From 32227991df477887a7fee66b20aed74f0e1127a9 Mon Sep 17 00:00:00 2001 From: sakhiy Date: Wed, 27 May 2026 01:03:21 +0000 Subject: [PATCH] Config baru: groq, openrouter, github doang (3 tier) --- .env.example | 28 ++++++------------------ README.md | 6 +++--- config.yaml | 61 ++++++++++++++-------------------------------------- 3 files changed, 25 insertions(+), 70 deletions(-) diff --git a/.env.example b/.env.example index a9a768e..01075b1 100644 --- a/.env.example +++ b/.env.example @@ -1,30 +1,14 @@ # AI PROXY CONFIG # Copy file ini ke .env dan isi API key masing-masing -# Gemini (Tier 1 - main) -GEMINI_API_KEY_1= -GEMINI_API_KEY_2= -GEMINI_API_KEY_3= -GEMINI_API_KEY_4= -GEMINI_API_KEY_5= - -# GitHub Models (Tier 2 - fallback) -GITHUB_TOKEN_1= -GITHUB_TOKEN_2= - -# Groq (Tier 3 - emergency) -GROQ_API_KEY_1= -GROQ_API_KEY_2= - -# OpenRouter (free tier) +# OpenRouter (Tier 1) OPENROUTER_API_KEY_1= -OPENROUTER_API_KEY_2= -OPENROUTER_API_KEY_3= -# Others -DEEPSEEK_API_KEY= -TOGETHER_API_KEY= -HUGGINGFACE_API_KEY= +# Groq (Tier 2) +GROQ_API_KEY_1= + +# GitHub Models (Tier 3) +GITHUB_TOKEN_1= # LiteLLM Admin LITELLM_MASTER_KEY= diff --git a/README.md b/README.md index 475fcad..1760a6d 100644 --- a/README.md +++ b/README.md @@ -60,9 +60,9 @@ curl http://localhost:4000/v1/chat/completions \ | Tier | Model Name | Provider | Akun | Fungsi | |------|-----------|----------|------|--------| -| 1 | `hermes-engine` | Gemini 2.5 Flash | 5 | Main — load balanced otomatis | -| 2 | `tier2-fallback` | GPT-4o Mini (GitHub) | 2 | Cadangan kalo Gemini error semua | -| 3 | `tier3-emergency` | Llama 3 70B (Groq) | 2 | Darurat kalo semua tier error | +| 1 | `primary` | GPT-4o Mini (OpenRouter) | 1 | Main | +| 2 | `secondary` | Llama 3.3 70B (Groq) | 1 | Fallback pertama | +| 3 | `tertiary` | GPT-4o Mini (GitHub) | 1 | Fallback terakhir | ## Port diff --git a/config.yaml b/config.yaml index 6fd8607..10e685c 100644 --- a/config.yaml +++ b/config.yaml @@ -1,59 +1,30 @@ model_list: - # --- TIER 1: GEMINI (5 Akun Load Balancing) --- - - model_name: hermes-engine + # --- TIER 1: OPENROUTER (Free) --- + - model_name: primary litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY_1 - tpm_fallback: true - - model_name: hermes-engine - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY_2 - tpm_fallback: true - - model_name: hermes-engine - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY_3 - tpm_fallback: true - - model_name: hermes-engine - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY_4 - tpm_fallback: true - - model_name: hermes-engine - litellm_params: - model: gemini/gemini-2.5-flash - api_key: os.environ/GEMINI_API_KEY_5 - tpm_fallback: true + model: openrouter/openai/gpt-4o-mini + api_key: os.environ/OPENROUTER_API_KEY_1 - # --- TIER 2: GITHUB MODELS (2 Akun Cadangan) --- - - model_name: tier2-fallback + # --- TIER 2: GROQ (Free) --- + - model_name: secondary + litellm_params: + model: groq/llama-3.3-70b-versatile + api_key: os.environ/GROQ_API_KEY_1 + + # --- TIER 3: GITHUB MODELS (via token) --- + - model_name: tertiary litellm_params: model: github/gpt-4o-mini api_key: os.environ/GITHUB_TOKEN_1 - - model_name: tier2-fallback - litellm_params: - model: github/gpt-4o-mini - api_key: os.environ/GITHUB_TOKEN_2 - - # --- TIER 3: GROQ (2 Akun Darurat) --- - - model_name: tier3-emergency - litellm_params: - model: groq/llama3-70b-8192 - api_key: os.environ/GROQ_API_KEY_1 - - model_name: tier3-emergency - litellm_params: - model: groq/llama3-70b-8192 - api_key: os.environ/GROQ_API_KEY_2 router_settings: routing_strategy: simple-shuffle fallbacks: - - hermes-engine: - - tier2-fallback - - tier3-emergency + primary: + - secondary + - tertiary retry_after: 0 num_retries: 2 timeout: 60 - allowed_fails: 1 + allowed_fails: 2 cooldown_time: 60