updated with gemini and new anthropic models too

app.py

@@ -1,22 +1,23 @@
 from dotenv import load_dotenv
-import io
+# import io
 import streamlit as st
-import streamlit.components.v1 as components
-import base64
+# import streamlit.components.v1 as components
+# import base64
 
-from langchain.prompts import PromptTemplate
-from langchain_core.output_parsers import PydanticOutputParser
+# from langchain.prompts import PromptTemplate
+# from langchain_core.output_parsers import PydanticOutputParser
 from langchain_anthropic import ChatAnthropic
 from langchain_openai import ChatOpenAI
 from langchain_groq import ChatGroq
+# from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_core.exceptions import OutputParserException
-from pydantic import ValidationError
-from langchain_core.pydantic_v1 import BaseModel, Field
-from resume_template import Resume
-from json import JSONDecodeError
-import PyPDF2
-import json
+# from langchain_core.exceptions import OutputParserException
+# from pydantic import ValidationError
+# from langchain_core.pydantic_v1 import BaseModel, Field
+# from resume_template import Resume
+# from json import JSONDecodeError
+# import PyPDF2
+# import json
 import time
 import os
 
@@ -31,7 +32,6 @@ os.environ['LANGCHAIN_PROJECT'] = 'Resume_Project'
 
 load_dotenv()
 
-
 st.set_page_config(layout="wide")
 
 st.title("Resume Parser")
@@ -52,13 +52,15 @@ with col2:
     """)
 
 llm_dict = {
-    "GPT 3.5 turbo": ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo"),
-    "Anthropic Sonnet": ChatAnthropic(model_name="claude-3-sonnet-20240229"),
+    "GPT 3.5 turbo": ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo-0125"),
+    "GPT 4o": ChatOpenAI(temperature=0, model_name="gpt-4o"),
+    "Anthropic 3.5 Sonnet": ChatAnthropic(model="claude-3-5-sonnet-20240620"),
     "Llama 3 8b": ChatGroq(model_name="llama3-8b-8192"),
     "Llama 3 70b": ChatGroq(model_name="llama3-70b-8192"),
     "Gemma 7b": ChatGroq(model_name="gemma-7b-it"),
     "Mixtral 8x7b": ChatGroq(model_name="mixtral-8x7b-32768"),
-    # "Gemini 1.5 Pro": ChatGoogleGenerativeAI(model_name="gemini-1.5-pro-latest"),
+    "Gemini 1.5 Pro": ChatGoogleGenerativeAI(model="gemini-1.5-pro"),
+    "Gemini 1.5 Flash": ChatGoogleGenerativeAI(model="gemini-1.5-flash"),
 }
 
 uploaded_file = st.file_uploader("Upload a PDF file", type="pdf")

resume_field_extraction.py

@@ -0,0 +1,40 @@
+from typing import List, Optional
+
+from langchain.chains import create_structured_output_runnable
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_core.pydantic_v1 import BaseModel, Field
+from langchain_openai import ChatOpenAI
+
+class CompanyOverview(BaseModel):
+    """Information about the company offering the job."""
+    about: Optional[str] = Field(..., description="Brief description of the company")
+    mission_and_values: Optional[str] = Field(None, description="Company mission and values")
+    size_and_locations: Optional[str] = Field(None, description="Company size and locations")
+
+class RoleSummary(BaseModel):
+    """Summary information about the job role."""
+    title: str = Field(..., description="Job title")
+    team_or_department: Optional[str] = Field(None, description="Team or department the role belongs to")
+    role_type: Optional[str] = Field(..., description="Type of role (full-time, part-time, contract, etc.)")
+    location: Optional[str] = Field(..., description="Location (on-site, remote, hybrid)")
+
+class ResponsibilitiesAndQualifications(BaseModel):
+    """Key responsibilities and qualifications for the job role."""
+    responsibilities: List[str] = Field(..., description="Key responsibilities of the role")
+    projects_and_problems: Optional[str] = Field(None, description="Types of projects and problems to be worked on")
+    required_skills_and_experience: List[str] = Field(..., description="Required skills and experience for the role")
+    preferred_skills_and_experience: Optional[List[str]] = Field(None, description="Preferred skills and experience for the role")
+
+class CompensationAndBenefits(BaseModel):
+    """Compensation and benefits offered for the job role."""
+    salary_or_pay_range: Optional[str] = Field(None, description="Salary or hourly pay range")
+    bonus_and_equity: Optional[str] = Field(None, description="Bonus and equity compensation")
+    benefits: Optional[List[str]] = Field(None, description="Benefits (health insurance, retirement plans, PTO, etc.)")
+    perks: Optional[List[str]] = Field(None, description="Perks (food, commuter benefits, learning stipend, etc.)")
+
+class JobDescription(BaseModel):
+    """Extracted information from a job description."""
+    company_overview: CompanyOverview
+    role_summary: RoleSummary
+    responsibilities_and_qualifications: ResponsibilitiesAndQualifications
+    compensation_and_benefits: CompensationAndBenefits

resume_helpers.py

@@ -29,13 +29,15 @@ os.environ['LANGCHAIN_PROJECT'] = 'Resume_Project'
 
 load_dotenv()
 llm_dict = {
-    "GPT 3.5 turbo": ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo"),
-    "Anthropic Sonnet": ChatAnthropic(model_name="claude-3-sonnet-20240229"),
+    "GPT 3.5 turbo": ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo-0125"),
+    "GPT 4o": ChatOpenAI(temperature=0, model_name="gpt-4o"),
+    "Anthropic 3.5 Sonnet": ChatAnthropic(model="claude-3-5-sonnet-20240620"),
     "Llama 3 8b": ChatGroq(model_name="llama3-8b-8192"),
     "Llama 3 70b": ChatGroq(model_name="llama3-70b-8192"),
     "Gemma 7b": ChatGroq(model_name="gemma-7b-it"),
     "Mixtral 8x7b": ChatGroq(model_name="mixtral-8x7b-32768"),
-    # "Gemini 1.5 Pro": ChatGoogleGenerativeAI(model_name="gemini-1.5-pro-latest"),
+    "Gemini 1.5 Pro": ChatGoogleGenerativeAI(model="gemini-1.5-pro"),
+    "Gemini 1.5 Flash": ChatGoogleGenerativeAI(model="gemini-1.5-flash"),
 }
 def pdf_to_string(file):
     """

resume_template.py

@@ -32,11 +32,6 @@ class Project(BaseModel):
     technologies: Optional[str] = None
     role: Optional[str] = None
 
-# class Certification(BaseModel):
-#     title: Optional[str] = None
-#     certifying_body: Optional[str] = None
-#     date: Optional[str] = None
-
 class Publication(BaseModel):
     title: Optional[str] = None
     co_authors: List[str] = []