Update app.py

app.py

@@ -1,14 +1,24 @@
 import streamlit as st
+from dotenv import load_dotenv
 from pathlib import Path
 from typing import Any, Dict, 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.readers import PDFReader
-from llama_index.llama_pack.base import BaseLlamaPack
+from llama_index import ServiceContext
 from llama_index.schema import NodeWithScore
 from llama_index.response_synthesizers import TreeSummarize
-from pydantic import BaseModel, Field
-from llama_index.service_context import ServiceContext
+from pydantic import BaseModel
+import os
+import pdfplumber
+import io
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Get OpenAI API key from environment variables
+openai_api_key = os.getenv("OPENAI_API_KEY")
 
 QUERY_TEMPLATE = """
 You are an expert resume reviewer. 
@@ -21,27 +31,16 @@ Your job is to decide if the candidate passes the resume screen given the job de
 {criteria_str}
 """
 
-
 class CriteriaDecision(BaseModel):
     """The decision made based on a single criterion"""
-
-    decision: bool = Field(description="The decision made based on the criterion")
-    reasoning: str = Field(description="The reasoning behind the decision")
-
+    decision: bool
+    reasoning: str
 
 class ResumeScreenerDecision(BaseModel):
     """The decision made by the resume screener"""
-
-    criteria_decisions: List[CriteriaDecision] = Field(
-        description="The decisions made based on the criteria"
-    )
-    overall_reasoning: str = Field(
-        description="The reasoning behind the overall decision"
-    )
-    overall_decision: bool = Field(
-        description="The overall decision made based on the criteria"
-    )
-
+    criteria_decisions: List[CriteriaDecision]
+    overall_reasoning: str
+    overall_decision: bool
 
 def _format_criteria_str(criteria: List[str]) -> str:
     criteria_str = ""
@@ -49,16 +48,12 @@ def _format_criteria_str(criteria: List[str]) -> str:
         criteria_str += f"- {criterion}\n"
     return criteria_str
 
-
 class ResumeScreenerPack(BaseLlamaPack):
-    def __init__(
-        self,
-        job_description: str,
-        criteria: List[str],
-        llm: Optional[LLM] = None,
+    def _init_(
+        self, job_description: str, criteria: List[str], llm: Optional[LLM] = None
     ) -> None:
         self.reader = PDFReader()
-        llm = llm or OpenAI(model="gpt-4")
+        llm = llm or OpenAI(model="gpt-4", api_key=openai_api_key)
         service_context = ServiceContext.from_defaults(llm=llm)
         self.synthesizer = TreeSummarize(
             output_cls=ResumeScreenerDecision, service_context=service_context
@@ -81,25 +76,44 @@ class ResumeScreenerPack(BaseLlamaPack):
         )
         return output.response
 
-
 def main():
-    st.title("Resume Screener")
+    st.title("Resume Screener App")
 
+    # Sidebar for user input
     job_description = st.text_area("Job Description")
-    criteria = st.text_area("Screening Criteria (Separate by new lines)")
-
-    criteria_list = criteria.split('\n') if criteria else []
-
-    def run_resume_screener(resume_path):
-        screener = ResumeScreenerPack(job_description, criteria_list)
-        output = screener.run(resume_path)
-        st.json(output)  # Displaying JSON output for example
-
-    uploaded_file = st.file_uploader("Upload a resume", type=['pdf'])
-
-    if uploaded_file:
-        st.write("Resume uploaded!")
-        run_resume_screener(uploaded_file)
-
-if __name__ == "__main__":
-    main()
+    criteria = st.text_area("Screening Criteria (separate each criterion by a new line)")
+
+    uploaded_file = st.file_uploader("Upload Resume (PDF)", type=["pdf"])
+
+    if st.button("Submit"):
+        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 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 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
+        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()