Skip to main content

​
Overview

The Documents API provides comprehensive document management with AI-powered features including semantic search, automatic metadata extraction, OCR processing, and document relationships. Base Path: /documentos/ Search documents by metadata and content. 
GET /documentos/api/buscar/
​
q
string
Search query for document title, code, or content
​
tipo_id
integer
Filter by document type ID
​
disciplina_id
integer
Filter by discipline ID
​
estado
string
Filter by status: BORRADOR, REVISION, APROBADO, ARCHIVADO
​
fecha_desde
string
Filter by date from (YYYY-MM-DD)
​
fecha_hasta
string
Filter by date to (YYYY-MM-DD)

​
Response

​
results
array
Array of document objects
Perform AI-powered semantic search using embeddings. 
POST /documentos/api/busqueda-vectorial/
​
query
string
required
Natural language search query
​
limit
integer
default:"10"
Number of results to return
​
similarity_threshold
float
default:"0.7"
Minimum similarity score (0-1)
​
biblioteca_id
integer
Filter by library/collection ID

​
Response

​
results
array
Array of search results with similarity scores
fetch('/documentos/api/busqueda-vectorial/', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-CSRFToken': csrfToken
  },
  credentials: 'same-origin',
  body: JSON.stringify({
    query: 'pump maintenance procedures',
    limit: 5,
    similarity_threshold: 0.75
  })
})
.then(res => res.json())
.then(data => console.log(data.results));

​
Document Details

​
Get Document Details

Retrieve comprehensive information about a document. 
GET /documentos/api/detalle/{doc_id}/
​
doc_id
integer
required
Document ID

​
Response

​
id
integer
Document ID
​
codigo
string
Document code
​
titulo
string
Document title
​
tipo
object
Document type information
​
disciplina
object
Discipline information
​
estado
string
Current status
​
revision_actual
object
Current revision details
​
metadatos
object
Custom metadata fields
​
comentarios
array
Array of comments
​
respuestas
array
Related response documents
​
responsable
object
Responsible user information

​
Document Operations

​
Update Document Status

Change the status of a document. 
POST /documentos/api/actualizar-estado/{doc_id}/
​
doc_id
integer
required
Document ID
​
estado
string
required
New status: BORRADOR, REVISION, APROBADO, ARCHIVADO
​
comentario
string
Optional comment explaining the status change

​
Update Document Responsible

Assign a new responsible person. 
POST /documentos/api/actualizar-responsable/{doc_id}/
​
doc_id
integer
required
Document ID
​
responsable_id
integer
required
User ID of new responsible person

​
Update Document Date

Update the document date. 
POST /documentos/api/actualizar-fecha/{doc_id}/
​
doc_id
integer
required
Document ID
​
fecha
string
required
New date (YYYY-MM-DD format)
​
tipo
string
required
Date type: emision, vencimiento, recepcion

​
Comments and Annotations

​
Add Comment

Add a comment to a document. 
POST /documentos/api/comentar/{doc_id}/
​
doc_id
integer
required
Document ID
​
texto
string
required
Comment text
​
x
float
X coordinate for pin comment on PDF
​
y
float
Y coordinate for pin comment on PDF
​
pagina
integer
PDF page number for pin
​
vinculos
array
Array of document IDs to link

​
Response

​
status
string
“success” or “error”
​
comentario_id
integer
Created comment ID
fetch('/documentos/api/comentar/456/', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-CSRFToken': csrfToken
  },
  credentials: 'same-origin',
  body: JSON.stringify({
    texto: 'This section needs revision',
    x: 150.5,
    y: 300.2,
    pagina: 3
  })
});

​
Edit Comment

Update an existing comment. 
POST /documentos/api/comentar/u/{comentario_id}/
​
comentario_id
integer
required
Comment ID
​
texto
string
required
Updated comment text

​
Delete Comment

Remove a comment. 
POST /documentos/api/comentar/d/{comentario_id}/
​
comentario_id
integer
required
Comment ID to delete

​
AI Processing

​
Trigger Text Extraction

Trigger n8n workflow to extract text from PDF. 
POST /documentos/api/trigger-extraction/{doc_id}/
​
doc_id
integer
required
Document ID
This endpoint triggers an external n8n workflow for PDF text extraction using OCR.

