Create app.py

app.py

@@ -0,0 +1,141 @@
+import os
+import openai
+import streamlit as st
+import base64
+
+# Set up OpenAI API key
+openai.api_key = os.getenv("OPENAI_API_KEY")  # Replace with your API key if needed
+
+# Helper function to encode a file to base64
+def encode_file_to_base64(uploaded_file):
+    """Encode a file to base64."""
+    return base64.b64encode(uploaded_file.read()).decode("utf-8")
+
+# Function to call GPT for parsing
+def call_gpt_for_parsing(option, encoded_pdf, instructions):
+    """Send option, encoded PDF, and parsing instructions to GPT for processing."""
+    prompt = f"""
+    Welcome to PMP Auto-PO Generator. Please parse the provided PDF file based on the selected option and instructions.
+
+    Selected Option: {option}
+
+    Instructions:
+    {instructions}
+
+    PDF File (Base64 Encoded):
+    {encoded_pdf}
+
+    Return the parsed data in JSON format.
+    """
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",  # Use GPT-4 for higher accuracy if needed
+        messages=[{"role": "user", "content": prompt}],
+        max_tokens=3000
+    )
+    return response['choices'][0]['message']['content']
+
+# Instruction sets for each option
+instruction_sets = {
+    "Toshiba": """
+    Extract columns: Pos., Item Code, Unit, Delivery Date, Quantity, Basic Price, Discount, Cur., Amount, Sub Total. 
+    Follow specific instructions for Item Code extraction:
+    - Identify Item Code blocks starting with a numeric code (e.g., 155569003011).
+    - Include all subsequent lines (e.g., descriptions, additional codes) until a new numeric block or section begins.
+    - Maintain the exact line order and formatting, preserving sub-lines.
+    """,
+    "BHEL": """
+    Extract columns: SI No, Material Description, Unit, Quantity, Dely Qty, Dely Date, Unit Rate, Value. 
+    Follow instructions for Material Description block extraction:
+    - Include primary description (e.g., BPS 017507).
+    - Add Material Number, HSN Code, GST percentage.
+    """,
+    "Federal Electric": """
+    Extract columns: S. No, Material No, Material Description, Qty, Unit, Price, Delivery Date, Total Value, Vat%, Amount Incl.VAT. 
+    Ensure all relevant data fields are included and validated.
+    """,
+    "AL NISF": """
+    Extract columns: Item, Description, Qty, Unit, Unit Price, Total Price. 
+    Follow detailed instructions for structuring descriptions:
+    - Add a bold header 'DESCRIPTION'.
+    - Include Computer Code Number, Product Name, Designation Number, Dimensions, Serial Number, and Manufacturing Year.
+    """,
+    "Others": """
+    Perform dynamic field mapping to extract all relevant data fields.
+    - Ensure the fields are captured accurately.
+    """
+}
+
+# App State for Multi-Step Interaction
+if "step" not in st.session_state:
+    st.session_state["step"] = 1  # Initialize the step counter
+    st.session_state["selected_option"] = None
+    st.session_state["encoded_pdf"] = None
+    st.session_state["parsed_output"] = None
+
+# Streamlit app
+def main():
+    st.title("PMP Auto-PO Generator")
+    
+    # Step 1: Welcome and Option Selection
+    if st.session_state["step"] == 1:
+        st.write("Welcome to PMP Auto-PO Generator!")
+        st.write("Please choose from the following options:")
+        options = ["Toshiba", "BHEL", "Federal Electric", "AL NISF", "Others"]
+        selected_option = st.selectbox("Select an option:", options)
+
+        if st.button("Next"):
+            if not selected_option:
+                st.warning("Please select an option to proceed.")
+            else:
+                st.session_state["selected_option"] = selected_option
+                st.session_state["step"] = 2
+
+    # Step 2: File Upload
+    elif st.session_state["step"] == 2:
+        st.write(f"Thanks for selecting {st.session_state['selected_option']}. Please upload your PO file.")
+        uploaded_file = st.file_uploader("Upload your PO file (PDF format only):", type=["pdf"])
+
+        if uploaded_file:
+            if uploaded_file.type != "application/pdf":
+                st.error("Invalid file format. Please upload a PDF file.")
+            else:
+                st.session_state["encoded_pdf"] = encode_file_to_base64(uploaded_file)
+                st.session_state["step"] = 3
+
+    # Step 3: Call GPT for Processing
+    elif st.session_state["step"] == 3:
+        st.write("Processing your file with GPT...")
+        instructions = instruction_sets[st.session_state["selected_option"]]
+
+        try:
+            parsed_output = call_gpt_for_parsing(
+                st.session_state["selected_option"],
+                st.session_state["encoded_pdf"],
+                instructions
+            )
+            st.session_state["parsed_output"] = parsed_output
+            st.session_state["step"] = 4
+        except Exception as e:
+            st.error(f"Error during GPT processing: {e}")
+
+    # Step 4: Review and Download
+    elif st.session_state["step"] == 4:
+        st.write("Parsing successful! Below is the extracted data:")
+        st.json(st.session_state["parsed_output"])
+
+        if st.button("Download as JSON"):
+            st.download_button(
+                label="Download JSON",
+                data=st.session_state["parsed_output"],
+                file_name="parsed_output.json",
+                mime="application/json"
+            )
+        
+        if st.button("Start Over"):
+            st.session_state["step"] = 1
+            st.session_state["selected_option"] = None
+            st.session_state["encoded_pdf"] = None
+            st.session_state["parsed_output"] = None
+
+if __name__ == "__main__":
+    main()