From eae09a84b31dd705ec6ae48659a53de867ac4232 Mon Sep 17 00:00:00 2001
From: Lars <Lars@stommer.de>
Date: Wed, 3 Sep 2025 12:29:42 +0200
Subject: [PATCH] =?UTF-8?q?app/embed=5Fserver.py=20hinzugef=C3=BCgt?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 app/embed_server.py | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)
 create mode 100644 app/embed_server.py

diff --git a/app/embed_server.py b/app/embed_server.py
new file mode 100644
index 0000000..ec9f6e9
--- /dev/null
+++ b/app/embed_server.py
@@ -0,0 +1,38 @@
+# 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}