Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+base_semantica.json filter=lfs diff=lfs merge=lfs -text

api_semantica.py

@@ -0,0 +1,51 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer, util
+import numpy as np
+import json
+import uvicorn
+
+app = FastAPI()
+
+# Cargar el modelo
+modelo = SentenceTransformer("sentence-transformers/paraphrase-multilingual-mpnet-base-v2")
+
+# Cargar la base de embeddings
+with open("base_semantica.json", "r", encoding="utf-8") as f:
+    base = json.load(f)
+
+# Pydantic schema para entrada
+class PreguntaInput(BaseModel):
+    pregunta: str
+    top_k: int = 3
+
+# Función de búsqueda
+def buscar_semanticamente(pregunta, top_k=3):
+    emb_pregunta = modelo.encode(pregunta)
+    resultados = []
+    for item in base:
+        emb_item = np.array(item["embedding"], dtype=np.float32)
+        score = util.cos_sim(emb_pregunta, emb_item).item()
+        resultados.append((score, item))
+    resultados.sort(reverse=True, key=lambda x: x[0])
+    return resultados[:top_k]
+
+# Endpoint principal
+@app.post("/buscar")
+async def buscar(input: PreguntaInput):
+    resultados = buscar_semanticamente(input.pregunta, input.top_k)
+    return {
+        "pregunta": input.pregunta,
+        "resultados": [
+            {
+                "score": round(score, 4),
+                "titulo": item["titulo"],
+                "url": item["url"],
+                "texto": item["texto"]
+            } for score, item in resultados
+        ]
+    }
+
+# Para correr en Hugging Face
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

base_semantica.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5758155fccf9c8e753e8fba10980900d78847bb5edfe09ea430ab5dcfbddcb6c
+size 169259490

requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+numpy
+sentence-transformers
+torch
+transformers
+pydantic