apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-06-28 21:49:40 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat(database-migrations): add migration to remove legacy model config tables and remove stale model connection code

Browse source
This commit is contained in:
Anish Sarkar 2026-06-13 12:45:43 +05:30
parent 50668775f8
commit bd4a04f2e7
93 changed files with 956 additions and 11442 deletions
Download patch file Download diff file Expand all files Collapse all files

50
surfsense_backend/app/config/__init__.py
View file

@ -119,7 +119,7 @@ def load_global_llm_configs():
else:
seen_slugs[slug] = cfg.get("id", 0)
# Stamp Auto (Fastest) ranking metadata. YAML configs are always
# Stamp Auto ranking metadata. YAML configs are always
# Tier A — operator-curated, locked first when premium-eligible.
# The OpenRouter refresh tick later re-stamps health for any cfg
# whose provider == "openrouter" via _enrich_health.
@ -210,42 +210,6 @@ def load_global_image_gen_configs():
return []
def load_global_vision_llm_configs():
data = _global_config_data()
if not data:
return []
try:
configs = copy.deepcopy(data.get("global_vision_llm_configs", []) or [])
for cfg in configs:
if isinstance(cfg, dict):
cfg.setdefault("billing_tier", "free")
return configs
except Exception as e:
print(f"Warning: Failed to load global vision LLM configs: {e}")
return []
def load_vision_llm_router_settings():
default_settings = {
"routing_strategy": "usage-based-routing",
"num_retries": 3,
"allowed_fails": 3,
"cooldown_time": 60,
}
data = _global_config_data()
if not data:
return default_settings
try:
settings = data.get("vision_llm_router_settings", {})
return {**default_settings, **settings}
except Exception as e:
print(f"Warning: Failed to load vision LLM router settings: {e}")
return default_settings
def load_image_gen_router_settings():
"""
Load router settings for image generation Auto mode from YAML file.
@ -482,12 +446,6 @@ def initialize_image_gen_router():
print(f"Warning: Failed to initialize Image Generation Router: {e}")
def initialize_vision_llm_router():
# Retired: vision Auto now uses shared capability-filtered model selection
# over GLOBAL/BYOK chat models with supports_image_input=true.
return
class Config:
# Check if ffmpeg is installed
if not is_ffmpeg_installed():
@ -869,12 +827,6 @@ class Config:
# Router settings for Image Generation Auto mode
IMAGE_GEN_ROUTER_SETTINGS = load_image_gen_router_settings()
# Global Vision LLM Configurations (optional)
GLOBAL_VISION_LLM_CONFIGS = load_global_vision_llm_configs()
# Router settings for Vision LLM Auto mode
VISION_LLM_ROUTER_SETTINGS = load_vision_llm_router_settings()
# Virtual GLOBAL connection/model catalog. This is server-only metadata
# derived from global_llm_config.yaml; GLOBAL keys are not stored in DB.
from app.services.global_model_catalog import (

80
surfsense_backend/app/config/global_llm_config.example.yaml
View file

@ -433,87 +433,11 @@ global_image_generation_configs:
# rpm: 30
# litellm_params: {}
# =============================================================================
# Vision LLM Configuration
# =============================================================================
# These configurations power the vision autocomplete feature (screenshot analysis).
# Only vision-capable models should be used here (e.g. GPT-4o, Gemini Pro, Claude 3).
# Supported providers: OpenAI, Anthropic, Google, Azure OpenAI, Vertex AI, Bedrock,
# xAI, OpenRouter, Ollama, Groq, Together AI, Fireworks AI, DeepSeek, Mistral, Custom
#
# Auto mode (ID 0) uses LiteLLM Router for load balancing across all vision configs.
# Router Settings for Vision LLM Auto Mode
vision_llm_router_settings:
routing_strategy: "usage-based-routing"
num_retries: 3
allowed_fails: 3
cooldown_time: 60
global_vision_llm_configs:
# Example: OpenAI GPT-4o (recommended for vision)
- id: -1001
name: "Global GPT-4o Vision"
description: "OpenAI's GPT-4o with strong vision capabilities"
litellm_provider: "openai"
model_name: "gpt-4o"
api_key: "sk-your-openai-api-key-here"
api_base: "https://api.openai.com/v1"
rpm: 500
tpm: 100000
litellm_params:
temperature: 0.3
max_tokens: 1000
# Example: Google Gemini 2.0 Flash
- id: -1002
name: "Global Gemini 2.0 Flash"
description: "Google's fast vision model with large context"
litellm_provider: "gemini"
model_name: "gemini-2.0-flash"
api_key: "your-google-ai-api-key-here"
api_base: "https://generativelanguage.googleapis.com/v1beta"
rpm: 1000
tpm: 200000
litellm_params:
temperature: 0.3
max_tokens: 1000
# Example: Anthropic Claude 3.5 Sonnet
- id: -1003
name: "Global Claude 3.5 Sonnet Vision"
description: "Anthropic's Claude 3.5 Sonnet with vision support"
litellm_provider: "anthropic"
model_name: "claude-3-5-sonnet-20241022"
api_key: "sk-ant-your-anthropic-api-key-here"
api_base: "https://api.anthropic.com/v1"
rpm: 1000
tpm: 100000
litellm_params:
temperature: 0.3
max_tokens: 1000
# Example: Azure OpenAI GPT-4o
# - id: -1004
# name: "Global Azure GPT-4o Vision"
# description: "Azure-hosted GPT-4o for vision analysis"
# litellm_provider: "azure"
# 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"
# rpm: 500
# tpm: 100000
# litellm_params:
# temperature: 0.3
# max_tokens: 1000
# base_model: "gpt-4o"
# Notes:
# - ID 0 is reserved for "Auto" mode - uses LiteLLM Router for load balancing
# - Use negative IDs to distinguish global models from BYOK/local DB models
# - IDs must be unique across chat, vision, and image generation configs
# - Suggested static ranges: chat -1..-999, vision -1001..-1999, image -2001..-2999
# - IDs must be unique across chat and image generation configs
# - Suggested static ranges: chat -1..-999, image -2001..-2999
# - 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