SurfSense/surfsense_backend/app/config/global_llm_config.example.yaml
2026-02-02 11:36:54 -08:00

204 lines
7.8 KiB
YAML

# Global LLM Configuration
#
# SETUP INSTRUCTIONS:
# 1. For production: Copy this file to global_llm_config.yaml and add your real API keys
# 2. For testing: The system will use this example file automatically if global_llm_config.yaml doesn't exist
#
# NOTE: The example API keys below are placeholders and won't work.
# Replace them with your actual API keys to enable global configurations.
#
# These configurations will be available to all users as a convenient option
# Users can choose to use these global configs or add their own
#
# AUTO MODE (Recommended):
# - Auto mode (ID: 0) uses LiteLLM Router to automatically load balance across all global configs
# - This helps avoid rate limits by distributing requests across multiple providers
# - New users are automatically assigned Auto mode by default
# - Configure router_settings below to customize the load balancing behavior
#
# Structure matches NewLLMConfig:
# - LLM model configuration (provider, model_name, api_key, etc.)
# - Prompt configuration (system_instructions, citations_enabled)
# Router Settings for Auto Mode
# These settings control how the LiteLLM Router distributes requests across models
router_settings:
# Routing strategy options:
# - "usage-based-routing": Routes to deployment with lowest current usage (recommended for rate limits)
# - "simple-shuffle": Random distribution with optional RPM/TPM weighting
# - "least-busy": Routes to least busy deployment
# - "latency-based-routing": Routes based on response latency
routing_strategy: "usage-based-routing"
# Number of retries before failing
num_retries: 3
# Number of failures allowed before cooling down a deployment
allowed_fails: 3
# Cooldown time in seconds after allowed_fails is exceeded
cooldown_time: 60
# Fallback models (optional) - when primary fails, try these
# Format: [{"primary_model": ["fallback1", "fallback2"]}]
# fallbacks: []
global_llm_configs:
# Example: OpenAI GPT-4 Turbo with citations enabled
- id: -1
name: "Global GPT-4 Turbo"
description: "OpenAI's GPT-4 Turbo with default prompts and citations"
provider: "OPENAI"
model_name: "gpt-4-turbo-preview"
api_key: "sk-your-openai-api-key-here"
api_base: ""
# Rate limits for load balancing (requests/tokens per minute)
rpm: 500 # Requests per minute
tpm: 100000 # Tokens per minute
litellm_params:
temperature: 0.7
max_tokens: 4000
# Prompt Configuration
system_instructions: "" # Empty = use default SURFSENSE_SYSTEM_INSTRUCTIONS
use_default_system_instructions: true
citations_enabled: true
# Example: Anthropic Claude 3 Opus
- id: -2
name: "Global Claude 3 Opus"
description: "Anthropic's most capable model with citations"
provider: "ANTHROPIC"
model_name: "claude-3-opus-20240229"
api_key: "sk-ant-your-anthropic-api-key-here"
api_base: ""
rpm: 1000
tpm: 100000
litellm_params:
temperature: 0.7
max_tokens: 4000
system_instructions: ""
use_default_system_instructions: true
citations_enabled: true
# Example: Fast model - GPT-3.5 Turbo (citations disabled for speed)
- id: -3
name: "Global GPT-3.5 Turbo (Fast)"
description: "Fast responses without citations for quick queries"
provider: "OPENAI"
model_name: "gpt-3.5-turbo"
api_key: "sk-your-openai-api-key-here"
api_base: ""
rpm: 3500 # GPT-3.5 has higher rate limits
tpm: 200000
litellm_params:
temperature: 0.5
max_tokens: 2000
system_instructions: ""
use_default_system_instructions: true
citations_enabled: false # Disabled for faster responses
# Example: Chinese LLM - DeepSeek with custom instructions
- id: -4
name: "Global DeepSeek Chat (Chinese)"
description: "DeepSeek optimized for Chinese language responses"
provider: "DEEPSEEK"
model_name: "deepseek-chat"
api_key: "your-deepseek-api-key-here"
api_base: "https://api.deepseek.com/v1"
rpm: 60
tpm: 100000
litellm_params:
temperature: 0.7
max_tokens: 4000
# Custom system instructions for Chinese responses
system_instructions: |
<system_instruction>
You are SurfSense, a reasoning and acting AI agent designed to answer user questions using the user's personal knowledge base.
