Update app.py

app.py

@@ -1,78 +1,31 @@
 import streamlit as st
-import os
-import json
-import tempfile
-from typing import List
-from pydantic import BaseModel
-from langchain_groq import ChatGroq
-from langchain.document_loaders import PyPDFLoader
+import requests
 
-# Define the response schema using Pydantic
-class ExtractionResult(BaseModel):
-    answers: List[str]
+st.title("PDF Extraction App")
+st.write("Upload a PDF file to extract correct answers and options using the backend service.")
 
-# Function to initialize the LLM
-def get_llm(api_key: str):
-    return ChatGroq(
-        model="llama-3.3-70b-versatile",
-        temperature=0,
-        max_tokens=1024,
-        api_key=api_key
-    )
+# File uploader widget for PDF files
+uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])
 
-# Function to process the uploaded PDF and extract text
-def process_pdf(file) -> str:
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
-        tmp_file.write(file.read())
-        tmp_path = tmp_file.name
-
-    loader = PyPDFLoader(tmp_path)
-    pages = loader.load_and_split()
-    os.remove(tmp_path)
-    all_page_content = "\n".join(page.page_content for page in pages)
-    return all_page_content
-
-# Build the prompt using the JSON schema from ExtractionResult
-def build_prompt(all_page_content: str) -> str:
-    schema_dict = ExtractionResult.model_json_schema()
-    schema = json.dumps(schema_dict, indent=2)
-    system_message = (
-        "You are a document analysis tool that extracts the options and correct answers from the provided document content. "
-        "The output must be a JSON object that strictly follows the schema: " + schema
-    )
-    user_message = (
-        "Please extract the correct answers and options (A, B, C, D, E) from the following document content:\n\n"
-        + all_page_content
-    )
-    return system_message + "\n\n" + user_message
-
-def main():
-    st.title("PDF Answer Extraction App")
-    st.write("Upload a PDF document to extract the correct answers and options.")
-
-    # Retrieve API key from Streamlit secrets or environment variables
-    api_key = st.secrets.get("GROQ_API_KEY") or os.getenv("GROQ_API_KEY")
-    if not api_key:
-        st.error("GROQ API key not found! Please set it in your environment or Streamlit secrets.")
-        st.stop()
-
-    # Initialize the language model
-    llm = get_llm(api_key)
-    
-    uploaded_file = st.file_uploader("Choose a PDF file", type=["pdf"])
-    
-    if uploaded_file is not None:
-        with st.spinner("Processing the PDF..."):
+if uploaded_file is not None:
+    if st.button("Extract Answers"):
+        with st.spinner("Processing the file, please wait..."):
             try:
-                all_page_content = process_pdf(uploaded_file)
-                prompt = build_prompt(all_page_content)
-                response = llm.invoke(prompt, response_format={"type": "json_object"})
-                result = ExtractionResult.model_validate_json(response.content)
-                
-                st.success("Extraction complete!")
-                st.json(result.model_dump())
+                # Prepare the file payload
+                files = {
+                    "file": (uploaded_file.name, uploaded_file.read(), "application/pdf")
+                }
+                # Make a POST request to the FastAPI endpoint
+                response = requests.post(
+                    "https://hammad712-grading.hf.space/extract-answers/",
+                    files=files
+                )
+                # Check for successful response
+                if response.status_code == 200:
+                    result = response.json()
+                    st.success("Extraction successful!")
+                    st.json(result)
+                else:
+                    st.error(f"Error: {response.text}")
             except Exception as e:
                 st.error(f"An error occurred: {e}")
-
-if __name__ == "__main__":
-    main()