mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-08 23:24:43 +02:00
ALI YESILKAYA
1c3128a319
* feat(stt): mémoire long-terme sémantique via Qdrant (5b) Serveur : longterm.py — collection Qdrant stt-memory (embeddings Qwen3 gpu-01, dim auto, Cosine), recall top-k injecté au prompt, remember des tours user. Tout dégrade proprement si Qdrant/embeddings injoignables (la mémoire court-terme tient). Env STT_MEMORY_LONGTERM, STT_QDRANT_URL, STT_EMBED_URL, STT_MEMORY_TOPK. Testé en process : dégradation OK (Qdrant down → mem=0, pas de crash, court-terme tient). Qdrant réparé le 17/06 (5c). Recherche sémantique réelle à valider sur cluster. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013FmcxGsyXZXogiAHQLjnZT * feat(stt): endpoint /v1/memory/health + upsert Qdrant synchrone - /v1/memory/health sonde activement embeddings + Qdrant + collection et expose les erreurs (recall/remember dégradent en silence → indébogables). Permet de diagnostiquer la mémoire long-terme sans kubectl exec. - remember() : upsert avec ?wait=true → le souvenir est immédiatement cherchable (sans wait, Qdrant met l'écriture en file → un recall cross-session immédiat pouvait le rater). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013FmcxGsyXZXogiAHQLjnZT --------- Co-authored-by: Claude <noreply@anthropic.com>
90 lines
2.8 KiB
Python
90 lines
2.8 KiB
Python
"""STT-server — API FastAPI pour les clients STT.
|
|
|
|
Endpoints :
|
|
GET /healthz → état du service
|
|
POST /v1/ask {text} → {reply} (requête AI, orchestrée vers LiteLLM)
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import httpx
|
|
from fastapi import FastAPI, HTTPException
|
|
from pydantic import BaseModel
|
|
|
|
from stt_server import __version__
|
|
from stt_server.brain import ask as brain_ask
|
|
from stt_server.config import settings
|
|
from stt_server.longterm import LongTermMemory
|
|
from stt_server.memory import SessionStore
|
|
|
|
app = FastAPI(title="STT-server", version=__version__)
|
|
sessions = SessionStore()
|
|
longterm = LongTermMemory() if settings.memory_longterm else None
|
|
|
|
|
|
class AskRequest(BaseModel):
|
|
text: str
|
|
model: str | None = None # alias LiteLLM ; défaut serveur si absent
|
|
session_id: str | None = None # mémoire court-terme : fil de conversation
|
|
|
|
|
|
class AskReply(BaseModel):
|
|
reply: str
|
|
model: str
|
|
|
|
|
|
@app.get("/healthz")
|
|
async def healthz() -> dict:
|
|
return {"status": "ok", "version": __version__}
|
|
|
|
|
|
@app.get("/v1/models")
|
|
async def v1_models() -> dict:
|
|
return {"default": settings.model, "available": settings.allowed_models}
|
|
|
|
|
|
@app.get("/v1/memory/health")
|
|
async def v1_memory_health() -> dict:
|
|
"""État de la mémoire long-terme (embeddings + Qdrant + collection), erreurs exposées."""
|
|
if not longterm:
|
|
return {"enabled": False}
|
|
return await longterm.health()
|
|
|
|
|
|
@app.post("/v1/reset")
|
|
async def v1_reset(req: AskRequest) -> dict:
|
|
if req.session_id:
|
|
sessions.reset(req.session_id)
|
|
return {"status": "reset"}
|
|
|
|
|
|
@app.post("/v1/ask", response_model=AskReply)
|
|
async def v1_ask(req: AskRequest) -> AskReply:
|
|
text = req.text.strip()
|
|
if not text:
|
|
raise HTTPException(status_code=400, detail="text vide")
|
|
model = req.model or settings.model
|
|
if model not in settings.allowed_models:
|
|
raise HTTPException(
|
|
status_code=400,
|
|
detail=f"modèle '{model}' non autorisé ; dispo : {settings.allowed_models}",
|
|
)
|
|
history = sessions.history(req.session_id) if req.session_id else None
|
|
memories = await longterm.recall(text) if longterm else None
|
|
try:
|
|
reply = await brain_ask(text, model, history, memories)
|
|
except httpx.HTTPError as e:
|
|
raise HTTPException(status_code=502, detail=f"upstream LiteLLM : {e}") from e
|
|
if req.session_id:
|
|
sessions.add(req.session_id, "user", text)
|
|
sessions.add(req.session_id, "assistant", reply)
|
|
if longterm:
|
|
await longterm.remember(req.session_id or "anon", text)
|
|
return AskReply(reply=reply, model=model)
|
|
|
|
|
|
def run() -> None:
|
|
"""Entrypoint `stt-server` (dev local). En prod : uvicorn via le conteneur."""
|
|
import uvicorn
|
|
|
|
uvicorn.run(app, host="0.0.0.0", port=8000) # noqa: S104 — service interne au cluster
|