Today's date (UTC): {resolved_today}
IMPORTANT: Please respond in Chinese (简体中文) unless the user specifically requests another language.
</system_instruction>
use_default_system_instructions: false
citations_enabled: true
# Example: Azure OpenAI GPT-4o
# IMPORTANT: For Azure deployments, always include 'base_model' in litellm_params
# to enable accurate token counting, cost tracking, and max token limits
- id: -5
name: "Global Azure GPT-4o"
description: "Azure OpenAI GPT-4o deployment"
provider: "AZURE"
# model_name format for Azure: azure/<your-deployment-name>
model_name: "azure/gpt-4o-deployment"
api_key: "your-azure-api-key-here"
api_base: "https://your-resource.openai.azure.com"
api_version: "2024-02-15-preview" # Azure API version
rpm: 1000
tpm: 150000
litellm_params:
temperature: 0.7
max_tokens: 4000
# REQUIRED for Azure: Specify the underlying OpenAI model
# This fixes "Could not identify azure model" warnings
# Common base_model values: gpt-4, gpt-4-turbo, gpt-4o, gpt-4o-mini, gpt-3.5-turbo
base_model: "gpt-4o"
system_instructions: ""
use_default_system_instructions: true
citations_enabled: true
# Example: Azure OpenAI GPT-4 Turbo
- id: -6
name: "Global Azure GPT-4 Turbo"
description: "Azure OpenAI GPT-4 Turbo deployment"
provider: "AZURE"
model_name: "azure/gpt-4-turbo-deployment"
api_key: "your-azure-api-key-here"
api_base: "https://your-resource.openai.azure.com"
api_version: "2024-02-15-preview"
rpm: 500
tpm: 100000
litellm_params:
temperature: 0.7
max_tokens: 4000
base_model: "gpt-4-turbo" # Maps to gpt-4-turbo-preview
system_instructions: ""
use_default_system_instructions: true
citations_enabled: true
# Example: Groq - Fast inference
- id: -7
name: "Global Groq Llama 3"
description: "Ultra-fast Llama 3 70B via Groq"
provider: "GROQ"
model_name: "llama3-70b-8192"
api_key: "your-groq-api-key-here"
api_base: ""
rpm: 30 # Groq has lower rate limits on free tier
tpm: 14400
litellm_params:
temperature: 0.7
max_tokens: 8000
system_instructions: ""
use_default_system_instructions: true
citations_enabled: true
# Notes:
# - ID 0 is reserved for "Auto" mode - uses LiteLLM Router for load balancing
# - Use negative IDs to distinguish global configs from user configs (NewLLMConfig in DB)
# - IDs should be unique and sequential (e.g., -1, -2, -3, etc.)
# - The 'api_key' field will not be exposed to users via API
# - system_instructions: Custom prompt or empty string to use defaults
# - use_default_system_instructions: true = use SURFSENSE_SYSTEM_INSTRUCTIONS when system_instructions is empty
# - citations_enabled: true = include citation instructions, false = include anti-citation instructions
# - All standard LiteLLM providers are supported
# - rpm/tpm: Optional rate limits for load balancing (requests/tokens per minute)
# These help the router distribute load evenly and avoid rate limit errors
#
# AZURE-SPECIFIC NOTES:
# - Always add 'base_model' in litellm_params for Azure deployments
# - This fixes "Could not identify azure model 'X'" warnings
# - base_model should match the underlying OpenAI model (e.g., gpt-4o, gpt-4-turbo, gpt-3.5-turbo)
# - model_name format: "azure/<your-deployment-name>"
# - api_version: Use a recent Azure API version (e.g., "2024-02-15-preview")
# - See: https://docs.litellm.ai/docs/proxy/cost_tracking#spend-tracking-for-azure-openai-models