File size: 10,003 Bytes
aac0403
 
 
 
 
 
e09ca3f
aac0403
 
 
 
e09ca3f
aac0403
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
883f71f
 
 
aac0403
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
from langchain_community.document_loaders import WebBaseLoader
from langchain_groq import ChatGroq
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnableLambda
from dotenv import load_dotenv
import streamlit as st
import os
import validators
import time
from urllib.parse import urlparse

# Load environment variables
load_dotenv()

# Page configuration
st.set_page_config(
    page_title="Web Q&A ChatBot",
    page_icon="πŸ€–",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Custom CSS for better styling
st.markdown("""
<style>
    .main-header {
        text-align: center;
        padding: 1rem 0;
        color: #1f77b4;
    }
    .stAlert {
        margin-top: 1rem;
    }
    .success-box {
        padding: 1rem;
        border-radius: 0.5rem;
        background-color: #d4edda;
        border: 1px solid #c3e6cb;
        color: #155724;
        margin: 1rem 0;
    }
    .error-box {
        padding: 1rem;
        border-radius: 0.5rem;
        background-color: #f8d7da;
        border: 1px solid #f5c6cb;
        color: #721c24;
        margin: 1rem 0;
    }
    .info-box {
        padding: 1rem;
        border-radius: 0.5rem;
        background-color: #d1ecf1;
        border: 1px solid #bee5eb;
        color: #0c5460;
        margin: 1rem 0;
    }
</style>
""", unsafe_allow_html=True)

def initialize_model():
    """Initialize the ChatGroq model"""
    try:
        model = ChatGroq(
            model="llama3-8b-8192", 
            temperature=0.7,
            max_tokens=1000
        )
        return model
    except Exception as e:
        st.error(f"Error initializing model: {str(e)}")
        return None

def create_prompt_template():
    """Create the prompt template"""
    return PromptTemplate(
        template="""You are a helpful AI assistant that answers questions based on web content.
        
        Question: {question}
        
        Web Content: {data}
        
        Instructions:
        - Provide a clear, accurate answer based on the web content
        - If the information is not available in the content, mention that
        - Be concise but comprehensive
        - Use bullet points when listing multiple items
        
        Answer:""",
        input_variables=["question", "data"]
    )

def extract_data(inputs):
    """Extract data from URL with better error handling"""
    try:
        url = inputs["url"]
        question = inputs["question"]
        
        # Validate URL
        if not validators.url(url):
            return {"question": question, "data": "Invalid URL format. Please provide a valid URL."}
        
        # Load web content
        with st.spinner("Loading web content..."):
            loader = WebBaseLoader(web_path=url)
            documents = loader.load()
            
            if not documents:
                return {"question": question, "data": "No content found at the provided URL."}
            
            content = documents[0].page_content
            
            # Limit content length to avoid token limits
            if len(content) > 12000:
                content = content[:10000] + "... (content truncated)"
            
            return {"question": question, "data": content}
            
    except Exception as e:
        error_msg = f"Error loading URL: {str(e)}"
        return {"question": inputs.get("question", ""), "data": error_msg}

def main():
    # Header
    st.markdown("<h1 class='main-header'>πŸ€– Web Q&A ChatBot</h1>", unsafe_allow_html=True)
    st.markdown("<p style='text-align: center; color: #666;'>Ask questions about any webpage content</p>", unsafe_allow_html=True)
    
    # Sidebar for configuration
    with st.sidebar:
        st.header("βš™οΈ Configuration")
        
        # Model settings
        st.subheader("Model Settings")
        temperature = st.slider("Temperature", 0.0, 1.0, 0.7, 0.1, help="Controls randomness in responses")
        max_tokens = st.slider("Max Tokens", 100, 2000, 1000, 100, help="Maximum response length")
        
        # API Key status
        st.subheader("API Status")
        groq_api_key = os.getenv("GROQ_API_KEY")
        if groq_api_key:
            st.success("βœ… GROQ API Key loaded")
        else:
            st.error("❌ GROQ API Key not found")
            st.info("Please set your GROQ_API_KEY in the .env file")
        
        # Instructions
        st.subheader("πŸ“– How to Use")
        st.markdown("""
        1. Enter a valid webpage URL
        2. Type your question about the content
        3. Click 'Get Answer' to analyze
        4. View the AI-generated response
        """)
        
