mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-09 01:24:42 +02:00
6e4a81e20a
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
42 lines
1.4 KiB
Python
42 lines
1.4 KiB
Python
"""Orchestration AI : route les requêtes des clients vers LiteLLM (s01).
|
|
|
|
LiteLLM (:4000) est OpenAI-compatible et route lui-même vers Qwen3 (g01) ou Claude
|
|
selon l'alias `hermes-default` / `hermes-switch`. L'intégration des outils Hermes
|
|
(« agir sur Funk » via le gateway :8080) est une étape ultérieure.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import httpx
|
|
|
|
from stt_server.config import settings
|
|
|
|
|
|
async def ask(
|
|
text: str,
|
|
model: str | None = None,
|
|
history: list[dict] | None = None,
|
|
memories: list[str] | None = None,
|
|
) -> str:
|
|
system = settings.system_prompt
|
|
if memories:
|
|
souvenirs = "\n".join(f"- {m}" for m in memories)
|
|
system += (
|
|
"\n\nÉléments de mémoire long-terme (peuvent aider, ignore si hors-sujet) :\n"
|
|
+ souvenirs
|
|
)
|
|
messages = [{"role": "system", "content": system}]
|
|
if history:
|
|
messages += history
|
|
messages.append({"role": "user", "content": text})
|
|
payload = {
|
|
"model": model or settings.model,
|
|
"messages": messages,
|
|
"max_tokens": settings.max_tokens,
|
|
"temperature": settings.temperature,
|
|
}
|
|
headers = {"Authorization": f"Bearer {settings.litellm_key}"}
|
|
async with httpx.AsyncClient(timeout=settings.request_timeout) as client:
|
|
r = await client.post(settings.litellm_url, json=payload, headers=headers)
|
|
r.raise_for_status()
|
|
return r.json()["choices"][0]["message"]["content"].strip()
|