Update app.py

app.py

@@ -6,10 +6,10 @@ from simple_salesforce import Salesforce
 from dotenv import load_dotenv
 import base64
 
-# Load environment variables
+# Load environment variables from .env
 load_dotenv()
 
-# Get Salesforce credentials and config
+# Salesforce credentials
 SF_USERNAME = os.getenv("SF_USERNAME")
 SF_PASSWORD = os.getenv("SF_PASSWORD")
 SF_SECURITY_TOKEN = os.getenv("SF_SECURITY_TOKEN")
@@ -19,7 +19,7 @@ SF_SCORE_FIELD = os.getenv("SF_SCORE_FIELD", "Suitability_Score__c")
 SF_LINK_FIELD = os.getenv("SF_RESUME_FIELD_LINK", "Resume_File_Link__c")
 SF_RECORD_ID = os.getenv("SF_RECORD_ID")
 
-# Validate required values
+# Validate required credentials
 required = ["SF_USERNAME", "SF_PASSWORD", "SF_SECURITY_TOKEN", "SF_RECORD_ID"]
 missing = [var for var in required if not os.getenv(var)]
 if missing:
@@ -36,45 +36,45 @@ sf = Salesforce(
     domain=domain
 )
 
-# Load Hugging Face model (demo model)
+# Load Hugging Face model
 classifier = pipeline("text-classification", model="nlptown/bert-base-multilingual-uncased-sentiment")
 
-# Function to process PDF
 def process_resume(file):
     try:
         record_id = SF_RECORD_ID
 
         # Extract text from PDF
         with pdfplumber.open(file.name) as pdf:
-            text = "\n".join([page.extract_text() or "" for page in pdf.pages])
+            extracted_text = "\n".join([page.extract_text() or "" for page in pdf.pages])
 
-        if not text.strip():
-            return "❌ No text found in uploaded PDF."
+        if not extracted_text.strip():
+            return "❌ No extractable text found in the PDF."
 
-        # Run AI model
-        result = classifier(text[:1000])
+        # Call Hugging Face model
+        result = classifier(extracted_text[:1000])
         label = result[0]['label']
         score = round(float(result[0]['score']) * 100, 2)
         summary = f"Predicted Label: {label}\nSuitability Score: {score:.2f}"
 
-        # Encode PDF to base64
+        # Encode PDF in base64
         with open(file.name, "rb") as f:
             encoded_pdf = base64.b64encode(f.read()).decode("utf-8")
 
-        # Upload as ContentVersion
-        version_result = sf.ContentVersion.create({
+        # Upload file as ContentVersion
+        content_result = sf.ContentVersion.create({
             "Title": "Resume",
             "PathOnClient": file.name,
             "VersionData": encoded_pdf
         })
 
-        version_id = version_result["id"]
-
-        # Get ContentDocumentId
-        query_result = sf.query(f"SELECT ContentDocumentId FROM ContentVersion WHERE Id = '{version_id}'")
+        # Get ContentDocumentId from ContentVersion
+        version_id = content_result.get("id")
+        query_result = sf.query(
+            f"SELECT ContentDocumentId FROM ContentVersion WHERE Id = '{version_id}'"
+        )
         content_doc_id = query_result["records"][0]["ContentDocumentId"]
 
-        # Link file to record
+        # Link file to Salesforce record
         sf.ContentDocumentLink.create({
             "ContentDocumentId": content_doc_id,
             "LinkedEntityId": record_id,
@@ -82,25 +82,25 @@ def process_resume(file):
             "Visibility": "AllUsers"
         })
 
-        # Construct download link
-        download_url = f"https://{sf.sf_instance}/sfc/servlet.shepherd/document/download/{content_doc_id}"
+        # Create download link
+        download_link = f"https://{sf.sf_instance}/sfc/servlet.shepherd/document/download/{content_doc_id}"
 
-        # Update record with score + link
+        # Update record with score and link
         sf.__getattr__(SF_OBJECT_NAME).update(record_id, {
             SF_SCORE_FIELD: score,
-            SF_LINK_FIELD: download_url
+            SF_LINK_FIELD: download_link
         })
 
-        return f"{summary}\n\n✅ Score and file uploaded to Salesforce.\n📎 [Download Resume]({download_url})"
+        return f"{summary}\n\n✅ Score and resume uploaded to Salesforce.\n📎 [Download Resume]({download_link})"
 
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-# Gradio UI
+# Gradio Interface
 gr.Interface(
     fn=process_resume,
-    inputs=gr.File(label="Upload Resume PDF", file_types=[".pdf"]),
+    inputs=gr.File(label="Upload Resume (PDF)", file_types=[".pdf"]),
     outputs="text",
     title="LIC Resume AI Scorer",
-    description="Upload a resume PDF. It will be scored and stored in Salesforce."
-).launch(share=False)
+    description="Upload a resume PDF. It will be scored and stored in Salesforce automatically."
+).launch(share=False)