feat: módulo embedding — encode, model CRUD, stores sqlvec y usearch

Funciones Python para embeddings: carga/guardado de modelos, encoding de
texto, y almacenamiento/búsqueda vectorial con sqlite-vec y usearch.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-02 22:03:57 +02:00
parent 99672a4745
commit f4d9d09575
11 changed files with 456 additions and 0 deletions
@@ -0,0 +1,33 @@
---
name: embedding_load_model
kind: function
lang: py
domain: infra
version: "1.0.0"
purity: impure
signature: "def embedding_load_model(path: str) -> SentenceTransformer"
description: "Carga modelo de embeddings desde path local. Retorna instancia lista para encode."
tags: [embedding, model, load, python]
uses_functions: []
uses_types: []
returns: []
returns_optional: false
error_type: "error_go_core"
imports: [sentence_transformers]
tested: false
tests: []
test_file_path: ""
file_path: "python/functions/embedding/model.py"
---
## Ejemplo
```python
model = embedding_load_model(".local/models/e5-small")
# model listo para usar con embedding_encode
```
## Notas
Carga desde path local (~1.8s) es mas rapida que desde HF cache (~4.1s).
El modelo retornado es compatible con embedding_encode.