From f1eb44ab956a6751dde3fbec130e3c9c109b7f4e Mon Sep 17 00:00:00 2001 From: Lars Date: Wed, 3 Sep 2025 12:28:19 +0200 Subject: [PATCH] =?UTF-8?q?embed=5Fserver.py=20gel=C3=B6scht?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- embed_server.py | 38 -------------------------------------- 1 file changed, 38 deletions(-) delete mode 100644 embed_server.py diff --git a/embed_server.py b/embed_server.py deleted file mode 100644 index ec9f6e9..0000000 --- a/embed_server.py +++ /dev/null @@ -1,38 +0,0 @@ -# FastAPI-Server für 384-d Embeddings (all-MiniLM-L6-v2) -from __future__ import annotations -from fastapi import FastAPI, HTTPException -from pydantic import BaseModel -from typing import List, Optional -from sentence_transformers import SentenceTransformer - -app = FastAPI(title="mindnet-embed", version="1.0") - -MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2" # 384-d -_model: SentenceTransformer | None = None - -class EmbedIn(BaseModel): - model: Optional[str] = None - inputs: List[str] - -class EmbedOut(BaseModel): - embeddings: List[List[float]] - -@app.on_event("startup") -def _load_model(): - global _model - _model = SentenceTransformer(MODEL_NAME) - -@app.post("/embed", response_model=EmbedOut) -def embed(payload: EmbedIn) -> EmbedOut: - if _model is None: - raise HTTPException(status_code=503, detail="Model not loaded") - if not payload.inputs: - return EmbedOut(embeddings=[]) - vecs = _model.encode(payload.inputs, normalize_embeddings=False).tolist() - if any(len(v) != 384 for v in vecs): - raise HTTPException(status_code=500, detail="Embedding size mismatch (expected 384)") - return EmbedOut(embeddings=vecs) - -@app.get("/health") -def health(): - return {"ok": True, "model": MODEL_NAME, "dim": 384}