Basic Query Example

import os
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_huggingface import HuggingFaceEmbeddings

# Ensure API key is set
if not os.getenv("GOOGLE_API_KEY"):
    raise ValueError("You must set the GOOGLE_API_KEY environment variable")

# Initialize LLM
llm = ChatGoogleGenerativeAI(
    model="gemini-1.5-flash",
    temperature=0
)

# Initialize embeddings model
embeddings = HuggingFaceEmbeddings(
    model_name="sentence-transformers/all-MiniLM-L6-v2"
)

print("LLM configured successfully.")

from langchain_community.document_loaders import PyPDFLoader
from langchain_community.vectorstores import FAISS
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
import os, random

# 1. Select a CV file
carpeta_fuente = "cvs_estudiantes_final"

# Get available files
archivos_disponibles = os.listdir(carpeta_fuente)
if not archivos_disponibles:
    raise Exception("No CVs found. Make sure to generate them first.")

# Choose one randomly
archivo_elegido = random.choice(archivos_disponibles)
ruta_archivo = f"{carpeta_fuente}/{archivo_elegido}"

print(f"📂 Selected student profile: '{archivo_elegido}'")
print("⏳ Reading PDF and creating vectors...")

# 2. Load and vectorize
loader = PyPDFLoader(ruta_archivo)
docs = loader.load()
vectorstore = FAISS.from_documents(docs, embeddings)
retriever = vectorstore.as_retriever()

# 3. Define the prompt template
template = """
You are a Technology Career Mentor and expert in youth employability.
Your mission is to analyze this student's profile based ONLY on the following context (their CV):
{context}

Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)

# 4. Create the processing chain
chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

# 5. Ask a question (focused on potential and skills, not years of experience)
pregunta = "What outstanding projects or academic experience does this student have and what is their main technology stack?"
respuesta = chain.invoke(pregunta)

print(f"\n❓ MENTOR QUESTION: {pregunta}")
print("-" * 50)
print(f"🤖 PROFILE ANALYSIS:\n{respuesta}")

📂 Selected student profile: 'CV_Estudiante_4_Fernanda_Paredes.pdf'
⏳ Reading PDF and creating vectors...

❓ MENTOR QUESTION: What outstanding projects or academic experience does this student have and what is their main technology stack?
--------------------------------------------------
🤖 PROFILE ANALYSIS:
Based exclusively on the CV provided, this is the analysis of Fernanda Paredes' profile:

---

### 1. Outstanding Projects and Academic Experience

Fernanda Paredes is a 9th semester Software Engineering student (UTP) seeking her first professional opportunity as a Data Analyst Trainee.

**Her experience and projects focus on the academic realm and are as follows:**

1. **Academic Project as Data Analyst Trainee (Jun 2025 - Feb 2026):** Although the CV does not detail specific project functions, the title indicates an orientation toward data analysis.
2. **Outstanding Achievement (Hackathon):** The strongest point of her profile is having obtained **first place in a university Hackathon** for developing a recycling application. This achievement demonstrates ability to work under pressure, innovation, and practical application of software development knowledge.

### 2. Main Technology Stack

Fernanda's technology stack is mixed, reflecting her interest in both software development and data analysis:

| Area | Mentioned Technologies |
| :--- | :--- |
| **Data Analysis / BI** | Python, PowerBI |
| **Software Development** | Java, Spring Boot |

**Mentor Conclusion:**

Fernanda has a solid foundation in development tools (Java, Spring Boot) and has demonstrated proactivity in the data area (Python, PowerBI), which is coherent with her goal of being a Data Analyst Trainee. Having won a Hackathon is an indicator of high potential and execution capability.