From 3c0a40635869247ebdc0bec1d1b729dd43002c8d Mon Sep 17 00:00:00 2001 From: Lars Date: Wed, 3 Sep 2025 12:51:31 +0200 Subject: [PATCH] app/embed_server.py aktualisiert --- app/embed_server.py | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/app/embed_server.py b/app/embed_server.py index ec9f6e9..15b01fe 100644 --- a/app/embed_server.py +++ b/app/embed_server.py @@ -1,4 +1,3 @@ -# FastAPI-Server für 384-d Embeddings (all-MiniLM-L6-v2) from __future__ import annotations from fastapi import FastAPI, HTTPException from pydantic import BaseModel @@ -7,7 +6,7 @@ from sentence_transformers import SentenceTransformer app = FastAPI(title="mindnet-embed", version="1.0") -MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2" # 384-d +MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2" # 384-dim _model: SentenceTransformer | None = None class EmbedIn(BaseModel): @@ -22,6 +21,10 @@ def _load_model(): global _model _model = SentenceTransformer(MODEL_NAME) +@app.get("/health") +def health(): + return {"ok": True, "model": MODEL_NAME, "dim": 384} + @app.post("/embed", response_model=EmbedOut) def embed(payload: EmbedIn) -> EmbedOut: if _model is None: @@ -32,7 +35,3 @@ def embed(payload: EmbedIn) -> EmbedOut: 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}