Update app.py

app.py

@@ -8,7 +8,8 @@ import fitz
 import docx2txt
 from groq import Groq
 from dotenv import load_dotenv
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, ValidationError # Added ValidationError
+from typing import Optional, List # Added Optional and List
 
 # --- 0. FIX: SET PAGE CONFIG AS THE FIRST STREAMLIT COMMAND ---
 st.set_page_config(layout="wide", page_title="Quantum Scrutiny Platform | Groq-Powered")
@@ -55,16 +56,22 @@ class ResumeAnalysis(BaseModel):
     name: str = Field(description="Full name of the candidate.")
     email: str = Field(description="Professional email address.")
     phone: str = Field(description="Primary phone number.")
-    certifications: list[str] = Field(description="List of professional certifications (e.g., PMP, AWS Certified).")
+    certifications: List[str] = Field(description="List of professional certifications.")
     experience_summary: str = Field(description="A concise summary of the candidate's professional experience.")
     education_summary: str = Field(description="A concise summary of the candidate's highest education.")
     
-    # --- FIX 1: Explicitly describe required STRING output format ---
-    communication_skills: str = Field(description="A score as a STRING (e.g., '8') or brief description of communication skills.")
-    technical_skills: list[str] = Field(description="List of technical skills/technologies mentioned (e.g., Python, SQL, Docker).")
-    aba_therapy_skills: str = Field(description="Specific mention or score as a STRING (e.g., '7') for ABA Therapy skills, ONLY if the role is 'Therapist'. Use the STRING 'N/A' if not applicable or found.")
-    rbt_bcba_certification: str = Field(description="Indicate the STRING 'Yes' or 'No' if RBT/BCBA certification is mentioned, ONLY if the role is 'Therapist'. Use the STRING 'N/A' if not applicable or found.")
-    autism_care_experience_score: str = Field(description="A score as a STRING (e.g., '9') for Autism-Care Experience, ONLY if the role is 'Therapist'. Use the STRING 'N/A' if not applicable or found.")
+    # --- CRITICAL FIX: Use str or Optional[str] and improve coercion ---
+    # The Groq model is returning INT (8) instead of STR ('8') for communication_skills. 
+    # The most stable fix is to keep the field as str and rely on Groq's JSON mode 
+    # but improve the prompt guidance. We will also update the helper functions to be more robust.
+    communication_skills: str = Field(description="A score as a STRING (e.g., '8') or description of communication skills.")
+    technical_skills: List[str] = Field(description="List of technical skills/technologies mentioned.")
+    
+    # These fields can sometimes return None, so we make them Optional[str]
+    # and default them to "N/A" in the final output in the analyze function if still None.
+    aba_therapy_skills: Optional[str] = Field(default="N/A", description="Specific score as a STRING (e.g., '7'). Use 'N/A' if not applicable.")
+    rbt_bcba_certification: Optional[str] = Field(default="N/A", description="Indicate 'Yes' or 'No'. Use 'N/A' if not applicable.")
+    autism_care_experience_score: Optional[str] = Field(default="N/A", description="A score as a STRING (e.g., '9'). Use 'N/A' if not applicable.")
 
