64.whl
+torchsummary==1.5.1
+torchvision @ https://download.pytorch.org/whl/cu124/torchvision-0.21.0%2Bcu124-cp311-cp311-linux_x86_64.whl
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.7.1
+traittypes==0.2.1
+transformers==4.51.3
+treelite==4.4.1
+treescope==0.1.9
+triton==3.2.0
+tweepy==4.15.0
+typeguard==4.4.2
+typer==0.15.3
+types-pytz==2025.2.0.20250326
+types-setuptools==80.0.0.20250429
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+tzdata==2025.2
+tzlocal==5.3.1
+uc-micro-py==1.0.3
+ucx-py-cu12==0.42.0
+ucxx-cu12==0.42.0
+umap-learn==0.5.7
+umf==0.10.0
+uritemplate==4.1.1
+urllib3==2.4.0
+uvicorn==0.34.2
+vega-datasets==0.9.0
+wadllib==1.3.6
+wandb==0.19.10
+wasabi==1.1.3
+wcwidth==0.2.13
+weasel==0.4.1
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==15.0.1
+Werkzeug==3.1.3
+widgetsnbextension==3.6.10
+wordcloud==1.9.4
+wrapt==1.17.2
+wurlitzer==3.1.1
+xarray==2025.3.1
+xarray-einstats==0.8.0
+xgboost==2.1.4
+xlrd==2.0.1
+xxhash==3.5.0
+xyzservices==2025.4.0
+yarl==1.20.0
+ydf==0.11.0
+yellowbrick==1.5
+yfinance==0.2.57
+zict==3.0.0
+zipp==3.21.0
+zstandard==0.23.0

ui_components/logo.py

@@ -0,0 +1,15 @@
+import modelscope_studio.components.antd as antd
+import modelscope_studio.components.base as ms
+
+
+def Logo():
+    with antd.Typography.Title(level=1,
+                               elem_style=dict(fontSize=24,
+                                               padding=8,
+                                               margin=0)):
+        with antd.Flex(align="center", gap="small", justify="center"):
+            antd.Image('./assets/DownArrow.jpg',
+                       preview=False,
+                       alt="logo",
+                       width=96,
+                       height=96)

ui_components/settings_header.py

@@ -0,0 +1,54 @@
+import gradio as gr
+import modelscope_studio.components.antd as antd
+import modelscope_studio.components.antdx as antdx
+import modelscope_studio.components.base as ms
+
+from config import DEFAULT_SETTINGS, MODEL_OPTIONS, MAX_THINKING_BUDGET, MIN_THINKING_BUDGET, get_text
+
+
+def SettingsHeader():
+    state = gr.State({"open": True})
+    with antdx.Sender.Header(title=get_text("Settings", "设置"),
+                             open=True) as settings_header:
+        with antd.Form(value=DEFAULT_SETTINGS) as settings_form:
+            with antd.Form.Item(form_name="model",
+                                label=get_text("Chat Model", "对话模型")):
+                with antd.Select(options=MODEL_OPTIONS):
+                    with ms.Slot("labelRender",
+                                 params_mapping="""(option) => ({
+                                label: option.label, 
+                                link: { href: window.MODEL_OPTIONS_MAP[option.value].link },  
+                            })"""):
+                        antd.Typography.Text(as_item="label")
+                        antd.Typography.Link(get_text("Model Link", "模型链接"),
+                                             href_target="_blank",
+                                             as_item="link")
+
+            with antd.Form.Item(form_name="thinking_budget",
+                                label=get_text("Thinking Budget", "思考预算"),
+                                elem_classes="setting-form-thinking-budget"):
+                antd.Slider(elem_style=dict(flex=1, marginRight=14),
+                            min=MIN_THINKING_BUDGET,
+                            max=MAX_THINKING_BUDGET,
+                            tooltip=dict(formatter="(v) => `${v}k`"))
+                antd.InputNumber(max=MAX_THINKING_BUDGET,
+                                 min=MIN_THINKING_BUDGET,
+                                 elem_style=dict(width=100),
+                                 addon_after="k")
+            # with antd.Form.Item(form_name="sys_prompt",
+            #                     label=get_text("System Prompt", "系统提示")):
+            #     antd.Input.Textarea(auto_size=dict(minRows=3, maxRows=6))
+
+    def close_header(state_value):
+        state_value["open"] = False
+        return gr.update(value=state_value)
+
+    state.change(fn=lambda state_value: gr.update(open=state_value["open"]),
+                 inputs=[state],
+                 outputs=[settings_header])
+
+    settings_header.open_change(fn=close_header,
+                                inputs=[state],
+                                outputs=[state])
+
+    return state, settings_form

ui_components/thinking_button.py

@@ -0,0 +1,28 @@
+import modelscope_studio.components.antd as antd
+import modelscope_studio.components.base as ms
+import gradio as gr
+from config import get_text
+
+
+def ThinkingButton():
+    state = gr.State({"enable_thinking": True})
+    with antd.Button(get_text("Thinking", "深度思考"),
+                     shape="round",
+                     color="primary",
+                     variant="solid") as thinking_btn:
+        with ms.Slot("icon"):
+            antd.Icon("SunOutlined")
+
+    def toggle_thinking(state_value):
+        state_value["enable_thinking"] = not state_value["enable_thinking"]
+        return gr.update(value=state_value)
+
+    def apply_state_change(state_value):
+        return gr.update(
+            variant="solid" if state_value["enable_thinking"] else "")
+
+    state.change(fn=apply_state_change, inputs=[state], outputs=[thinking_btn])
+
+    thinking_btn.click(fn=toggle_thinking, inputs=[state], outputs=[state])
+
+    return state