Update app.py

app.py

@@ -834,7 +834,7 @@ def process_pdf(file):
             esco_occ_future = executor.submit(classify_esco_by_hierarchical_level, responsibilities)
             qualification_future = executor.submit(extract_qualification, responsibilities)
             skills_future = executor.submit(extract_skills, responsibilities)
-
+            
             job_family = job_family_future.result()
             occ_group = occ_group_future.result()
             esco_occ = esco_occ_future.result()
@@ -843,16 +843,10 @@ def process_pdf(file):
 
         log_debug(f"Identified {job_family}")
 
-        skill_map = map_proficiency_and_assessment(skills, responsibilities)
-
-        has_esco = esco_occ.get("Level_5_ESCO_code") is not None
-        skill_esco_extract = []
-        skill_esco_map = []
-        if has_esco:
-            Level_5_code = esco_occ["Level_5_ESCO_code"]
-            skill_esco_extract = review_skills(Level_5_code)
-            skill_esco_map = map_proficiency_and_assessment(skill_esco_extract, responsibilities)
+        interview = build_interview(responsibilities, skills)
 
+        ## Map skills from responsibilities
+        skill_map = map_proficiency_and_assessment(skills, responsibilities)
         time.sleep(6)
         assessment_lookup = {item['skill_name']: item for item in skill_map}
         joined_skills = [
@@ -870,6 +864,43 @@ def process_pdf(file):
             for skill in skills
         ]
 
+        
+        ## Generate ESCO skills if we have level 5 mapping.... 
+        has_esco = esco_occ.get("Level_5_ESCO_code") is not None
+        skill_esco_extract = []
+        skill_esco_map = []
+        if has_esco:
+            Level_5_code = esco_occ["Level_5_ESCO_code"]
+            skill_esco_extract = review_skills(Level_5_code)
+            skill_esco_map = map_proficiency_and_assessment(skill_esco_extract, responsibilities)
+        else:
+            log_debug(f"No Level 5 ESCO code found for {os.path.basename(file.name)}, skipping ESCO skills mapping")
+
+        joined_skills_esco = []
+        if has_esco and skill_esco_extract:
+            assessment_esco_lookup = {item['skill_name']: item for item in skill_esco_map}
+            joined_skills_esco = [
+                {
+                    "skill_name": skill["skill_name"],
+                    "skill_description": skill["skill_description"],
+                    "skill_code": skill["skill_code"],
+                    **assessment_esco_lookup.get(skill["skill_name"], {})
+                }
+                for skill in skill_esco_extract
+            ]
+            
+        if has_esco:
+            esco_levels = {f"Level_{i}_ESCO_{field}": esco_occ.get(f"Level_{i}_ESCO_{field}")
+                           for i in range(1, 6) for field in ["code", "name", "desc"]}
+            esco_skills = {
+                "skills": joined_skills_esco
+            }
+        else:
+            esco_levels = {f"Level_{i}_ESCO_{field}": None
+                           for i in range(1, 6) for field in ["code", "name", "desc"]}
+            esco_skills = None
+
+        
         # Prepare all data for JSON output
         result_data = {
             "file_name": os.path.basename(file.name),
@@ -881,18 +912,8 @@ def process_pdf(file):
             "interview_questions": build_interview(responsibilities, skills),
             "skills": joined_skills,
             "esco_levels": {f"Level_{i}_ESCO_{field}": esco_occ.get(f"Level_{i}_ESCO_{field}")
-                          for i in range(1, 6) for field in ["code", "name", "desc"]},
-            "esco_skills": {
-                "skills": [
-                    {
-                        "skill_name": skill["skill_name"],
-                        "skill_description": skill["skill_description"],
-                        "skill_code": skill["skill_code"],
-                        **assessment_esco_lookup.get(skill["skill_name"], {})
-                    }
-                    for skill in (skill_esco_extract if has_esco else [])
-                ]
-            },
+                          for i in range(1, 5) for field in ["code", "name", "desc"]},
+            "esco_skills": esco_skills,
             "processing_time": time.strftime("%Y-%m-%d %H:%M:%S")
         }
 
