Refactor app.py to streamline CV parsing and email generation. Removed the 'other' section from CV parsing logic, simplifying the handling of miscellaneous content. Updated the email prompt to clarify instructions and enhance professionalism. Increased max_new_tokens for model generation to improve response quality. Improved UI feedback for generated emails in the Streamlit interface.

app.py

@@ -16,7 +16,6 @@ def parse_cv_sections(text: str) -> Dict[str, str]:
         'experience': '',
         'skills': '',
         'projects': '',
-        'other': '',  # Added other section for miscellaneous content
     }
     
     # Common section headers in CVs
@@ -38,20 +37,13 @@ def parse_cv_sections(text: str) -> Dict[str, str]:
             continue
             
         # Check if line is a section header
-        section_found = False
         for section, pattern in section_patterns.items():
             if re.search(pattern, line, re.IGNORECASE):
                 current_section = section
-                section_found = True
                 break
-        
+                
         if current_section and line:
-            # If line doesn't match any known section and we haven't found a section yet,
-            # put it in 'other'
-            if not section_found and current_section is None:
-                sections['other'] += line + '\n'
-            else:
-                sections[current_section] += line + '\n'
+            sections[current_section] += line + '\n'
     
     return sections
 
@@ -100,12 +92,10 @@ client = InferenceClient(token=access_token)
 
 def create_email_prompt(job_description: str, cv_sections: Dict[str, str]) -> str:
     """Create a detailed prompt for email generation."""
-    return f"""Based on the following information, generate only a professional job application email.
-
-Job Description:
+    return f"""Job Description:
 {job_description}
 
-CV Details:
+Your CV Details:
 Experience:
 {cv_sections['experience']}
 
@@ -115,21 +105,17 @@ Skills:
 Education:
 {cv_sections['education']}
 
-Additional Information:
-{cv_sections['other']}
-
-Contact Information:
-{cv_sections['contact']}
-
-Guidelines:
+Instructions: Write a professional job application email following these guidelines:
 1. Start with a proper greeting
 2. First paragraph: Express interest in the position and mention how you found it
-3. Second paragraph: Highlight 2-3 most relevant experiences that match the job requirements
+3. Second paragraph: Highlight 2-3 most relevant experiences from your CV that match the job requirements
 4. Third paragraph: Mention specific skills that align with the role
 5. Closing paragraph: Express enthusiasm for an interview and provide contact information
 6. End with a professional closing
 
-Generate only the email, without any additional text or explanations."""
+Keep the tone professional, confident, and enthusiastic. Be concise but impactful.
+
+Email:"""
 
 def conversation_predict(input_text: str, cv_sections: Dict[str, str]):
     """Generate a response using the model with improved prompting."""
@@ -141,7 +127,7 @@ def conversation_predict(input_text: str, cv_sections: Dict[str, str]):
     # Generate a response with the model
     outputs = model.generate(
         input_ids,
-        max_new_tokens=512,
+        max_new_tokens=2048,
         temperature=0.7,
         top_p=0.95,
         do_sample=True
@@ -218,9 +204,8 @@ with tab1:
     if st.button("Generate Email"):
         if message and cv_file and isinstance(cv_sections, dict):
             response = conversation_predict(message, cv_sections)
-            # Remove any potential prompt text from the response
-            email_text = response.split("Email:")[-1].strip()
-            st.text_area("Generated Email", email_text, height=400)
+            st.markdown("### Generated Email:")
+            st.markdown(response)
         else:
             st.warning("Please upload a CV and enter a job description.")