Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/JoseOlivares19/Proyecto-PC3-JavaScript-Avanzado/llms.txt

Use this file to discover all available pages before exploring further.

The /predict/talent-match endpoint classifies a developer’s technical profile into one of four career tracks by combining self-assessed skill scores across five technology areas with their project experience count and stated career preference. The RandomForest model applies weighted scoring across Frontend, Backend, Data, and Fullstack dimensions to determine the best-fit profile. The response includes confidence, a four-profile probability ranking, and a concrete development roadmap tailored to the predicted track.

​
Endpoint

POST http://localhost:8001/predict/talent-match
Content-Type: application/json

​
Request Body

​
javascript
integer
required
Self-assessed JavaScript proficiency score. Must be between 0 and 100.
​
react
integer
required
Self-assessed React proficiency score. Must be between 0 and 100.
​
spring_boot
integer
required
Self-assessed Spring Boot proficiency score. Must be between 0 and 100.
​
python_datos
integer
required
Self-assessed Python for data / ML proficiency score. Must be between 0 and 100.
​
sql
integer
required
Self-assessed SQL proficiency score. Must be between 0 and 100.
​
experiencia_proyectos
integer
required
Number of completed projects the developer has delivered (academic or professional). Must be between 0 and 10.
​
preferencia
integer
required
Developer’s stated career track preference. Accepted values:
  • 0 — Frontend
  • 1 — Backend
  • 2 — Data / Analytics
  • 3 — Fullstack

​
Example Request

curl -X POST http://localhost:8001/predict/talent-match \
  -H "Content-Type: application/json" \
  -d '{
    "javascript": 85,
    "react": 90,
    "spring_boot": 20,
    "python_datos": 15,
    "sql": 55,
    "experiencia_proyectos": 4,
    "preferencia": 0
  }'

​
Example Response

{
  "caso": "TalentMatchAI",
  "prediccion": "FRONTEND_REACT",
  "confianza": 0.9388,
  "ranking": [
    { "clase": "FRONTEND_REACT",      "probabilidad": 0.9388 },
    { "clase": "FULLSTACK_JUNIOR",     "probabilidad": 0.0412 },
    { "clase": "BACKEND_SPRING",       "probabilidad": 0.0138 },
    { "clase": "DATA_ANALYST_JUNIOR",  "probabilidad": 0.0062 }
  ],
  "recomendaciones": [
    "Construir un dashboard React con rutas, hooks y consumo REST.",
    "Reforzar diseño de componentes y manejo de estado."
  ],
  "entrada": {
    "javascript": 85,
    "react": 90,
    "spring_boot": 20,
    "python_datos": 15,
    "sql": 55,
    "experiencia_proyectos": 4,
    "preferencia": 0
  }
}

​
Response Fields

​
caso
string
Human-readable model identifier. Always "TalentMatchAI" for this endpoint.
​
prediccion
string
The top predicted career profile label. One of:
LabelProfile
FRONTEND_REACTStrong JS and React scores with frontend preference — build component-driven UIs
BACKEND_SPRINGStrong Spring Boot and SQL scores with backend preference — build REST APIs and services
DATA_ANALYST_JUNIORStrong Python and SQL scores with data preference — build pipelines and ML models
FULLSTACK_JUNIORBalanced scores across all areas with fullstack preference — integrate end-to-end systems
​
confianza
float
Probability assigned to the top predicted profile, in the range 0.0 to 1.0.
​
ranking
array of objects
Probability distribution across all four career profile labels, sorted in descending order of probability.
​
recomendaciones
array of strings
A two-item development roadmap tailored to the predicted profile. Recommendations are fixed per label and focus on the most impactful next steps for the developer to consolidate their track.
​
entrada
object
Echo of the validated request payload as parsed by Pydantic. Use this to store the assessed profile alongside the developer record in your talent management system.
The preferencia field carries a fixed bonus of 12 points to its corresponding profile dimension inside the model’s scoring function. Setting preferencia to align with the developer’s strongest skill area will yield the highest confidence scores. Mismatches between skill scores and preferencia are valid inputs and will produce a lower-confidence prediction reflecting the tension between ability and stated preference.

Build docs developers (and LLMs) love

Get started for freeTalk to us