Update app.py

app.py

@@ -1,64 +1,86 @@
+import json
+import re
+import random
+import html
+import requests
+from bs4 import BeautifulSoup
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
+from llama_cpp_agent import LlamaCppAgent
+from llama_cpp_agent.providers import LlamaCppPythonProvider
+from llama_cpp_agent.chat_history import BasicChatHistory
+from llama_cpp_agent.chat_history.messages import Roles
+from huggingface_hub import hf_hub_download
 
-"""
-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")
+# Download your GGUF model from the HF repo
+:contentReference[oaicite:2]{index=2}
+:contentReference[oaicite:3]{index=3}
 
+# Scraping logic (adjusted from your script):
+:contentReference[oaicite:4]{index=4}
+    :contentReference[oaicite:5]{index=5}
+    return {
+        "product_title": title_text,
+        "price": price_text,
+        "rating": rating_text,
+        "first_review": review_text,
+        :contentReference[oaicite:6]{index=6}
+    }
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Inference function
+:contentReference[oaicite:7]{index=7}
+    :contentReference[oaicite:8]{index=8}
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Format prompt
+    prompt = json.dumps({
+        "product_title": prod["product_title"],
+        "price": prod["price"],
+        "rating": prod["rating"],
+        "first_review": prod["first_review"],
+        "about_this_item": prod["about_this_item"],
+    }, ensure_ascii=False)
+    full_prompt = (
+        "Write a product review based on the following product details.\n"
+        f"Your input is:\n{prompt}"
+    )
 
-    messages.append({"role": "user", "content": message})
+    # Llama.cpp setup
+    llm = Llama(model_path=MODEL_PATH, n_ctx=2048)
+    provider = LlamaCppPythonProvider(llm)
+    agent = LlamaCppAgent(provider, system_prompt="", predefined_messages_formatter_type="CHATML")
+    settings = provider.get_provider_default_settings()
+    settings.stream = False
 
-    response = ""
+    # Run inference
+    stream = agent.get_chat_response(
+        full_prompt,
+        llm_sampling_settings=settings,
+        chat_history=BasicChatHistory(),
+        returns_streaming_generator=False
+    )
+    full_text = "".join(token for token in stream)
 
-    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
+    # Extract JSON from response
+    match = re.search(r'\{.*"title".*"review".*\}', full_text, re.DOTALL)
+    if match:
+        review = json.loads(match.group())
+    else:
+        review = {"title": "", "review": full_text.strip()}
 
-        response += token
-        yield response
+    return prod["product_title"], review["title"], review["review"]
 
-
-"""
-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)",
-        ),
+# Gradio UI
+:contentReference[oaicite:9]{index=9}
+    fn=review_generation_ui,
+    :contentReference[oaicite:10]{index=10}
+    outputs=[
+        :contentReference[oaicite:11]{index=11}
+        :contentReference[oaicite:12]{index=12}
+        :contentReference[oaicite:13]{index=13}
     ],
+    :contentReference[oaicite:14]{index=14}
+    :contentReference[oaicite:15]{index=15}
 )
 
-
-if __name__ == "__main__":
+:contentReference[oaicite:16]{index=16}
     demo.launch()