Add experience management and skill categorization to profile model

agents/profile_extractor.py

@@ -2,7 +2,7 @@
 Agent for extracting profile information from resumes
 """
 import groq
-from models import Profile, SocialMedia, Project, Skill, Education
+from models import Profile, SocialMedia, Project, Skill, Education, Experience, Category
 from typing import List, Dict, Any, Optional
 from langchain.output_parsers import PydanticOutputParser
 from langchain.prompts import PromptTemplate
@@ -61,7 +61,7 @@ class ProfileExtractor:
             logger.error(f"LangChain extraction failed: {e}")
             if settings.DEBUG:
                 print(f"LangChain extraction failed: {e}")
-            return self._extract_with_fallback(pdf_text)
+            return Profile(name="N/A", title="N/A", email="N/A", bio="N/A")
     
     def _extract_with_langchain(self, pdf_text: str) -> Profile:
         """Extract profile with structured LangChain approach"""
@@ -75,8 +75,9 @@ class ProfileExtractor:
         5. Tagline (a short 5-10 word catchy phrase summarizing professional identity)
         6. Social media links (LinkedIn, GitHub, Instagram)
         7. Projects (with title, description, and tech stack)
-        8. Skills
+        8. Skills (with category only one of : Technical, Soft Skills, or Domain Knowledge)
         9. Education history (with school, degree, field of study, start date and end date)
+        10. Work experience (with company, position, start date, end date, and description)
         
         Return the information in the following JSON format:
         {
@@ -98,8 +99,9 @@ class ProfileExtractor:
                 }
             ],
             "skills": [
-                {"name": "Skill 1"},
-                {"name": "Skill 2"}
+                {"name": "Skill 1", "category": "Technical"},
+                {"name": "Skill 2", "category": "Soft Skills"},
+                {"name": "Skill 3", "category": "Domain Knowledge"}
             ],
             "educations": [
                 {
@@ -109,6 +111,15 @@ class ProfileExtractor:
                     "startDate": "Start Year",
                     "endDate": "End Year or Present"
                 }
+            ],
+            "experiences": [
+                {
+                    "company": "Company Name",
+                    "position": "Job Title",
+                    "startDate": "Start Date",
+                    "endDate": "End Date or Present",
+                    "description": "Job Description"
+                }
             ]
         }
         
@@ -136,7 +147,7 @@ class ProfileExtractor:
         json_start = response_text.find('{')
         json_end = response_text.rfind('}') + 1
         
-        if json_start >= 0 and json_end > json_start:
+        if (json_start >= 0 and json_end > json_start):
             json_str = response_text[json_start:json_end]
             profile_dict = json.loads(json_str)
             profile = Profile.model_validate(profile_dict)
@@ -217,122 +228,80 @@ class ProfileExtractor:
                         logger.debug(f"Added education: {education}")
             except Exception as e:
                 logger.error(f"Error extracting education: {e}")
-        if profile.skills:
+        
+        if not profile.skills:
             try:
-                response = self.llm.invoke("Extract a top 8 of skills from this resume text, separated by commas. Respond with just the skills: " + ", ".join([skill.name for skill in profile.skills]))
-                skills = response.content.split(",")
-                for skill in skills:
-                    if skill:
-                        profile.topSkills.append(Skill(name=skill.strip()))
-                        logger.debug(f"Added skill: {skill}")
+                skills_prompt = """
+                Extract skills from this resume text and categorize them. 
+                For each skill, determine if it's a Technical skill, Soft Skill, or Domain Knowledge.
+                Format the response as a JSON array of objects with 'name' and 'category' fields.
+                Example: [{"name": "Python", "category": "Technical"}, {"name": "Communication", "category": "Soft Skills"}]
+                """
+                response = self.llm.invoke(skills_prompt + "\n\n" + pdf_text)
+                skills_text = response.content.strip()
+                
+                json_start = skills_text.find('[')
+                json_end = skills_text.rfind(']') + 1
+                
+                if json_start >= 0 and json_end > json_start:
+                    skills_json = skills_text[json_start:json_end]
+                    skills_list = json.loads(skills_json)
+                    
+                    for skill_data in skills_list:
+                        category = None
+                        skill_name = skill_data.get("name", "").strip()
+                        category_str = skill_data.get("category", "").strip()
+                        
+                        # Map the category string to our Category enum
+                        if category_str.lower() == "technical":
+                            category = Category.TECHNICAL
+                        elif category_str.lower() in ["soft skills", "soft skill"]:
+                            category = Category.SOFT_SKILLS
+                        elif category_str.lower() in ["domain knowledge", "domain"]:
+                            category = Category.DOMAIN_KNOWLEDGE
+                        
+                        if skill_name:
+                            profile.skills.append(Skill(name=skill_name, category=category))
+                            logger.debug(f"Added categorized skill: {skill_name} ({category})")
             except Exception as e:
-                logger.error(f"Error extracting skills: {e}")
-        
-        return profile
-    
-    def _extract_with_fallback(self, pdf_text: str) -> Profile:
-        """Fallback method for profile extraction using direct API calls"""
-        logger.debug("Extracting profile with fallback method")
-        client = groq.Groq(api_key=self.groq_api_key)
+                logger.error(f"Error extracting categorized skills: {e}")
         