@@ -902,7 +923,7 @@ def process_pdf(file):
             json_path = f.name
             log_debug(f"Results saved to temporary JSON file: {json_path}")
 
-        # Format outputs for display
+        # Format outputs for display through html cards
         formatted_skills = format_skill_cards(joined_skills)
         formatted_ccog = format_ccog_card(result_data['ccoq_levels'])
         formatted_esco_levels = format_esco_card(result_data['esco_levels'])
@@ -914,11 +935,11 @@ def process_pdf(file):
             job_family,
             "\n".join(qualification),
             formatted_ccog,
-            "\n".join(result_data['interview_questions']),
+            "\n".join(interview),
             formatted_skills,
             formatted_esco_levels,
             formatted_esco_skills,
-            "Processing completed successfully." if DEBUG else None,
+            debug_message if DEBUG else None,
             json_path  # Return path to JSON file
         )
 
@@ -939,6 +960,8 @@ def process_pdf(file):
             error_message,
             None  # No JSON path on error
         )
+
+        
 # ================= Build Word Report =================
 from docx import Document
 import os
@@ -947,34 +970,37 @@ import time
 import tempfile
 from typing import Dict, List, Union
 
-def generate_word_document(
-    file_name: str,
-    responsibilities: str,
-    job_family: str,
-    qualification: str,
-    ccoq_levels: Dict,
-    interview: str,
-    skills: List[Dict],
-    esco_levels: Dict,
-    esco_skills: Dict
-) -> str:
-    """
-    Generate a comprehensive Word document from analysis results with multiple fallback mechanisms.
+def create_error_doc(message: str) -> str:
+    """Create a simple Word document with an error message."""
+    doc = Document()
+    doc.add_heading('Error Generating Report', level=1)
+    doc.add_paragraph(message)
+    temp_file = tempfile.NamedTemporaryFile(suffix=".docx", delete=False)
+    doc.save(temp_file.name)
+    return temp_file.name
+    
 
-    Args:
-        file_name: Original PDF filename
-        responsibilities: Extracted responsibilities text
-        job_family: Identified job family
-        qualification: Required qualifications
-        ccoq_levels: CCOG classification levels
-        interview: Generated interview questions
-        skills: List of required skills
-        esco_levels: ESCO classification levels
-        esco_skills: ESCO mapped skills
 
+def generate_word_document(json_path: Optional[str]) -> str:
+    """
+    Generate a Word document from the analysis results JSON file.
+    
+    Args:
+        json_path: Path to the JSON file containing analysis results
+        
     Returns:
         Path to the generated Word document
     """
+    if not json_path or not os.path.exists(json_path):
+        return create_error_doc("No valid analysis data was provided.")
+
+    try:
+        with open(json_path, 'r') as f:
+            data = json.load(f)
+    except Exception as e:
+        return create_error_doc(f"Failed to load JSON file: {str(e)}")
+
+            
     # Initialize document with metadata
     doc = Document()
     doc.core_properties.author = "IOM Talent Management System"
@@ -983,10 +1009,10 @@ def generate_word_document(
     # Default values for all fields
     default_values = {
         "file": "Unknown file",
-        "responsibilities": "No responsibilities extracted",
-        "classified_job_family": "No job family identified",
-        "qualification": ["No qualification information available"],
-        "interview": ["No interview questions generated"],
+        "responsibilities": "No responsibilities extracted.",
+        "classified_job_family": "No job family identified.",
+        "qualification": ["No qualification information available."],
+        "interview": ["No interview questions generated."],
         "skills": {"skills": [{"skill_name": "No skills identified", "description": "", "code": ""}]},
         "skills_esco": {"skills": [{"skill_name": "No ESCO skills identified", "description": "", "code": ""}]}
     }
@@ -994,13 +1020,15 @@ def generate_word_document(
     # Safely build the result dictionary with fallbacks
     try:
         result = {
-            "file": file_name if file_name and isinstance(file_name, str) else default_values["file"],
-            "responsibilities": responsibilities if responsibilities else default_values["responsibilities"],
-            "classified_job_family": job_family if job_family else default_values["classified_job_family"],
-            "qualification": qualification.split('\n') if qualification else default_values["qualification"],
-            "interview": interview.split('\n') if interview else default_values["interview"],
-            "skills": {"skills": skills} if skills and isinstance(skills, list) else default_values["skills"],
-            "skills_esco": esco_skills if esco_skills and isinstance(esco_skills, dict) else default_values["skills_esco"]
+            "file": data.get("file", default_values["file"]),
+            "responsibilities": data.get("responsibilities", default_values["responsibilities"]),
+            "classified_job_family": data.get("job_family", default_values["classified_job_family"]),
+            "qualification": data.get("qualification", default_values["qualification"]),
+            "interview": data.get("interview", default_values["interview"]),
+            "skills": data.get("skills", default_values["skills"]),
+            "skills_esco": data.get("skills_esco", default_values["skills_esco"]),
+            "ccog_levels": data.get("ccog_levels", {}),
+            "esco_levels": data.get("esco_levels", {})
         }
 
