Hugging Face's logo

Spaces:
GiantAnalytics
/
Chat_with_Website
Build error

App Files Community
Chat_with_Website
File size: 4,680 Bytes 
bef21a8
 
 
 
 
 
 
 
 
 
 
 
7c31854
bef21a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c31854
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bef21a8
 
 
7c31854
bef21a8
 
 
 
 
 
 
 
 
 
 
7c31854
bef21a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import streamlit as st
import tempfile
import os
import shutil
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain_community.document_loaders import WebBaseLoader
from langchain.chains.question_answering import load_qa_chain
from langchain_openai import ChatOpenAI
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.pdfbase.pdfmetrics import stringWidth

# Hardcoded OpenAI API Key
os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY')

# Streamlit UI
st.title("🔍 AI Benefits Analysis for Any Company")

# User input: Only Website URL (with placeholder)
website_url = st.text_input("Enter Website URL", placeholder="e.g., https://www.companywebsite.com")

# Fixed question for AI analysis
fixed_question = (
    "Analyze how Artificial Intelligence (AI) can benefit this company based on its industry, "
    "key operations, and challenges. Provide insights on AI-driven improvements in customer experience, "
    "automation, sales, risk management, decision-making, and innovation. Include an AI implementation roadmap, "
    "challenges, solutions, and future opportunities with real-world examples."
)

# Temporary directory to store FAISS index
temp_dir = tempfile.gettempdir()
faiss_db_path = os.path.join(temp_dir, "faiss_index_dir")

# Function to fetch and process website data
def build_embeddings(url):
    st.info("Fetching and processing website data...")

    # Load website data
    loader = WebBaseLoader(url)
    raw_text = loader.load()

    # Chunking the fetched text
    text_splitter = CharacterTextSplitter(separator='\n', chunk_size=500, chunk_overlap=50)
    docs = text_splitter.split_documents(raw_text)

    # Creating embeddings
    embeddings = OpenAIEmbeddings()
    docsearch = FAISS.from_documents(docs, embeddings)

    # Save FAISS index
    if os.path.exists(faiss_db_path):
        shutil.rmtree(faiss_db_path)
    os.makedirs(faiss_db_path)
    docsearch.save_local(faiss_db_path)

    return docsearch

# Function to save text to a PDF file
def save_text_to_pdf(text, file_path):
    c = canvas.Canvas(file_path, pagesize=letter)
    width, height = letter
    
    # Define margins
    margin_x = 50
    margin_y = 50
    max_width = width - 2 * margin_x  # Usable text width
    
    # Title
    c.setFont("Helvetica-Bold", 16)
    c.drawString(margin_x, height - margin_y, "AI Benefits Analysis Report")
    
    # Move cursor down
    y_position = height - margin_y - 30
    c.setFont("Helvetica", 12)
    
    # Function to wrap text within max_width
    def wrap_text(text, font_name, font_size, max_width):
        words = text.split()
        lines = []
        current_line = ""
        
        for word in words:
            test_line = current_line + " " + word if current_line else word
            if stringWidth(test_line, font_name, font_size) <= max_width:
                current_line = test_line
            else:
                lines.append(current_line)
                current_line = word
        
        if current_line:
            lines.append(current_line)
        
        return lines
    
    # Process text
    lines = text.split("\n")
    wrapped_lines = []
    for line in lines:
        wrapped_lines.extend(wrap_text(line, "Helvetica", 12, max_width))
    
    # Write text line by line with proper spacing
    for line in wrapped_lines:
        if y_position < margin_y:  # If at bottom of page, create a new page
            c.showPage()
            c.setFont("Helvetica", 12)
            y_position = height - margin_y
        c.drawString(margin_x, y_position, line)
        y_position -= 16  # Line spacing
    
    c.save()
    
# Run everything in one click
if st.button("Get AI Insights") and website_url:
    docsearch = build_embeddings(website_url)

    # AI Benefits Analysis
    st.subheader("💬 AI Benefits Analysis")

    chain = load_qa_chain(ChatOpenAI(model="gpt-4o"), chain_type="stuff")
    docs = docsearch.similarity_search(fixed_question)
    response = chain.run(input_documents=docs, question=fixed_question)

    st.write("**AI Insights:**", response)

    # Save the AI insights as a PDF
    pdf_file = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
    save_text_to_pdf(response, pdf_file.name)

    # Provide download link for the generated PDF file
    with open(pdf_file.name, "rb") as f:
        st.download_button(
            label="Download AI Insights as PDF File",
            data=f,
            file_name="ai_benefits_analysis_report.pdf",
            mime="application/pdf"
        )