Update app.py

app.py

@@ -1,64 +1,95 @@
+import openai
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+from bs4 import BeautifulSoup
 
-"""
-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")
+# Initialize OpenAI with your API key
+openai.api_key = "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"
 
+# Function to fetch and crawl website content
+def fetch_website_content(url):
+    try:
+        # Send a GET request to the website
+        response = requests.get(url)
+        if response.status_code != 200:
+            return "Error: Could not fetch the webpage. Please check the URL."
+        
+        # Parse the website content with BeautifulSoup
+        soup = BeautifulSoup(response.content, 'html.parser')
+        
+        # Extract text content from paragraph tags
+        website_text = " ".join([p.text for p in soup.find_all('p')])
+        return website_text
+    
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Function to split content into chunks that fit within the token limits
+def split_content_into_chunks(content, max_chunk_size=3000):
+    # Split the content into chunks based on token limits
+    words = content.split()
+    chunks = []
+    
+    while words:
+        chunk = words[:max_chunk_size]
+        chunks.append(" ".join(chunk))
+        words = words[max_chunk_size:]
+    
+    return chunks
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Function to query GPT model with website content
+def ask_question(url, question):
+    # Fetch website content
+    website_text = fetch_website_content(url)
+    
+    if "Error" in website_text:
+        return website_text
+    
+    # Split content into manageable chunks based on OpenAI's token limit
+    chunks = split_content_into_chunks(website_text)
+    
+    # Initialize a variable to hold the entire response
+    full_answer = ""
+    
+    # Query GPT model for each chunk
+    for chunk in chunks:
+        # Prepare the prompt for GPT
+        messages = [
+            {"role": "system", "content": "You are a helpful assistant who answers questions based on the following website content."},
+            {"role": "user", "content": f"Website content: {chunk}\n\nQuestion: {question}"}
+        ]
+        
+        # Use GPT-3.5-turbo model to generate an answer
+        try:
+            response = openai.ChatCompletion.create(
+                model="gpt-3.5-turbo",  # Use gpt-4 if you have access to it
+                messages=messages,
+                max_tokens=3000,  # Increase max_tokens to the highest possible value
+                temperature=0.5,
+            )
+            answer = response.choices[0].message['content'].strip()
+            full_answer += answer + "\n\n"  # Append chunked responses together
+            
+        except Exception as e:
+            return f"Error: {str(e)}"
+    
+    return full_answer
 
-    messages.append({"role": "user", "content": message})
+# Gradio interface for chatbot
+def chatbot(url, question):
+    return ask_question(url, question)
 
-    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
-"""
-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)",
-        ),
+# Define Gradio interface using new syntax
+iface = gr.Interface(
+    fn=chatbot,
+    inputs=[
+        gr.Textbox(label="Website URL", placeholder="Enter website URL here..."),
+        gr.Textbox(label="Your Question", placeholder="Ask a question to understand what is in the website or generate article based on the website information...")
     ],
+    outputs=gr.Textbox(),
+    title="Contentigo - Lite",
+    description="Ask questions about the content of any website. Also, generate articles based on the website content."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio interface
+iface.launch()