Lars/mindnet
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 21 Wiki Activity

app/embed_server.py aktualisiert
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 3s
Details

Browse Source
This commit is contained in:
Lars 2025-09-03 12:51:31 +02:00
parent d4e333325e
commit 3c0a406358
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
app/embed_server.py
View File

@ -1,4 +1,3 @@
# FastAPI-Server für 384-d Embeddings (all-MiniLM-L6-v2)
from __future__ import annotations from __future__ import annotations
from fastapi import FastAPI, HTTPException from fastapi import FastAPI, HTTPException
from pydantic import BaseModel from pydantic import BaseModel
@ -7,7 +6,7 @@ from sentence_transformers import SentenceTransformer
app = FastAPI(title="mindnet-embed", version="1.0") 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 _model: SentenceTransformer | None = None
class EmbedIn(BaseModel): class EmbedIn(BaseModel):
@ -22,6 +21,10 @@ def _load_model():
global _model global _model
_model = SentenceTransformer(MODEL_NAME) _model = SentenceTransformer(MODEL_NAME)
@app.get("/health")
def health():
return {"ok": True, "model": MODEL_NAME, "dim": 384}
@app.post("/embed", response_model=EmbedOut) @app.post("/embed", response_model=EmbedOut)
def embed(payload: EmbedIn) -> EmbedOut: def embed(payload: EmbedIn) -> EmbedOut:
if _model is None: if _model is None:
@ -32,7 +35,3 @@ def embed(payload: EmbedIn) -> EmbedOut:
if any(len(v) != 384 for v in vecs): if any(len(v) != 384 for v in vecs):
raise HTTPException(status_code=500, detail="Embedding size mismatch (expected 384)") raise HTTPException(status_code=500, detail="Embedding size mismatch (expected 384)")
return EmbedOut(embeddings=vecs) return EmbedOut(embeddings=vecs)
@app.get("/health")
def health():
return {"ok": True, "model": MODEL_NAME, "dim": 384}