Document Summarizer with Gemini

app.py

@@ -0,0 +1,88 @@
+import streamlit as st
+import os
+import google.generativeai as genai
+from PyPDF2 import PdfReader
+from fpdf import FPDF
+
+genai.configure(api_key=os.environ.get("GEMINI_API_KEY"))
+
+generation_config = {
+    "temperature": 2,
+    "top_p": 0.95,
+    "top_k": 64,
+    "max_output_tokens": 65536,
+    "response_mime_type": "text/plain",
+}
+
+model = genai.GenerativeModel(
+    model_name="gemini-2.0-flash-thinking-exp-01-21",
+    generation_config=generation_config,
+)
+
+def extract_text_from_pdf(file):
+    """Extract text from an uploaded PDF file."""
+    reader = PdfReader(file)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text() + "\n"
+    return text
+
+def stream_response(prompt):
+    """Stream response from the generative model."""
+    chat_session = model.start_chat(
+        history=[{"role": "user", "parts": [prompt]}]
+    )
+    for response_chunk in chat_session.send_message("Processing input...", stream=True):
+        if response_chunk.text:
+            yield response_chunk.text
+
+def create_pdf(content):
+    """Create a well-formatted PDF file from the given content."""
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Arial", size=12)
+    lines = content.split("\n")
+    for line in lines:
+        formatted_line = line.replace("**", "")  # Remove markdown-style bolding
+        pdf.multi_cell(0, 10, formatted_line)
+    return pdf
+
+# Streamlit UI
+st.title("Text Summarization and Insight Extraction")
+
+# Session state to persist generated text
+if "generated_text" not in st.session_state:
+    st.session_state.generated_text = ""
+
+uploaded_file = st.file_uploader("Upload a document (PDF) or paste text below:", type=["pdf"])
+input_text = st.text_area("Or paste your article here:", placeholder="Paste your article or text here...")
+
+if st.button("Generate Summary and Insights"):
+    if uploaded_file:
+        input_text = extract_text_from_pdf(uploaded_file)
+
+    if input_text.strip():
+        st.markdown("### Generating Results...")
+        response_container = st.empty()
+        st.session_state.generated_text = ""  # Clear previous text
+        for chunk in stream_response(f"Summarize the following text and extract key insights:\n{input_text}"):
+            st.session_state.generated_text += chunk
+            response_container.markdown(st.session_state.generated_text)
+    else:
+        st.warning("Please upload a file or enter text to process.")
+
+if st.session_state.generated_text:
+    st.markdown("### Summary and Insights")
+    st.text_area("Results:", st.session_state.generated_text, height=300)
+
+    # PDF Download
+    pdf = create_pdf(st.session_state.generated_text)
+    pdf_file = "summary_insights.pdf"
+    pdf.output(pdf_file)
+    with open(pdf_file, "rb") as f:
+        st.download_button(
+            label="Download PDF",
+            data=f,
+            file_name="summary_insights.pdf",
+            mime="application/pdf"
+        )

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+PyPDF2
+fpdf
+google-generativeai