 
 # --- 3. HELPER FUNCTIONS ---
@@ -95,30 +102,29 @@ def analyze_resume_with_groq(resume_text: str, job_role: str) -> ResumeAnalysis:
     therapist_instructions = ""
     if job_role == "Therapist":
         therapist_instructions = (
-            "Because the job role is 'Therapist', you MUST carefully look for: "
-            "1. ABA Therapy Skills, RBT/BCBA Certification, and Autism-Care Experience. "
-            "2. Provide a score from 1-10 as a **STRING** (e.g., '7') for the specialized fields: 'aba_therapy_skills' and 'autism_care_experience_score'. "
-            "3. If any specialized therapist field is not found, you MUST use the **STRING** 'N/A'. "
-            "4. Set 'rbt_bcba_certification' to the **STRING** 'Yes' or 'No'."
+            "Because the job role is 'Therapist', you MUST carefully look for ABA Therapy Skills, RBT/BCBA Certification, and Autism-Care Experience. "
+            "Provide a score from 1-10 as a **STRING** (e.g., '7') for the specialized fields. "
+            "If any specialized therapist field is not found, you MUST return **null** or **N/A** for that field."
         )
     else:
-        # For non-therapist roles, explicitly instruct the model to use 'N/A' for therapist fields
+        # For non-therapist roles, explicitly instruct the model to use 'null' 
+        # so Optional[str] handles it cleanly.
         therapist_instructions = (
-            "Since the role is not 'Therapist', set 'aba_therapy_skills', 'autism_care_experience_score', and 'rbt_bcba_certification' to the **STRING** 'N/A'."
+            "Since the role is not 'Therapist', set 'aba_therapy_skills', 'autism_care_experience_score', and 'rbt_bcba_certification' to **null** or **N/A**."
         )
 
     # System Prompt for Groq
     system_prompt = (
         f"You are a professional Resume Analyzer. Your task is to extract specific information from the provided resume text. "
         f"The candidate is applying for the role of '{job_role}'. "
-        f"Follow the instructions precisely and return a JSON object that strictly adheres to the provided Pydantic schema. "
-        f"**IMPORTANT:** All values must be returned as the data type specified. Numerical scores must be enclosed in quotes to be treated as **STRING** types (e.g., \"8\"). "
-        f"For skills, provide a list of 5-10 most relevant items. {therapist_instructions}"
+        f"Return a JSON object that strictly adheres to the provided Pydantic schema. "
+        f"**CRITICAL:** Ensure 'communication_skills' is returned as a **STRING** value, even if it's a number (e.g., \"8\" NOT 8). " # <-- Re-emphasizing string output for the specific failing field
+        f"{therapist_instructions}"
     )
 
     try:
         chat_completion = groq_client.chat.completions.create(
-            model="mixtral-8x7b-32768", # Fast model suitable for this task
+            model="mixtral-8x7b-32768", 
             messages=[
                 {"role": "system", "content": system_prompt},
                 {"role": "user", "content": f"Analyze the following resume text:\n\n---\n{resume_text}\n---"}
@@ -127,15 +133,23 @@ def analyze_resume_with_groq(resume_text: str, job_role: str) -> ResumeAnalysis:
             temperature=0.0
         )
         
-        # The response is a JSON string, which we can parse into the Pydantic model
+        # Parse the JSON response
         analysis = ResumeAnalysis.parse_raw(chat_completion.choices[0].message.content)
+
+        # Post-processing: Ensure Optional fields are strings for score calculation
+        analysis.aba_therapy_skills = str(analysis.aba_therapy_skills or 'N/A')
+        analysis.rbt_bcba_certification = str(analysis.rbt_bcba_certification or 'N/A')
+        analysis.autism_care_experience_score = str(analysis.autism_care_experience_score or 'N/A')
+        analysis.communication_skills = str(analysis.communication_skills) # Coerce communication_skills to string just in case it passed validation as an int somehow
+
         return analysis
         
+    except ValidationError as ve:
+        st.error(f"Groq API Validation Error: The model returned incompatible data. Details: {ve}")
+        print(f"Failed JSON: {chat_completion.choices[0].message.content}") # Print the bad JSON for debugging
+        return ResumeAnalysis(name="Extraction Failed", email="", phone="", certifications=[], experience_summary="", education_summary="", communication_skills="N/A", technical_skills=[], aba_therapy_skills="N/A", rbt_bcba_certification="N/A", autism_care_experience_score="N/A")
     except Exception as e:
-        # This will now only catch errors related to the API connection or Pydantic structural errors
-        # (e.g., list vs string), not the common type mismatches.
         st.error(f"Groq API Error: {e}") 
-        # Return an empty/default analysis object on failure
         return ResumeAnalysis(name="Extraction Failed", email="", phone="", certifications=[], experience_summary="", education_summary="", communication_skills="N/A", technical_skills=[], aba_therapy_skills="N/A", rbt_bcba_certification="N/A", autism_care_experience_score="N/A")
 
