first commit

app.py

@@ -0,0 +1,144 @@
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import gradio as gr
+
+# Set the random seed for reproducibility
+torch.random.manual_seed(0)
+
+# Load the model and tokenizer from Hugging Face
+model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Phi-3.5-mini-instruct",
+    device_map="cpu",
+    # device_map="cuda",
+    torch_dtype="auto",
+    trust_remote_code=True,
+)
+
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct")
+
+# Create a text-generation pipeline
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+)
+
+# Define the pipeline arguments
+generation_args = {
+    "max_new_tokens": 500,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+chat_session = {}
+
+
+# Function to generate responses based on the entire chat history
+def generate_response(chat_history):
+    messages = [{"role": "system", "content": "You are a helpful AI assistant."}]
+    
+    # Append the chat history (user and assistant messages)
+    for user_message, assistant_message in chat_history:
+        messages.append({"role": "user", "content": user_message})
+        messages.append({"role": "assistant", "content": assistant_message})
+    
+    # Generate response for the latest user message
+    user_input = chat_history[-1][0]  # The latest user message
+    messages.append({"role": "user", "content": user_input})
+    response = pipe(messages, **generation_args)
+    
+    # Append the assistant response to the chat history
+    assistant_response = response[0]["generated_text"]
+    return assistant_response
+
+
+# Function to update chat
+def chat(user_message,history,session):
+
+    if session == "":
+        return history, "Error: Session ID cannot be empty. Please start a new chat."
+        
+
+    history = history or []  # Initialize history if empty
+        
+    # Generate assistant response based on the history
+    assistant_message = generate_response(history + [(user_message, "")])
+    
+    # Append user and assistant messages to history
+    history.append([user_message, assistant_message])
+    chat_session[session] = history
+
+    return history, ""
+
+
+def get_session_list():
+    return list(chat_session.keys())
+
+# Function to create new chat and return updated session list
+def new_chat():
+    session = f'session:{len(chat_session) + 1}'
+    chat_session[session] = []  # Initialize empty chat history for the new session
+    return [], "", session, get_session_list()  # Return the new session and update session list
+
+# Function to fetch old chat session history
+def old_chat(sessions):
+    return chat_session.get(sessions, [])
+
+# Function to reset chat history
+def reset_button():
+    global chat_session  # Access the global chat_session
+    chat_session = {}  # Reset the global chat_session
+    return [], "", "",[],""  # Reset chat history, session, and input field
+
+
+
+with gr.Blocks(css=".small-btn {width: 100px !important;} .large-textbox {width: 100% !important;}") as demo:
+    gr.Markdown("# 🤖 AI Assistant")
+
+    with gr.Column():
+        new_chat_button = gr.Button("Start New Chat")
+    with gr.Row():
+        with gr.Column(scale=3):
+            chatbot = gr.Chatbot(elem_id="chatbot")
+            with gr.Row():
+                with gr.Column(scale=5):
+                    user_input = gr.Textbox(
+                        show_label=False,
+                        placeholder="Type your message here...",
+                        container=False,
+                        elem_classes="large-textbox"
+                    )
+                with gr.Column(scale=1):
+                    send_button = gr.Button("Send", variant="primary", elem_classes="small-btn")
+            
+        with gr.Column(scale=1):
+            session = gr.Textbox(label="Current Session", interactive=False)
+            session_list = gr.Dropdown(label="Available Sessions", choices=get_session_list(), allow_custom_value=True)
+            load_session = gr.Textbox(label="Load Session", interactive=True)
+            with gr.Row():
+                get_old_session_button = gr.Button("Load Session")
+                avail_session = gr.Button("Get Available Session")
+            reset_button_ = gr.Button("Reset All", variant="secondary")
+
+    # Button click actions
+    user_input.submit(chat, [user_input, chatbot, session], [chatbot, user_input])
+    send_button.click(chat, [user_input, chatbot, session], [chatbot, user_input])  # Send button
+    new_chat_button.click(new_chat, [], [chatbot, user_input, session, session_list])  # Also update the session list
+    get_old_session_button.click(old_chat, [load_session], [chatbot])
+    reset_button_.click(reset_button, [], [chatbot, session, user_input, session_list, load_session])
+    avail_session.click(get_session_list, [], [session_list])
+
+# Launch the Gradio app
+demo.launch()
+
+
+
+
+
+
+
+
+
+

requirements.txt

@@ -0,0 +1,81 @@
+accelerate==0.26.0
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.3.0
+cycler==0.12.1
+exceptiongroup==1.2.2
+fastapi==0.115.0
+ffmpy==0.4.0
+filelock==3.16.1
+fonttools==4.54.1
+fsspec==2024.9.0
+gradio==4.44.1
+gradio_client==1.3.0
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.25.1
+idna==3.10
+importlib_resources==6.4.5
+Jinja2==3.1.4
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.3
+numpy==2.1.2
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.77
+nvidia-nvtx-cu12==12.1.105
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+pillow==10.4.0
+psutil==6.0.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+rich==13.9.2
+ruff==0.6.9
+safetensors==0.4.5
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tokenizers==0.20.0
+tomlkit==0.12.0
+torch==2.4.1
+tqdm==4.66.5
+transformers==4.45.2
+triton==3.0.0
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.31.0
+websockets==12.0