Initial commit: Customer Support Chatbot with DialoGPT-medium

.gitignore

@@ -0,0 +1,11 @@
+__pycache__/
+*.py[cod]
+*$py.class
+.env
+.venv
+env/
+venv/
+ENV/
+.idea/
+.vscode/
+*.log 

README.md

@@ -12,3 +12,57 @@ short_description: AiAssistant
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Customer Support Chatbot
+
+A beautiful chatbot built using DialoGPT-medium and the Victorano/customer-support-1k dataset. The chatbot features a clean and modern Gradio interface with conversation history support.
+
+## Features
+
+- Powered by DialoGPT-medium model
+- Clean and modern Gradio interface
+- Conversation history within the same session
+- Copy button for messages
+- Bot avatar using DiceBear API
+- Responsive design
+
+## Setup
+
+1. Install the required dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+2. Run the application:
+```bash
+python app.py
+```
+
+## Deployment on Hugging Face Spaces
+
+1. Create a new Space on Hugging Face
+2. Choose "Gradio" as the SDK
+3. Upload these files to your Space:
+   - app.py
+   - requirements.txt
+   - README.md
+
+The Space will automatically build and deploy your chatbot.
+
+## Usage
+
+1. Type your message in the text input box
+2. Press Enter or click the Send button
+3. The chatbot will generate a response based on your input
+4. The conversation history will be maintained in the chat window
+5. You can copy any message using the copy button that appears on hover
+
+## Model Details
+
+- Model: microsoft/DialoGPT-medium
+- Dataset: Victorano/customer-support-1k
+- Generation Parameters:
+  - max_length: 1000
+  - temperature: 0.7
+  - top_k: 50
+  - top_p: 0.9

app.py

@@ -0,0 +1,69 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from datasets import load_dataset
+import random
+
+# Load the model and tokenizer
+model_name = "microsoft/DialoGPT-medium"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Load the customer support dataset
+dataset = load_dataset("Victorano/customer-support-1k")
+
+def generate_response(message, history):
+    # Encode the user message
+    input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
+    
+    # Generate response
+    with torch.no_grad():
+        output_ids = model.generate(
+            input_ids,
+            max_length=1000,
+            num_return_sequences=1,
+            no_repeat_ngram_size=2,
+            temperature=0.7,
+            top_k=50,
+            top_p=0.9,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    # Decode and return the response
+    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    return response
+
+# Create the Gradio interface
+with gr.Blocks(css="footer {display: none !important}") as demo:
+    gr.Markdown("""
+    # 🤖 Customer Support Chatbot
+    This chatbot is powered by DialoGPT-medium and trained on customer support conversations.
+    """)
+    
+    chatbot = gr.Chatbot(
+        [],
+        elem_id="chatbot",
+        bubble_full_width=False,
+        avatar_images=(None, "https://api.dicebear.com/7.x/bottts/svg?seed=1"),
+        height=500,
+        show_copy_button=True,
+    )
+    
+    with gr.Row():
+        txt = gr.Textbox(
+            show_label=False,
+            placeholder="Type your message here...",
+            container=False
+        )
+        submit_btn = gr.Button("Send", variant="primary")
+    
+    # Handle user input and generate response
+    def user_input(message, history):
+        return "", history + [[message, generate_response(message, history)]]
+    
+    # Connect the interface components
+    txt.submit(user_input, [txt, chatbot], [txt, chatbot])
+    submit_btn.click(user_input, [txt, chatbot], [txt, chatbot])
+
+if __name__ == "__main__":
+    demo.launch() 

requirements.txt

@@ -0,0 +1,4 @@
+gradio==4.19.2
+transformers==4.37.2
+torch==2.2.0
+datasets==2.17.1