Update app.py

app.py

@@ -17,6 +17,7 @@ from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 
+# Environment Variable Checks
 GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY")
 HUGGINGFACE_ACCESS_TOKEN = os.environ.get("HUGGINGFACE_ACCESS_TOKEN")
 
@@ -28,6 +29,7 @@ if not HUGGINGFACE_ACCESS_TOKEN:
     st.error("❌ HUGGINGFACE_ACCESS_TOKEN not found.")
     st.stop()
 
+# Initialize LLM and Embeddings
 llm = ChatGoogleGenerativeAI(
     model="gemini-1.5-pro",
     google_api_key=GOOGLE_API_KEY
@@ -38,6 +40,7 @@ embeddings = HuggingFaceInferenceAPIEmbeddings(
     model_name="BAAI/bge-small-en-v1.5"
 )
 
+# Pydantic Models for Structured Output
 class KeyPoint(BaseModel):
     point: str = Field(description="A key point extracted from the document.")
 
@@ -48,8 +51,10 @@ class DocumentAnalysis(BaseModel):
     key_points: List[KeyPoint] = Field(description="List of key points from the document.")
     summary: Summary = Field(description="Summary of the document.")
 
+# Output Parser
 parser = PydanticOutputParser(pydantic_object=DocumentAnalysis)
 
+# Prompt Template
 prompt_template = """
 Analyze the following text and extract key points and a summary.
 {format_instructions}
@@ -61,15 +66,19 @@ prompt = PromptTemplate(
     partial_variables={"format_instructions": parser.get_format_instructions()}
 )
 
+# LLM Chain
 chain = LLMChain(llm=llm, prompt=prompt, output_parser=parser)
 
+# Text Analysis Function
 def analyze_text_structured(text):
     return chain.run(text=text)
 
+# PDF Text Extraction
 def extract_text_from_pdf(pdf_file):
     pdf_reader = PyPDF2.PdfReader(pdf_file)
     return "".join(page.extract_text() for page in pdf_reader.pages)
 
+# JSON to Readable Text
 def json_to_text(analysis):
     text_output = "=== Summary ===\n" + f"{analysis.summary.summary}\n\n"
     text_output += "=== Key Points ===\n"
@@ -77,6 +86,7 @@ def json_to_text(analysis):
         text_output += f"{i}. {key_point.point}\n"
     return text_output
 
+# PDF Report Generation (Updated)
 def create_pdf_report(analysis):
     pdf = FPDF()
     pdf.add_page()
@@ -84,22 +94,31 @@ def create_pdf_report(analysis):
     pdf.cell(200, 10, txt="PDF Analysis Report", ln=True, align='C')
     pdf.cell(200, 10, txt=f"Generated on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ln=True, align='C')
     pdf.multi_cell(0, 10, txt=json_to_text(analysis))
-    pdf_output = pdf.output(dest='S')
-    return pdf_output.encode('latin-1') if isinstance(pdf_output, str) else pdf_output
+    
+    # Use BytesIO to create a bytes-like object
+    pdf_bytes = io.BytesIO()
+    pdf.output(pdf_bytes, dest='S')
+    pdf_bytes.seek(0)
+    return pdf_bytes.getvalue()
 
+# Word Report Generation (Updated)
 def create_word_report(analysis):
     doc = Document()
     doc.add_heading('PDF Analysis Report', 0)
     doc.add_paragraph(f'Generated on: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}')
     doc.add_heading('Analysis', level=1)
     doc.add_paragraph(json_to_text(analysis))
+    
+    # Use BytesIO to create a bytes-like object
     docx_bytes = io.BytesIO()
     doc.save(docx_bytes)
     docx_bytes.seek(0)
     return docx_bytes.getvalue()
 
+# Streamlit Page Configuration
 st.set_page_config(page_title="Chat With PDF", page_icon="📄")
 
+# Custom CSS
 def local_css():
     st.markdown("""
     <style>
@@ -184,6 +203,7 @@ def local_css():
 
 local_css()
 
+# Session State Initialization
 if "current_file" not in st.session_state:
     st.session_state.current_file = None
 if "pdf_summary" not in st.session_state:
@@ -199,12 +219,14 @@ if "vectorstore" not in st.session_state:
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
+# Main App Layout
 st.markdown('<div class="main-header">', unsafe_allow_html=True)
 st.markdown('<div class="flag-stripe"></div>', unsafe_allow_html=True)
 st.title("📄 Chat With PDF")
 st.caption("Your AI-powered Document Analyzer")
 st.markdown('</div>', unsafe_allow_html=True)
 
+# PDF Upload and Analysis Section
 with st.container():
     st.markdown('<div class="card animate-fadeIn">', unsafe_allow_html=True)
     uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")
@@ -254,6 +276,7 @@ with st.container():
                 )
     st.markdown('</div>', unsafe_allow_html=True)
 
+# Document Chat Section
 if "vectorstore" in st.session_state and st.session_state.vectorstore is not None:
     st.subheader("Chat with the Document")
     
@@ -282,6 +305,7 @@ if "vectorstore" in st.session_state and st.session_state.vectorstore is not Non
         
         st.session_state.messages.append({"role": "assistant", "content": response.content})
 
+# Footer
 st.markdown(
     f'<div class="footer">Analysis Time: {st.session_state.analysis_time:.1f}s | Powered by Google Generative AI</div>',
     unsafe_allow_html=True