​
Update Extracted Text

Callback endpoint to receive extracted text from n8n. 
POST /documentos/api/update-texto/{doc_id}/
​
doc_id
integer
required
Document ID
​
texto
string
required
Extracted text content

​
Vectorize Document

Generate embeddings for semantic search. 
POST /documentos/api/vectorize/{doc_id}/
​
doc_id
integer
required
Document ID
Uses Google Gemini API to generate embeddings from extracted text. Configured via GEMINI_API_KEY setting.

​
Chat with AI

Ask questions about documents using AI. 
POST /documentos/api/chat-ia/
​
query
string
required
Natural language question
​
documento_id
integer
Specific document ID to query
​
biblioteca_id
integer
Library/collection ID to search within

​
Response

​
respuesta
string
AI-generated answer
​
documentos_relevantes
array
Array of relevant document IDs
​
confianza
float
Confidence score (0-1)
fetch('/documentos/api/chat-ia/', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-CSRFToken': csrfToken
  },
  credentials: 'same-origin',
  body: JSON.stringify({
    query: 'What is the recommended maintenance interval for centrifugal pumps?',
    biblioteca_id: 5
  })
});

​
Library Management

​
Get Document Libraries

Retrieve libraries/collections for a document. 
GET /documentos/api/bibliotecas/{doc_id}/
​
doc_id
integer
required
Document ID

​
Response

​
bibliotecas
array
Array of library objects

​
Toggle Library Membership

Add or remove document from a library. 
POST /documentos/api/bibliotecas/toggle/{doc_id}/{bib_id}/
​
doc_id
integer
required
Document ID
​
bib_id
integer
required
Library ID

​
Get Library Documents

Retrieve all documents in a library. 
GET /documentos/api/bibliotecas/documentos/{bib_id}/
​
bib_id
integer
required
Library ID
​
page
integer
default:"1"
Page number for pagination

​
Metadata Management

​
Get Model Fields

Retrieve available fields for a content type (for metadata configuration). 
GET /documentos/api/model-fields/
​
ct_id
integer
required
ContentType ID

​
Response

​
fields
array
Array of field names available for the model

​
Update Metadata Value

Update a custom metadata field value. 
POST /documentos/api/metadato/u/{mv_id}/
​
mv_id
integer
required
MetadataValue ID
​
valor
string
required
New metadata value

​
Document Creation

​
Bulk Upload

Upload multiple documents at once. 
POST /documentos/carga-masiva/submit/
​
archivos
array
required
Array of file uploads (multipart/form-data)
​
tipo_id
integer
required
Default document type ID
​
disciplina_id
integer
Default discipline ID
​
auto_process
boolean
default:"true"
Automatically trigger AI processing

​
n8n Integration

​
Processing Callback

Webhook endpoint for n8n to return processing results. 
POST /documentos/api/callback-procesamiento/{revision_id}/
​
revision_id
integer
required
Revision ID
​
texto_extraido
string
Extracted text from PDF
​
metadata
object
Extracted metadata (title, author, date, etc.)
​
procesado_exitoso
boolean
required
Whether processing was successful
This endpoint is called by the n8n workflow after PDF processing completes.Configuration:
  • N8N_PROCESS_DOCUMENT_WEBHOOK_URL - Webhook URL to trigger processing
  • INTERNAL_SITE_URL - URL for n8n to callback to Django

​
Configuration

​
Key Settings

# energia/settings.py

# n8n Integration
N8N_BASE_URL = os.environ.get('N8N_INTERNAL_URL', 'http://n8n:5678')
N8N_EXTRACT_TEXTO_WEBHOOK_URL = f'{N8N_BASE_URL}/webhook/extract-text'
N8N_PROCESS_DOCUMENT_WEBHOOK_URL = f'{N8N_BASE_URL}/webhook/process-document'
N8N_CHAT_WEBHOOK_URL = f'{N8N_BASE_URL}/webhook/chat-documento'

# AI Configuration
GEMINI_API_KEY = os.environ.get('GEMINI_API_KEY', '')

# Callback URL
INTERNAL_SITE_URL = os.environ.get('INTERNAL_SITE_URL', 'http://app:8000')

​
Next Steps

Assets API

Asset management endpoints

Maintenance API

Work orders and maintenance

Build docs developers (and LLMs) love

Get started for freeTalk to us