-        def get_llm_response(prompt: str) -> str:
-            """Helper function to get a response from the LLM."""
+        if not profile.experiences:
             try:
-                chat_completion = client.chat.completions.create(
-                    messages=[{"role": "user", "content": prompt}],
-                    model=self.model_name, 
-                    temperature=settings.FALLBACK_TEMPERATURE,
-                    max_tokens=settings.MAX_TOKENS
-                )
-                return chat_completion.choices[0].message.content
+                experience_prompt = """
+                Extract work experience from this resume. For each position, provide:
+                - Company name
+                - Position/job title
+                - Start date
+                - End date (or "Present" if current)
+                - Job description (summarize responsibilities and achievements)
+                Format the response as a list of JSON objects.
+                """
+                response = self.llm.invoke(experience_prompt + "\n\n" + pdf_text)
+                exp_text = response.content.strip()
+                
+                json_start = exp_text.find('[')
+                json_end = exp_text.rfind(']') + 1
+                
+                if json_start >= 0 and json_end > json_start:
+                    exp_json = exp_text[json_start:json_end]
+                    experiences = json.loads(exp_json)
+                    
+                    for exp in experiences:
+                        experience = Experience(
+                            company=exp.get("company", "Unknown"),
+                            position=exp.get("position", ""),
+                            startDate=exp.get("startDate", ""),
+                            endDate=exp.get("endDate", ""),
+                            description=exp.get("description", "")
+                        )
+                        profile.experiences.append(experience)
+                        logger.debug(f"Added experience: {experience.company} - {experience.position}")
             except Exception as e:
-                logger.error(f"Error during LLM call: {e}")
-                return ""  # Return empty string on failure
-        
-        name = get_llm_response(f"Extract the full name from the following text. If no name is present, respond with 'N/A'. Only respond with the name: {pdf_text}").strip()
-        title = get_llm_response(f"Extract the professional title from the following text. If no title is present, respond with 'N/A'. Only respond with the title: {pdf_text}").strip()
-        email = get_llm_response(f"Extract the email address from the following text. If no email is present, respond with 'N/A'. Only respond with the email: {pdf_text}").strip()
-        bio = get_llm_response(f"Create a short professional biography (around 50-100 words) based on the following text. Focus on skills and experience. If no bio is possible, respond with 'N/A'. Provide only the biography itself: {pdf_text}").strip()
-        tagline = get_llm_response(f"Create a short and catchy tagline (around 5-10 words) that summarizes the person's professional identity from the following text. If no tagline is possible, respond with 'N/A'. Provide only the tagline: {pdf_text}").strip()
-        
-        linkedin = get_llm_response(f"Extract the LinkedIn profile URL from the following text. If no LinkedIn URL is present, respond with 'N/A'. Only respond with the LinkedIn URL: {pdf_text}").strip()
-        github = get_llm_response(f"Extract the GitHub profile URL from the following text. If no GitHub URL is present, respond with 'N/A'. Only respond with the GitHub URL: {pdf_text}").strip()
-        instagram = get_llm_response(f"Extract the Instagram profile URL from the following text. If no Instagram URL is present, respond with 'N/A'. Only respond with the Instagram URL: {pdf_text}").strip()
-        
-        project_info = get_llm_response(f"Extract information about projects from the following text in this format Project Title: Project Description: Tech Stack:. If no projects are present, respond with 'N/A': {pdf_text}").strip()
-        skills_info = get_llm_response(f"Extract a list of skills from the following text, separated by commas. If no skills are present, respond with 'N/A'. Only respond with the skills: {pdf_text}").strip()
-        
-        education_info = get_llm_response(f"Extract education history from the following resume. For each education entry, provide the school name, degree type, field of study, start date, and end date. Format as 'School: Degree: Field: StartDate: EndDate' with each education on a new line. If no education is found, respond with 'N/A': {pdf_text}").strip()
-        
-        social_media = SocialMedia(
-            linkedin=linkedin if linkedin != 'N/A' else None,
-            github=github if github != 'N/A' else None,
-            instagram=instagram if instagram != 'N/A' else None
-        )
-        
-        projects = []
-        if project_info != "N/A":
-            project_lines = project_info.split("\n")
-            for line in project_lines:
-                if ":" in line:
-                    try:
-                        project_title, project_description_techstack = line.split(":", 1)
-                        project_description, tech_stack = project_description_techstack.split("Tech Stack:", 1)
-                        
-                        projects.append(Project(
-                            title=project_title.strip(),
-                            description=project_description.strip(),
-                            techStack=tech_stack.strip()
-                        ))
-                        logger.debug(f"Added project: {project_title.strip()}")
-                    except ValueError as e:
-                        logger.error(f"Error parsing project: {line}. Error: {e}")
-        
-        skills = []
-        if skills_info != "N/A":
-            skill_list = [skill.strip() for skill in skills_info.split(",")]
-            for skill_name in skill_list:
-                if skill_name:
-                    skills.append(Skill(name=skill_name))
-                    logger.debug(f"Added skill: {skill_name}")
-        
-        educations = []
-        if education_info != "N/A":
-            education_lines = education_info.split("\n")
-            for line in education_lines:
-                if ":" in line:
-                    try:
-                        parts = line.split(":")
-                        if len(parts) >= 5:
-                            educations.append(Education(
-                                school=parts[0].strip(),
-                                degree=parts[1].strip(),
-                                fieldOfStudy=parts[2].strip(),
-                                startDate=parts[3].strip(),
-                                endDate=parts[4].strip()
-                            ))
-                            logger.debug(f"Added education: {parts[0].strip()}")
-                    except Exception as e:
-                        logger.error(f"Error parsing education: {line}. Error: {e}")
-        
-        profile = Profile(
-            name=name if name != 'N/A' else "N/A",
-            title=title if title != 'N/A' else "N/A",
-            email=email if email != 'N/A' else "N/A",
-            bio=bio if bio != 'N/A' else "N/A",
-            tagline=tagline if tagline != 'N/A' else None,
-            social=social_media if (social_media.github or social_media.instagram or social_media.linkedin) else None,
-            chatbot=None,
-            profileImg=None,
-            heroImg=None,
-            projects=projects,
-            skills=skills,
-            educations=educations
-        )
-        
-        logger.info("Profile extracted successfully with fallback method")
+                logger.error(f"Error extracting work experience: {e}")
+                
         return profile
-
+    
 