        # Example URLs
        st.subheader("πŸ“ Example URLs")
        example_urls = [
            "https://www.wikipedia.org/wiki/Artificial_intelligence",
            "https://news.ycombinator.com/",
            "https://www.github.com/",
        ]
        for url in example_urls:
            if st.button(f"Use: {urlparse(url).netloc}", key=url):
                st.session_state.example_url = url
    
    # Main content area
    col1, col2 = st.columns([3, 1])
    
    with col1:
        # URL input
        url_input = st.text_input(
            "πŸ”— Enter Website URL:",
            value=st.session_state.get('example_url', ''),
            placeholder="https://example.com",
            help="Enter the complete URL including https://"
        )
        
        # Question input
        question_input = st.text_area(
            "❓ Enter Your Question:",
            placeholder="What is this webpage about? What are the main features? etc.",
            height=100,
            help="Ask specific questions about the webpage content"
        )
    
    with col2:
        st.markdown("<br><br>", unsafe_allow_html=True)
        get_answer_btn = st.button("πŸš€ Get Answer", type="primary", use_container_width=True)
        clear_btn = st.button("πŸ—‘οΈ Clear", use_container_width=True)
        
        if clear_btn:
            st.session_state.clear()
            st.rerun()
    
    # Process the request
    if get_answer_btn:
        if not url_input or not question_input:
            st.warning("⚠️ Please provide both URL and question!")
        elif not groq_api_key:
            st.error("❌ GROQ API Key is required. Please check your .env file.")
        else:
            # Initialize components
            model = initialize_model()
            if not model:
                st.error("Failed to initialize the model. Please check your API key.")
                return
            
            prompt = create_prompt_template()
            parser = StrOutputParser()
            process_url = RunnableLambda(extract_data)
            
            # Create chain
            chain = process_url | prompt | model | parser
            
            # Process request
            with st.spinner("πŸ”„ Processing your request..."):
                try:
                    start_time = time.time()
                    
                    result = chain.invoke({
                        "question": question_input,
                        "url": url_input
                    })
                    
                    end_time = time.time()
                    processing_time = round(end_time - start_time, 2)
                    
                    # Display results
                    st.success(f"βœ… Answer generated in {processing_time} seconds!")
                    
                    # Create tabs for different views
                    tab1, tab2, tab3 = st.tabs(["πŸ“ Answer", "πŸ”— URL Info", "βš™οΈ Settings"])
                    
                    with tab1:
                        st.markdown("### πŸ€– AI Response:")
                        st.markdown(f"**Question:** {question_input}")
                        st.markdown("**Answer:**")
                        st.write(result)
                        
                        # Copy button simulation
                        st.code(result, language=None)
                    
                    with tab2:
                        st.markdown("### πŸ”— URL Information:")
                        parsed_url = urlparse(url_input)
                        st.write(f"**Domain:** {parsed_url.netloc}")
                        st.write(f"**Scheme:** {parsed_url.scheme}")
                        st.write(f"**Path:** {parsed_url.path}")
                        st.write(f"**Full URL:** {url_input}")
                    
                    with tab3:
                        st.markdown("### βš™οΈ Request Settings:")
                        st.write(f"**Model:** llama3-8b-8192")
                        st.write(f"**Temperature:** {temperature}")
                        st.write(f"**Max Tokens:** {max_tokens}")
                        st.write(f"**Processing Time:** {processing_time}s")
                    
                except Exception as e:
                    st.error(f"❌ An error occurred: {str(e)}")
                    st.info("πŸ’‘ Tips:\n- Check if the URL is accessible\n- Try a different webpage\n- Ensure your internet connection is stable")
    
    # Footer
    st.markdown("---")
    st.markdown(
        "<p style='text-align: center; color: #666;'>Built with ❀️ using Streamlit, LangChain, and GROQ</p>",
        unsafe_allow_html=True
    )

# Store chat history in session state
if 'chat_history' not in st.session_state:
    st.session_state.chat_history = []

# Add chat history section
if st.session_state.chat_history:
    st.markdown("## πŸ“š Recent Queries")
    for i, (url, question, answer) in enumerate(st.session_state.chat_history[-3:]):
        with st.expander(f"Query {len(st.session_state.chat_history) - i}: {question[:50]}..."):
            st.write(f"**URL:** {url}")
            st.write(f"**Question:** {question}")
            st.write(f"**Answer:** {answer[:200]}...")

if __name__ == "__main__":
    main()