         # Add level information with validation
@@ -1014,115 +1042,49 @@ def generate_word_document(
         log_debug(f"Error building result dictionary: {str(e)}")
         result = default_values
 
-    # ================= DOCUMENT CONTENT GENERATION =================
+    #  DOCUMENT CONTENT GENERATION  
     try:
         # Document header
         doc.add_heading('Job Description Analysis Report', level=0)
         doc.add_paragraph(f"Generated on {time.strftime('%Y-%m-%d %H:%M:%S')}")
         doc.add_paragraph("International Organization for Migration", style="Intense Quote")
 
-        # Metadata table
-        table = doc.add_table(rows=1, cols=2)
-        table.style = 'Light Shading Accent 1'
-        hdr_cells = table.rows[0].cells
-        hdr_cells[0].text = 'Field'
-        hdr_cells[1].text = 'Value'
-
-        def _add_table_row(table, field, value):
-            row = table.add_row().cells
-            row[0].text = field
-            row[1].text = str(value or "Not available")
-
-        _add_table_row(table, "File Name", result["file"])
-        _add_table_row(table, "Job Family", result["classified_job_family"])
-
-        # Section generator with error handling
-        def _add_section(heading, content, level=2):
-            doc.add_heading(heading, level=level)
-            if not content:
-                doc.add_paragraph("No information available", style='Subtle Emphasis')
-                return
-
-            if isinstance(content, (list, tuple)):
-                for item in content:
-                    if item and str(item).strip():
-                        doc.add_paragraph(str(item).strip(), style='List Bullet' if level > 2 else None)
-            elif isinstance(content, dict):
-                for k, v in content.items():
-                    if v is not None:
-                        doc.add_paragraph(f"{k}: {v}")
-            elif isinstance(content, str):
-                doc.add_paragraph(content)
-
-        # Core sections
-        _add_section("1. Responsibilities", result["responsibilities"])
-        _add_section("2. Qualifications", result["qualification"])
-
-        # Skills sections with robust handling
-        def _add_skills_section(heading, skills_data):
-            doc.add_heading(heading, level=2)
-            if not skills_data or not skills_data.get("skills"):
-                doc.add_paragraph("No skills information available", style='Subtle Emphasis')
-                return
-
-            try:
-                skills_table = doc.add_table(rows=1, cols=4)
-                skills_table.style = 'Medium List 2 Accent 1'
-                hdr = skills_table.rows[0].cells
-                hdr[0].text = 'Skill'
-                hdr[1].text = 'Description'
-                hdr[2].text = 'Proficiency'
-                hdr[3].text = 'Assessment'
-
-                for skill in skills_data["skills"]:
-                    if not isinstance(skill, dict):
-                        continue
-
-                    row = skills_table.add_row().cells
-                    row[0].text = str(skill.get("skill_name", "Unnamed skill"))
-                    row[1].text = str(skill.get("skill_description", ""))[:100] + ("..." if len(str(skill.get("skill_description", ""))) > 100 else "")
-                    row[2].text = str(skill.get("proficiency_level", "Not specified"))
-                    row[3].text = str(skill.get("assessment_method", "Not specified"))
-            except Exception as e:
-                doc.add_paragraph(f"Could not display skills table: {str(e)}", style='Subtle Emphasis')
-
-        _add_skills_section("3. Required Skills", result["skills"])
-        _add_skills_section("4. ESCO Mapped Skills", result["skills_esco"])
-
-        # Classification sections
-        def _add_classification_section(heading, prefix, levels=4):
-            doc.add_heading(heading, level=2)
-            found = False
-            for i in range(1, levels+1):
-                code = result.get(f"{prefix}_{i}_code")
-                name = result.get(f"{prefix}_{i}_name")
-                desc = result.get(f"{prefix}_{i}_desc")
-
-                if any([code, name, desc]):
-                    found = True
-                    doc.add_heading(f"Level {i}", level=3)
-                    if code:
-                        doc.add_paragraph(f"Code: {code}")
-                    if name:
-                        doc.add_paragraph(f"Name: {name}")
-                    if desc:
-                        doc.add_paragraph(f"Description: {desc}")
-
-            if not found:
-                doc.add_paragraph("No classification information available", style='Subtle Emphasis')
-
-        _add_classification_section("5. CCOG Classification", "Level_CCOG")
-        _add_classification_section("6. ESCO Classification", "Level_ESCO", levels=5)
-
-        # Interview questions
-        doc.add_heading("7. Suggested Interview Questions", level=2)
-        if result["interview"] and any(q.strip() for q in result["interview"]):
-            for i, question in enumerate(result["interview"], 1):
-                if question.strip():
-                    doc.add_paragraph(f"{i}. {question}", style='List Number')
-        else:
-            doc.add_paragraph("No interview questions generated", style='Subtle Emphasis')
 