 # Create module-level instance for easier imports
 profile_extractor = ProfileExtractor()

app.py

@@ -13,7 +13,7 @@ from typing import Dict, Any
 from agents import profile_extractor as pe, grammar_corrector as gc
 from utils import extract_text_from_pdf, save_temp_pdf
 from services import storage_service
-from models import Skill, Project, Education, SocialMedia
+from models import Skill, Project, Education, SocialMedia, Experience, Category
 from config import get_settings
 
 # Get settings
@@ -182,22 +182,103 @@ def collect_missing_data(profile):
         if proj_data["title"] and proj_data["description"]:  # Only add if title and description are provided
             profile.projects.append(Project(**proj_data))
     
-    # Skills
+    # Skills with categories
     st.subheader("Skills")
     
-    # Create a comma-separated list of existing skills
-    existing_skills = ", ".join([skill.name for skill in profile.skills]) if profile.skills else ""
+    # Group existing skills by category
+    technical_skills = [skill.name for skill in profile.skills if skill.category == Category.TECHNICAL]
+    soft_skills = [skill.name for skill in profile.skills if skill.category == Category.SOFT_SKILLS]
+    domain_skills = [skill.name for skill in profile.skills if skill.category == Category.DOMAIN_KNOWLEDGE]
+    uncategorized = [skill.name for skill in profile.skills if skill.category is None]
     
-    # Allow editing of the skills
-    skills_input = st.text_area("Enter your skills (comma separated):", value=existing_skills)
+    # Allow editing of the skills by category
+    st.write("Technical Skills")
+    tech_skills_input = st.text_area("Enter your technical skills (comma separated):", 
+                                   value=", ".join(technical_skills) if technical_skills else "")
+    
+    st.write("Soft Skills")
+    soft_skills_input = st.text_area("Enter your soft skills (comma separated):", 
+                                   value=", ".join(soft_skills) if soft_skills else "")
+    
+    st.write("Domain Knowledge")
+    domain_skills_input = st.text_area("Enter your domain knowledge skills (comma separated):", 
+                                     value=", ".join(domain_skills) if domain_skills else "")
+    
+    st.write("Uncategorized Skills")
+    uncategorized_input = st.text_area("Enter any other skills (comma separated):", 
+                                     value=", ".join(uncategorized) if uncategorized else "")
     