 
@@ -154,11 +168,11 @@ def calculate_resume_score(analysis: ResumeAnalysis) -> float:
 
     # 3. Communication Score (Max 20 points)
     try:
-        # Safely parse the communication score string (e.g., '8' or '8-High')
-        score_str = analysis.communication_skills.split('-')[0].strip()
+        # Safely parse the communication score string, handling N/A or raw numbers
+        score_str = str(analysis.communication_skills).split('-')[0].strip() # Use str() to handle if it somehow remained an int
         comm_rating = float(score_str)
     except (ValueError, IndexError):
-        comm_rating = 5.0 # Default if unparsable
+        comm_rating = 5.0 
         
     score_comm = (comm_rating / 10.0) * 20.0
     total_score += score_comm
@@ -170,15 +184,15 @@ def calculate_resume_score(analysis: ResumeAnalysis) -> float:
     # --- Therapist-Specific Bonus Checks ---
     if st.session_state.get('selected_role') == "Therapist":
         try:
-            # Safely parse specialized scores, handling 'N/A'
-            aba_score = float(analysis.aba_therapy_skills.split('-')[0].strip()) if analysis.aba_therapy_skills != 'N/A' else 0.0
-            autism_score = float(analysis.autism_care_experience_score.split('-')[0].strip()) if analysis.autism_care_experience_score != 'N/A' else 0.0
+            # Safely parse specialized scores, handling 'N/A' or None
+            aba_score = float(str(analysis.aba_therapy_skills).split('-')[0].strip()) if str(analysis.aba_therapy_skills).upper() not in ['N/A', 'NONE'] else 0.0
+            autism_score = float(str(analysis.autism_care_experience_score).split('-')[0].strip()) if str(analysis.autism_care_experience_score).upper() not in ['N/A', 'NONE'] else 0.0
             
             # Add a bonus based on the average specialized scores (max 10 points)
             specialized_bonus = ((aba_score + autism_score) / 20.0) * 10.0
             total_score += specialized_bonus
-        except (ValueError, IndexError):
-            pass
+        except (ValueError, IndexError, TypeError):
+            pass # Ignore if specialized scores are still corrupted
 
     
     final_score = round(min(total_score, 100))
@@ -196,6 +210,12 @@ def append_analysis_to_dataframe(job_role: str, analysis: ResumeAnalysis, score:
     technical_skills_list = ", ".join(data['technical_skills'])
     certifications_list = ", ".join(data['certifications'])
     
+    # Ensure fields that might have been None are now strings for the DataFrame
+    comm_skills = str(data['communication_skills'] or 'N/A')
+    aba_skills = str(data['aba_therapy_skills'] or 'N/A')
+    rbt_cert = str(data['rbt_bcba_certification'] or 'N/A')
+    autism_exp = str(data['autism_care_experience_score'] or 'N/A')
+    
     df_data = {
         'Name': data['name'],
         'Job Role': job_role,
@@ -205,12 +225,12 @@ def append_analysis_to_dataframe(job_role: str, analysis: ResumeAnalysis, score:
         'Shortlisted': data['Shortlisted'],
         'Experience Summary': data['experience_summary'],
         'Education Summary': data['education_summary'],
-        'Communication Rating (1-10)': data['communication_skills'],
+        'Communication Rating (1-10)': comm_skills,
         'Skills/Technologies': technical_skills_list,
         'Certifications': certifications_list,
-        'ABA Skills (1-10)': data['aba_therapy_skills'],
-        'RBT/BCBA Cert': data['rbt_bcba_certification'],
-        'Autism-Care Exp (1-10)': data['autism_care_experience_score'],
+        'ABA Skills (1-10)': aba_skills,
+        'RBT/BCBA Cert': rbt_cert,
+        'Autism-Care Exp (1-10)': autism_exp,
     }
 
     new_df = pd.DataFrame([df_data])