Update app.py

app.py

@@ -1,64 +1,91 @@
+# app.py
+
+import pandas as pd
+from fastapi import FastAPI
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+import faiss
+from datasets import load_dataset
+
+# Load the dataset
+support_data = load_dataset("rjac/e-commerce-customer-support-qa")
+faq_data = pd.read_csv("Ecommerce_FAQs.csv")
+
+# Data preparation
+faq_data.rename(columns={'prompt': 'Question', 'response': 'Answer'}, inplace=True)
+faq_data = faq_data[['Question', 'Answer']]
+support_data_df = pd.DataFrame(support_data['train'])
+
+def extract_conversation(data):
+    try:
+        parts = data.split("\n\n")
+        question = parts[1].split(": ", 1)[1] if len(parts) > 1 else ""
+        answer = parts[2].split(": ", 1)[1] if len(parts) > 2 else ""
+        return pd.Series({"Question": question, "Answer": answer})
+    except IndexError:
+        return pd.Series({"Question": "", "Answer": ""})
+
+support_data_df[['Question', 'Answer']] = support_data_df['conversation'].apply(extract_conversation)
+combined_data = pd.concat([faq_data, support_data_df[['Question', 'Answer']]], ignore_index=True)
+
+# Initialize SBERT Model
+model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
+
+# Generate and Index Embeddings
+questions = combined_data['Question'].tolist()
+embeddings = model.encode(questions, convert_to_tensor=True)
+index = faiss.IndexFlatL2(embeddings.shape[1])
+index.add(embeddings.cpu().numpy())
+
+# Define FastAPI app and model
+app = FastAPI()
+
+class Query(BaseModel):
+    question: str
+
+@app.post("/ask")
+def ask_bot(query: Query):
+    question_embedding = model.encode([query.question], convert_to_tensor=True)
+    question_embedding_np = question_embedding.cpu().numpy()
+    _, closest_index = index.search(question_embedding_np, k=1)
+    best_match_idx = closest_index[0][0]
+    answer = combined_data.iloc[best_match_idx]['Answer']
+    return {"answer": answer}
+
+# Gradio Interface
+
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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
-"""
+import requests
+
+# Define the URL of your FastAPI endpoint
+API_URL = "http://localhost:8000/ask"  # Update to your deployed FastAPI URL if needed
+
+def respond(message, history: list[tuple[str, str]]):
+    payload = {"question": message}
+    
+    try:
+        response = requests.post(API_URL, json=payload)
+        response.raise_for_status()
+        response_data = response.json()
+        answer = response_data.get("answer", "Sorry, I didn't get that.")
+    except requests.exceptions.RequestException as e:
+        answer = f"Request Error: {str(e)}"
+    
+    # Update history
+    history.append((message, answer))
+    return answer, history
+
+# Gradio Chat Interface
 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)",
-        ),
-    ],
 )
 
-
 if __name__ == "__main__":
+    import threading
+    import uvicorn
+
+    # Run FastAPI in a separate thread
+    threading.Thread(target=uvicorn.run, args=(app,), kwargs={"host": "0.0.0.0", "port": 8000}).start()
+    
+    # Launch Gradio interface
     demo.launch()