     # Update profile with skills data
     profile.skills = []
-    if skills_input:
-        skills_list = [skill.strip() for skill in skills_input.split(",")]
-        for skill_name in skills_list:
-            if skill_name:
-                profile.skills.append(Skill(name=skill_name))
+    
+    def add_skills_by_category(skills_input, category):
+        if skills_input:
+            skills_list = [skill.strip() for skill in skills_input.split(",")]
+            for skill_name in skills_list:
+                if skill_name:
+                    profile.skills.append(Skill(name=skill_name, category=category))
+    
+    add_skills_by_category(tech_skills_input, Category.TECHNICAL)
+    add_skills_by_category(soft_skills_input, Category.SOFT_SKILLS)
+    add_skills_by_category(domain_skills_input, Category.DOMAIN_KNOWLEDGE)
+    add_skills_by_category(uncategorized_input, None)
+    
+    # Work Experience
+    st.subheader("Work Experience")
+    experience_data = []
+    
+    # Display existing experience entries with edit options
+    if profile.experiences:
+        for i, exp in enumerate(profile.experiences):
+            st.write(f"Experience #{i+1}")
+            company = st.text_input(f"Company {i+1}:", value=exp.company, key=f"company_{i}")
+            position = st.text_input(f"Position {i+1}:", value=exp.position, key=f"position_{i}")
+            start = st.text_input(f"Start Date {i+1}:", value=exp.startDate, key=f"exp_start_{i}")
+            end = st.text_input(f"End Date {i+1}:", value=exp.endDate if exp.endDate else "", key=f"exp_end_{i}")
+            description = st.text_area(f"Description {i+1}:", value=exp.description if exp.description else "", key=f"exp_desc_{i}")
+            
+            if company and position:  # Only add if company and position are provided
+                experience_data.append({
+                    "company": company,
+                    "position": position,
+                    "startDate": start,
+                    "endDate": end if end else None,
+                    "description": description if description else None
+                })
+    
+    # Option to add new experience entries
+    add_experience = st.checkbox("Add more work experience", key="add_exp")
+    if add_experience:
+        num_new_exp = st.number_input("Number of additional experiences:", min_value=1, max_value=10, value=1)
+        offset = len(profile.experiences) if profile.experiences else 0
+        
+        for i in range(int(num_new_exp)):
+            st.write(f"Additional Experience #{i+1}")
+            company = st.text_input(f"Company:", key=f"new_company_{offset+i}")
+            position = st.text_input(f"Position:", key=f"new_position_{offset+i}")
+            start = st.text_input(f"Start Date:", key=f"new_exp_start_{offset+i}")
+            end = st.text_input(f"End Date:", key=f"new_exp_end_{offset+i}")
+            description = st.text_area(f"Description:", key=f"new_exp_desc_{offset+i}")
+            
+            if company and position:  # Only add if company and position are provided
+                correct_grammar_btn = st.button(f"Correct Grammar for Experience #{i+1}")
+                if correct_grammar_btn and description:
+                    description = grammar_corrector.correct_grammar(description)
+                    st.success("Grammar corrected!")
+                    
+                experience_data.append({
+                    "company": company,
+                    "position": position,
+                    "startDate": start,
+                    "endDate": end if end else None,
+                    "description": description if description else None
+                })
+    
+    # Update profile with experience data
+    profile.experiences = []
+    for exp_data in experience_data:
+        if exp_data["company"] and exp_data["position"]:  # Only add if company and position are provided
+            profile.experiences.append(Experience(**exp_data))
     
     return profile
 
@@ -264,10 +345,42 @@ def display_profile(profile):
         st.subheader("Projects")
         st.table(projects_data)
 