+
+        doc.add_heading('Position Description Analysis Report', level=1)
+        doc.add_paragraph(f"File: {result['file']}")
+        doc.add_paragraph(f"Job Family: {result['classified_job_family']}")
+    
+        doc.add_heading('Responsibilities', level=2)
+        doc.add_paragraph(result['responsibilities'])
+    
+        doc.add_heading('Qualifications', level=2)
+        for item in result['qualification']:
+            doc.add_paragraph(item, style='List Bullet')
+    
+        doc.add_heading('Interview Questions', level=2)
+        for item in result['interview']:
+            doc.add_paragraph(item, style='List Bullet')
+    
+        doc.add_heading('Skills (Extracted)', level=2)
+        for skill in result['skills'].get("skills", []):
+            doc.add_paragraph(f"{skill.get('skill_name', 'Unnamed Skill')} - {skill.get('description', '')}")
+    
+        doc.add_heading('Skills (ESCO)', level=2)
+        for skill in result['skills_esco'].get("skills", []):
+            doc.add_paragraph(f"{skill.get('skill_name', 'Unnamed Skill')} - {skill.get('description', '')}")
+    
+        if result["ccog_levels"]:
+            doc.add_heading('C-COG Levels', level=2)
+            for key, value in result["ccog_levels"].items():
+                doc.add_paragraph(f"{key}: {value}")
+    
+        if result["esco_levels"]:
+            doc.add_heading('ESCO Levels', level=2)
+            for key, value in result["esco_levels"].items():
+                doc.add_paragraph(f"{key}: {value}")
+
+        
         # Footer
         doc.add_paragraph()
         doc.add_paragraph("Generated by IOM Talent Management AI Tool", style='Footer')
@@ -1134,7 +1096,7 @@ def generate_word_document(
         doc.add_heading("Partial Report Generated", level=1)
         doc.add_paragraph(f"Some sections could not be generated due to: {str(e)}")
 
