apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-25 00:36:31 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

refactor: update image generation configuration to remove TPM references and clarify RPM usage in comments

Browse source
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-02-05 18:07:27 -08:00
parent 074e11be2c
commit 0d031cb2c2
2 changed files with 11 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

16
surfsense_backend/app/config/global_llm_config.example.yaml
View file

@ -208,8 +208,7 @@ global_image_generation_configs:
model_name: "dall-e-3"
api_key: "sk-your-openai-api-key-here"
api_base: ""
rpm: 50
tpm: 100000
rpm: 50 # Requests per minute (image gen is rate-limited by RPM, not tokens)
litellm_params: {}
# Example: OpenAI GPT Image 1
@ -221,7 +220,6 @@ global_image_generation_configs:
api_key: "sk-your-openai-api-key-here"
api_base: ""
rpm: 50
tpm: 100000
litellm_params: {}
# Example: Azure OpenAI DALL-E 3
@ -234,7 +232,6 @@ global_image_generation_configs:
api_base: "https://your-resource.openai.azure.com"
api_version: "2024-02-15-preview"
rpm: 50
tpm: 100000
litellm_params:
base_model: "dall-e-3"
@ -247,7 +244,6 @@ global_image_generation_configs:
# api_key: "your-openrouter-api-key-here"
# api_base: ""
# rpm: 30
# tpm: 50000
# litellm_params: {}
# Notes:
@ -262,17 +258,11 @@ global_image_generation_configs:
# - 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
#
# IMAGE GENERATION NOTES:
# - Image generation configs use the same ID scheme as LLM configs (negative for global)
# - Supported models: dall-e-2, dall-e-3, gpt-image-1 (OpenAI), azure/* (Azure),
# bedrock/* (AWS), vertex_ai/* (Google), recraft/* (Recraft), openrouter/* (OpenRouter)
# - The router uses litellm.aimage_generation() for async image generation
# - api_version is required for Azure image generation deployments
# - Only RPM (requests per minute) is relevant for image generation rate limiting.
# TPM (tokens per minute) does not apply since image APIs are billed/rate-limited per request, not per token.