wooo/ewoooc
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat(ai): 強化 ElephantAlpha NIM fallback
All checks were successful
CD Pipeline / deploy (push) Successful in 1m48s
Details

Browse Source
This commit is contained in:
OoO
2026-04-30 09:33:39 +08:00
parent 3949720998
commit 91ad98e621
7 changed files with 167 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.env.example
View File

@@ -107,12 +107,14 @@ HERMES_TIMEOUT=120
# Elephant Alpha AI Agent Super Orchestrator Settings
# ==========================================
# Description: Elephant Alpha (100B parameter model) for autonomous AI agent coordination
# Provider: OpenRouter AI
# Documentation: https://openrouter.ai/docs/quick-start
# Provider: NVIDIA NIM hosted OpenAI-compatible API
# Documentation: https://docs.nvidia.com/nim/large-language-models/latest/reference/api-reference.html
# OpenRouter API Configuration
# OpenRouter key 保留給舊流程；ElephantService 目前使用 NVIDIA_API_KEY。
OPENROUTER_API_KEY=sk-or-v1-your-openrouter-api-key-here
ELEPHANT_ALPHA_MODEL=openrouter/elephant-alpha
# NVIDIA NIM hosted model；Ultra 253B 可能需帳號權限，預設用已驗證可呼叫的 Super 49B。
ELEPHANT_ALPHA_MODEL=nvidia/llama-3.3-nemotron-super-49b-v1.5
ELEPHANT_ALPHA_FALLBACK_MODELS=nvidia/llama-3.3-nemotron-super-49b-v1.5,nvidia/llama-3.1-nemotron-70b-instruct,meta/llama-3.1-8b-instruct
# Elephant Alpha Behavior Configuration
ELEPHANT_ALPHA_CONFIDENCE_THRESHOLD=0.7