neue Version mit Wartezeit bei externen LLM Fehler
This commit is contained in:
1 parent
c9cf1b7e4c
commit
ecfdc67485
2 files changed
+93
-88
No files matched your search
+14
-12
@@ -2,8 +2,8 @@
|
||||
FILE: app/config.py
|
||||
DESCRIPTION: Zentrale Pydantic-Konfiguration.
|
||||
WP-20: Hybrid-Cloud Modus Support (OpenRouter/Gemini/Ollama).
|
||||
FIX: Update auf Gemini 2.5 Serie & Optimierung für Gemma 2 Durchsatz.
|
||||
VERSION: 0.6.6
|
||||
FIX: Einführung von Parametern zur intelligenten Rate-Limit Steuerung (429 Handling).
|
||||
VERSION: 0.6.7
|
||||
STATUS: Active
|
||||
DEPENDENCIES: os, functools, pathlib, python-dotenv
|
||||
"""
|
||||
@@ -27,32 +27,36 @@ class Settings:
|
||||
VECTOR_SIZE: int = int(os.getenv("VECTOR_DIM", "768"))
|
||||
DISTANCE: str = os.getenv("MINDNET_DISTANCE", "Cosine")
|
||||
|
||||
# --- Lokale Embeddings ---
|
||||
# --- Lokale Embeddings (Ollama & Sentence-Transformers) ---
|
||||
EMBEDDING_MODEL: str = os.getenv("MINDNET_EMBEDDING_MODEL", "nomic-embed-text")
|
||||
MODEL_NAME: str = os.getenv("MINDNET_MODEL", "sentence-transformers/all-MiniLM-L6-v2")
|
||||
|
||||
# --- WP-20 Hybrid LLM Provider ---
|
||||
# "openrouter" ist primär für den Ingest-Turbo mit Gemma 2 empfohlen.
|
||||
# Erlaubt: "ollama" | "gemini" | "openrouter"
|
||||
MINDNET_LLM_PROVIDER: str = os.getenv("MINDNET_LLM_PROVIDER", "openrouter").lower()
|
||||
|
||||
# Google AI Studio (Fallback auf 2.5-Serie)
|
||||
# Google AI Studio (2025er Lite-Modell für höhere Kapazität)
|
||||
GOOGLE_API_KEY: str | None = os.getenv("GOOGLE_API_KEY")
|
||||
# "gemini-2.5-flash-lite" ist die skalierbare 2025-Alternative für hohe Last.
|
||||
GEMINI_MODEL: str = os.getenv("MINDNET_GEMINI_MODEL", "gemini-2.5-flash-lite")
|
||||
|
||||
# OpenRouter Integration (openai/gpt-oss-20b:free oder gemma-2)
|
||||
# OpenRouter Integration (Verfügbares Free-Modell 2025)
|
||||
OPENROUTER_API_KEY: str | None = os.getenv("OPENROUTER_API_KEY")
|
||||
# "google/gemma-2-9b-it:free" bietet hohe Kapazität bei Kostenfreiheit.
|
||||
OPENROUTER_MODEL: str = os.getenv("OPENROUTER_MODEL", "google/gemma-2-9b-it:free")
|
||||
OPENROUTER_MODEL: str = os.getenv("OPENROUTER_MODEL", "mistralai/mistral-7b-instruct:free")
|
||||
|
||||
LLM_FALLBACK_ENABLED: bool = os.getenv("MINDNET_LLM_FALLBACK", "true").lower() == "true"
|
||||
|
||||
# --- NEU: Intelligente Rate-Limit Steuerung ---
|
||||
# Dauer der Wartezeit in Sekunden, wenn ein HTTP 429 (Rate Limit) auftritt
|
||||
LLM_RATE_LIMIT_WAIT: float = float(os.getenv("MINDNET_LLM_RATE_LIMIT_WAIT", "60.0"))
|
||||
# Anzahl der Cloud-Retries bei 429, bevor Ollama-Fallback greift
|
||||
LLM_RATE_LIMIT_RETRIES: int = int(os.getenv("MINDNET_LLM_RATE_LIMIT_RETRIES", "3"))
|
||||
|
||||
# --- WP-05 Lokales LLM (Ollama) ---
|
||||
OLLAMA_URL: str = os.getenv("MINDNET_OLLAMA_URL", "http://127.0.0.1:11434")
|
||||
LLM_MODEL: str = os.getenv("MINDNET_LLM_MODEL", "phi3:mini")
|
||||
PROMPTS_PATH: str = os.getenv("MINDNET_PROMPTS_PATH", "config/prompts.yaml")
|
||||
|
||||
# --- Performance & Last-Steuerung ---
|
||||
# --- WP-06 / WP-14 Performance & Last-Steuerung ---
|
||||
LLM_TIMEOUT: float = float(os.getenv("MINDNET_LLM_TIMEOUT", "300.0"))
|
||||
DECISION_CONFIG_PATH: str = os.getenv("MINDNET_DECISION_CONFIG", "config/decision_engine.yaml")
|
||||
BACKGROUND_LIMIT: int = int(os.getenv("MINDNET_LLM_BACKGROUND_LIMIT", "2"))
|
||||
@@ -62,8 +66,6 @@ class Settings:
|
||||
MINDNET_VAULT_ROOT: str = os.getenv("MINDNET_VAULT_ROOT", "./vault_master")
|
||||
MINDNET_TYPES_FILE: str = os.getenv("MINDNET_TYPES_FILE", "config/types.yaml")
|
||||
MINDNET_VOCAB_PATH: str = os.getenv("MINDNET_VOCAB_PATH", "/mindnet/vault/mindnet/_system/dictionary/edge_vocabulary.md")
|
||||
|
||||
# WP-22: 'full' für Multi-Hash Change Detection
|
||||
CHANGE_DETECTION_MODE: str = os.getenv("MINDNET_CHANGE_DETECTION_MODE", "full")
|
||||
|
||||
# --- WP-04 Retriever Gewichte ---
|
||||
|
||||
Reference in new issue
Block a user