-    # ================= FILE SAVING WITH MULTIPLE FALLBACKS =================
+    #   FILE SAVING WITH MULTIPLE FALLBACKS  
     try:
         # Generate appropriate filename
         if file_name and isinstance(file_name, str):
@@ -1167,6 +1129,7 @@ def generate_word_document(
         error_doc.save(fallback_path)
         return fallback_path
 
+        
 # ================= GRADIO INTERFACE =================
 with gr.Blocks(
     title="AI-powered tool to review Job Position Description",
@@ -1197,17 +1160,30 @@ css="""
 /* Gradio layout fixes */
 .gradio-container {
     max-width: none !important;
-    padding: 0 !important;
+    padding: 0 20px !important;
 }
 
 .gradio-container .gradio-row {
-        max-width: none !important;
-        margin: 0 !important;
+  max-width: 100% !important;
+  margin: 0 auto !important;
+  flex: 1 !important;
+  display: grid !important;
+  grid-template-columns: 1fr !important;
 }
-    
+
 .gradio-container .gradio-column {
-        min-width: 0 !important;
-        padding: 0 !important;
+  min-width: 0 !important;
+  padding: 0 !important;
+  flex: 1 !important;
+  max-width: none !important;
+}
+
+/* Ensure the parent container doesn't constrain the grid */
+.container-wrap {
+    width: 100%;
+    max-width: none !important;
+    padding: 0 !important;
+    margin: 0 !important;
 }
 
 /* Set the size of the SVG icon for file download */
@@ -1363,14 +1339,15 @@ label {
         box-sizing: border-box;
 }
     
+ 
+
 .skills-container {
-    display: grid;
-    grid-template-columns: repeat(auto-fill, minmax(min(350px, 100%), 1fr));
-    gap: 1.5rem;
-    padding: 1rem;
-    width: 100%;
-    max-width: 100%;
-    box-sizing: border-box;
+  display: grid;
+  grid-template-columns: repeat(auto-fill, minmax(350px, 1fr));
+  gap: 1.5rem;
+  padding: 1rem;
+  width: 100%;
+  margin: 0 auto;
 }
 
 /* Card styling */
@@ -1678,6 +1655,15 @@ progress::-webkit-progress-value {
     padding: 1rem !important;
 }
 /* Responsive Layout */
+
+/* For larger screens */
+@media (min-width: 1200px) {
+  .skills-container {
+      grid-template-columns: repeat(auto-fit, minmax(380px, 1fr));
+      max-width: 1400px;
+  }
+}
+
 @media (max-width: 768px) {
     .gr-row {
         flex-direction: column !important;
@@ -1789,7 +1775,7 @@ progress::-webkit-progress-value {
     with gr.Row():
         with gr.Column():
             gr.Markdown("## Interview Questions")
-            interview_output = gr.Textbox(label="Interview Questions", lines=10, interactive=False)
+            interview_output = gr.Textbox(label="", lines=10, interactive=False)
 
     with gr.Row():
         with gr.Column():
@@ -1824,6 +1810,7 @@ progress::-webkit-progress-value {
                     interactive=False,
                     elem_classes=["debug-console"]
                 )
+                temp_json_path = gr.Textbox(label="", interactive=False)
 
     submit_btn.click(
         fn=process_pdf,
@@ -1838,22 +1825,15 @@ progress::-webkit-progress-value {
             skills_output,
             esco_levels_output,
             esco_skills_output,
-            debug_console if DEBUG else None
+            debug_console if DEBUG else None,
+            temp_json_path_ouput
         ]
     )
 
     download_btn.click(
         fn=generate_word_document,
         inputs=[
-            file_name_output,
-            responsibilities_output,
-            job_family_output,
-            qualification_output,
-            ccoq_levels_output,
-            interview_output,
-            skills_output,
-            esco_levels_output,
-            esco_skills_output
+            temp_json_path_ouput
         ],
         outputs=gr.File(label="Download the corresponding Word report")
     )