Spaces:
Running
Running
| import os | |
| import google.generativeai as genai | |
| import streamlit as st | |
| from PyPDF2 import PdfReader | |
| from collections import Counter | |
| import re | |
| # Get the API key from environment variable | |
| api_key = os.getenv("GEMINI_API_KEY") | |
| if api_key is None: | |
| st.error("API key not found. Please set the GEMINI_API_KEY environment variable.") | |
| else: | |
| # Gemini Model Initialization | |
| MODEL_ID = "gemini-2.0-flash-exp" | |
| genai.configure(api_key=api_key) | |
| model = genai.GenerativeModel(MODEL_ID) | |
| # Correct initialization of the 'chat' object | |
| chat = model.start_chat() | |
| st.title("📚 AI-Powered Document Analyzer") | |
| with st.expander("📖 **What is this app about?**"): | |
| st.write(""" | |
| The **AI-Powered Document Analyzer** app is an AI-powered tool designed to help users extract valuable insights from any PDF document. | |
| By leveraging **Gemini 2.0's Flash Experimental Model**, this intelligent system allows users to interactively engage with their documents, | |
| making research and information retrieval more efficient. | |
| """) | |
| # Upload Section | |
| st.header("Upload Document") | |
| uploaded_file = st.file_uploader("Upload a PDF file to be analyzed", type=["pdf"]) | |
| def extract_text_from_pdf(file): | |
| pdf_reader = PdfReader(file) | |
| return "\n".join([page.extract_text() for page in pdf_reader.pages if page.extract_text()]) | |
| def extract_keywords(text, num_keywords=10): | |
| words = re.findall(r'\b\w{4,}\b', text.lower()) # Extract words with 4+ letters | |
| common_words = set("the and for with from this that have will are was were been has".split()) # Stop words | |
| filtered_words = [word for word in words if word not in common_words] | |
| most_common = Counter(filtered_words).most_common(num_keywords) | |
| return [word for word, _ in most_common] | |
| def generate_suggested_questions(keywords): | |
| """Generate sample questions based on extracted keywords.""" | |
| questions = [] | |
| for keyword in keywords: | |
| questions.append(f"What is the significance of {keyword} in the document?") | |
| questions.append(f"Can you summarize the document's section on {keyword}?") | |
| return questions | |
| if uploaded_file: | |
| document_text = extract_text_from_pdf(uploaded_file) | |
| st.session_state["document_text"] = document_text | |
| st.success("Document uploaded successfully!") | |
| # Display Keyword Insights | |
| st.header("🔑 Key Topic Insights") | |
| keywords = extract_keywords(document_text) | |
| st.write(", ".join(keywords)) | |
| # Generate Suggested Questions | |
| st.session_state["suggested_questions"] = generate_suggested_questions(keywords) | |
| else: | |
| st.session_state.pop("document_text", None) # Remove document text if no file is uploaded | |
| st.session_state.pop("suggested_questions", None) | |
| # Question-Answering Section | |
| if "document_text" in st.session_state: | |
| st.header("Ask AI About Your Document") | |
| # Handle the selected question from buttons | |
| if "selected_question" not in st.session_state: | |
| st.session_state["selected_question"] = "" | |
| def ask_ai(question): | |
| """Process user question with the uploaded document.""" | |
| try: | |
| prompt = f"Analyze the following document and answer: {question}\n\nDocument Content:\n{st.session_state['document_text'][:5000]}" | |
| response = chat.send_message(prompt) # Sending the message to 'chat' | |
| return response.text | |
| except Exception as e: | |
| return f"Error: {e}" | |
| # Text input for entering a question | |
| selected_question = st.text_input( | |
| "Enter your question about the document contents:", | |
| value=st.session_state["selected_question"] | |
| ) | |
| # Suggested Questions Section (between input and button) | |
| if "suggested_questions" in st.session_state: | |
| st.write("💡 **Suggested Questions:**") | |
| # Limit to 5 questions | |
| limited_suggested_questions = st.session_state["suggested_questions"][:5] | |
| num_columns = len(limited_suggested_questions) | |
| # Display in a row with smaller text | |
| cols = st.columns(num_columns) | |
| for i, question in enumerate(limited_suggested_questions): | |
| with cols[i]: | |
| if st.button(f"🔹 {question}", key=f"btn_{i}"): | |
| st.session_state["selected_question"] = question | |
| # Generate Answer Button | |
| if st.button("Generate Answer") and selected_question: | |
| with st.spinner("AI is reading the document..."): | |
| response = ask_ai(selected_question) | |
| st.markdown(f"**Response:** \n {response}") | |
| else: | |
| st.warning("Please upload a document to proceed.") | |