Batch Processing Example

import glob
import pandas as pd
from langchain_core.output_parsers import JsonOutputParser
from pydantic import BaseModel, Field
from langchain_community.document_loaders import PyPDFLoader

# Define the data schema
class PerfilEstudiante(BaseModel):
    # Personal Information
    nombre: str = Field(description="Student's full name")
    email: str = Field(description="University or personal email")
    ubicacion: str = Field(description="City/Country")

    # Academic Profile
    universidad: str = Field(description="Name of university or institute")
    carrera: str = Field(description="Major being studied (e.g., Software Engineering)")
    ciclo_actual: str = Field(description="Current semester or cycle (e.g., 7th Semester, Graduate)")

    # Tech Talent
    stack_principal: list = Field(description="List of top 5 languages/technologies they master")
    proyectos_destacados: list = Field(description="Names of academic projects, thesis, or freelance work mentioned")

    # Profile Evaluation
    tipo_perfil: str = Field(description="Classify as: Backend, Frontend, Data, Fullstack, or Management")
    potencial_contratacion: str = Field(description="Brief justification for why to hire them as an intern")

parser = JsonOutputParser(pydantic_object=PerfilEstudiante)

from langchain_core.prompts import ChatPromptTemplate

template_estudiantes = """
You are an Expert in Youth Employability and IT Recruitment.
Analyze this student's CV and extract structured data.

USE THE FOLLOWING JSON FORMAT:
{format_instructions}

EXTRACTION RULES (Focus on Potential):

1. ACADEMIC:
   - Look for current cycle (e.g., "VI Cycle", "7th", "Graduate"). If not stated, infer from dates.
   - University: Extract main name (e.g., "UTP", "UPC", "San Marcos").

2. PROJECTS (Key for juniors):
   - Look for sections like "Academic Projects", "Freelance", or "Experience".
   - Extract concrete project names (e.g., "Library System", "Recycling App").
   - DO NOT put generic company names, look for WHAT THEY DID.

3. PROFILE TYPE:
   - Analyze their skills.
   - If they know Python + Pandas -> "Data".
   - If they know React + Node -> "Fullstack".
   - If they know Java + Spring -> "Backend".

CV TEXT:
{context}
"""

prompt_extract = ChatPromptTemplate.from_template(template_estudiantes)
chain_extract = prompt_extract | llm | parser

resultados = []
archivos = glob.glob("cvs_estudiantes_final/*.pdf")

print(f"Analyzing potential of {len(archivos)} students with AI...")

for pdf in archivos:
    try:
        # Load PDF
        loader = PyPDFLoader(pdf)
        pages = loader.load()
        texto_completo = "\n".join([p.page_content for p in pages])

        # Invoke Gemini
        data = chain_extract.invoke({
            "context": texto_completo,
            "format_instructions": parser.get_format_instructions()
        })

        # Add source filename
        data['archivo_origen'] = pdf.split("/")[-1]
        resultados.append(data)

        print(f"Processed: {data['nombre']} ({data['ciclo_actual']}) -> {data['tipo_perfil']}")

    except Exception as e:
        print(f"Error reading {pdf}: {e}")

print("\nTALENT TABLE (REVERSE MATCH):")
df_talent = pd.DataFrame(resultados)

cols = ["nombre", "universidad", "ciclo_actual", "tipo_perfil", 
        "stack_principal", "potencial_contratacion"]

# Only show columns that exist
cols_existentes = [c for c in cols if c in df_talent.columns]
print(df_talent[cols_existentes])

Analyzing potential of 5 students with AI...
Processed: FERNANDA PAREDES (9no Ciclo) -> Data
Processed: XIMENA RIOS (9no ciclo) -> Fullstack
Processed: NICOLAS PAREDES (7mo Ciclo) -> Fullstack
Processed: LUCIANA CORDOVA (8vo ciclo) -> Fullstack
Processed: FERNANDA MENDOZA (8vo Ciclo) -> Fullstack

TALENT TABLE (REVERSE MATCH):

import pandas as pd

# Export DataFrame
nombre_archivo = "Base_Talento_Estudiantes.xlsx"
df_talent.to_excel(nombre_archivo, index=False)

print(f"Excel file generated: {nombre_archivo}")