Update app.py

app.py

@@ -1,17 +1,15 @@
 import streamlit as st
 from dotenv import load_dotenv
 import os
-from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any, List, Optional
 from llama_index.llama_pack.base import BaseLlamaPack
-from llama_index.readers import PDFReader
 from llama_index.llms.base import LLM
 from llama_index.llms import OpenAI
 from llama_index import ServiceContext
 from llama_index.schema import NodeWithScore
 from llama_index.response_synthesizers import TreeSummarize
 from pydantic import BaseModel
-import pdfplumber
+import PyPDF2
 import io
 
 # Load environment variables from .env file
@@ -55,7 +53,6 @@ class ResumeScreenerPack(BaseLlamaPack):
         criteria: List[str] = [],
         llm: Optional[LLM] = None
     ) -> None:
-        self.reader = PDFReader()
         llm = llm or OpenAI(model="gpt-4", api_key=openai_api_key)
         service_context = ServiceContext.from_defaults(llm=llm)
         criteria_str = _format_criteria_str(criteria)
@@ -66,16 +63,15 @@ class ResumeScreenerPack(BaseLlamaPack):
             output_cls=ResumeScreenerDecision, service_context=service_context
         )
 
-    def get_modules(self) -> Dict[str, Any]:
+    def get_modules(self) -> dict:
         """Get modules."""
-        return {"reader": self.reader, "synthesizer": self.synthesizer}
+        return {"synthesizer": self.synthesizer}
 
-    def run(self, resume_path: str, *args: Any, **kwargs: Any) -> Any:
+    def run(self, resume_text: str) -> Any:
         """Run pack."""
-        docs = self.reader.load_data(Path(resume_path))
         output = self.synthesizer.synthesize(
             query=self.query,
-            nodes=[NodeWithScore(node=doc, score=1.0) for doc in docs],
+            nodes=[NodeWithScore(node=resume_text, score=1.0)],
         )
         return output.response
 
@@ -103,14 +99,13 @@ def main():
 def extract_text_from_pdf(uploaded_file):
     if uploaded_file is not None:
         try:
-            # Read PDF content from BytesIO
-            uploaded_content = io.BytesIO(uploaded_file.read())
-
-            with pdfplumber.open(uploaded_content) as pdf:
-                text = ""
-                for page in pdf.pages:
-                    text += page.extract_text()
-                return text
+            # Read PDF content using PyPDF2
+            pdf_reader = PyPDF2.PdfFileReader(uploaded_file)
+            text = ""
+            for page_num in range(pdf_reader.numPages):
+                page = pdf_reader.getPage(page_num)
+                text += page.extractText()
+            return text
         except Exception as e:
             st.error(f"Error extracting text from PDF: {str(e)}")
             return ""