Update app.py

app.py

@@ -9,6 +9,8 @@ from llama_index import ServiceContext
 from llama_index.schema import NodeWithScore
 from llama_index.response_synthesizers import TreeSummarize
 from pydantic import BaseModel
+import PyPDF2
+import io
 
 # Load environment variables from .env file
 load_dotenv()
@@ -65,12 +67,12 @@ class ResumeScreenerPack(BaseLlamaPack):
         """Get modules."""
         return {"synthesizer": self.synthesizer}
 
-    def run(self, qualification: str) -> Any:
+    def run(self, resume_text: str) -> Any:
         """Run pack."""
         node_with_score_input = {
             "metadata": {},  # Provide any necessary metadata
-            "content": qualification,  # Use qualification as content
-            "type": "qualification",  # Define the type as per your schema
+            "content": resume_text,  # Use extracted text as content
+            "type": "resume_text",  # Define the type as per your schema
         }
 
         output = self.synthesizer.synthesize(
@@ -85,17 +87,36 @@ def main():
     # Sidebar for user input
     job_description = st.text_area("Job Description")
     criteria = st.text_area("Screening Criteria (separate each criterion by a new line)")
-    qualification = st.text_area("Qualification")
+
+    uploaded_file = st.file_uploader("Upload Resume (PDF)", type=["pdf"])
 
     if st.button("Submit"):
-        if job_description and criteria and qualification:
+        if job_description and criteria and uploaded_file:
+            resume_text = extract_text_from_pdf(uploaded_file)
+
             screener_pack = ResumeScreenerPack(job_description=job_description, criteria=criteria.split("\n"))
 
-            with st.spinner("Analyzing the qualification..."):
-                result = screener_pack.run(qualification)
+            with st.spinner("Analyzing the resume..."):
+                result = screener_pack.run(resume_text)
 
             st.subheader("Screening Results")
             st.json(result)
 
+def extract_text_from_pdf(uploaded_file):
+    if uploaded_file is not None:
+        try:
+            # Read PDF content using PyPDF2's PdfReader
+            pdf_reader = PyPDF2.PdfReader(uploaded_file)
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+            return text
+        except Exception as e:
+            st.error(f"Error extracting text from PDF: {str(e)}")
+            return ""
+    else:
+        st.error("Please upload a PDF file.")
+        return ""
+
 if __name__ == "__main__":
     main()