-    # Display skills as a comma separated list if available
+    # Display work experience in a table if available
+    if profile.experiences:
+        experiences_data = {
+            "Company": [exp.company for exp in profile.experiences],
+            "Position": [exp.position for exp in profile.experiences],
+            "Start Date": [exp.startDate for exp in profile.experiences],
+            "End Date": [exp.endDate if exp.endDate else "Present" for exp in profile.experiences],
+            "Description": [exp.description if exp.description else "" for exp in profile.experiences]
+        }
+        st.subheader("Work Experience")
+        st.table(experiences_data)
+
+    # Display skills categorized by type if available
     if profile.skills:
         st.subheader("Skills")
-        st.write(", ".join([skill.name for skill in profile.skills]))
+        
+        technical = [skill.name for skill in profile.skills if skill.category == Category.TECHNICAL]
+        soft = [skill.name for skill in profile.skills if skill.category == Category.SOFT_SKILLS]
+        domain = [skill.name for skill in profile.skills if skill.category == Category.DOMAIN_KNOWLEDGE]
+        other = [skill.name for skill in profile.skills if skill.category is None]
+        
+        if technical:
+            st.write("**Technical Skills:**")
+            st.write(", ".join(technical))
+            
+        if soft:
+            st.write("**Soft Skills:**")
+            st.write(", ".join(soft))
+            
+        if domain:
+            st.write("**Domain Knowledge:**")
+            st.write(", ".join(domain))
+            
+        if other:
+            st.write("**Other Skills:**")
+            st.write(", ".join(other))
 
 def main():
     """Main application function"""

models.py

@@ -1,9 +1,16 @@
 from typing import List, Optional
 from pydantic import BaseModel
+from enum import Enum
+
+class Category(str, Enum):
+    TECHNICAL = "Technical"
+    SOFT_SKILLS = "Soft Skills"
+    DOMAIN_KNOWLEDGE = "Domain Knowledge"
 
 class Skill(BaseModel):
     img: Optional[str] = None # Allow null values
     name: str
+    category: Optional[Category] = None
 
 class Project(BaseModel):
     img: Optional[str] = None
@@ -21,13 +28,20 @@ class SocialMedia(BaseModel):
 class Chatbot(BaseModel):
     token: str
     apiBaseURL: str
-    
+
 class Education(BaseModel):
     school: str
     degree: str
     fieldOfStudy: str
     startDate: str
-    endDate: str    
+    endDate: str
+
+class Experience(BaseModel):
+    company: str
+    position: str
+    startDate: str
+    endDate: Optional[str] = None
+    description: Optional[str] = None
 
 class Profile(BaseModel):
     name: str
@@ -42,4 +56,5 @@ class Profile(BaseModel):
     projects: List[Project] = []
     skills: List[Skill] = []
     topSkills: List[str] = []
-    educations: List[Education] = []
+    educations: List[Education] = []
+    experiences: List[Experience] = []

services/storage_service.py

@@ -38,6 +38,7 @@ class StorageService:
                     projects TEXT,
                     skills TEXT,
                     educations TEXT
+                    experiences TEXT
                 )
             """)
             conn.commit()
@@ -70,7 +71,22 @@ class StorageService:
                     "demoUrl": project.demoUrl
                 } for project in profile.projects
             ]),
-            "skills": json.dumps([skill.name for skill in profile.skills]),
+            "skills": json.dumps([
+                {
+                    "name": skill.name,
+                    "category": skill.category.value if skill.category else None,
+                    "img": skill.img
+                } for skill in profile.skills
+            ]),
+            "experiences": json.dumps([
+                {
+                    "company": exp.company,
+                    "position": exp.position,
+                    "startDate": exp.startDate,
+                    "endDate": exp.endDate,
+                    "description": exp.description
+                } for exp in profile.experiences
+            ]),
             "educations": json.dumps([
                 {
                     "school": edu.school,
@@ -147,8 +163,8 @@ class StorageService:
             conn = sqlite3.connect(self.db_path)
             cursor = conn.cursor()
             cursor.execute("""
-                INSERT INTO profiles (name, title, email, bio, tagline, social, profileImg, projects, skills, educations)
-                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                INSERT INTO profiles (name, title, email, bio, tagline, social, profileImg, projects, skills, educations, experiences)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
             """, (
                 profile_dict["name"],
                 profile_dict["title"],
@@ -159,7 +175,8 @@ class StorageService:
                 profile_dict["profileImg"],
                 profile_dict["projects"],
                 profile_dict["skills"],
-                profile_dict["educations"]
+                profile_dict["educations"],
+                profile_dict["experiences"]
             ))
             conn.commit()
             profile_id = str(cursor.lastrowid)
@@ -211,7 +228,9 @@ class StorageService:
                     "profileImg": row[7],
                     "projects": json.loads(row[8]) if row[8] else [],
                     "skills": json.loads(row[9]) if row[9] else [],
-                    "educations": json.loads(row[10]) if row[10] else []
+                    "educations": json.loads(row[10]) if row[10] else [],
+                    "experiences": json.loads(row[11]) if row[11] else []
+
                 }
                 logger.debug(f"Retrieved profile: {profile_id}")
                 return profile