error after last update (docker) #32
Comments
|
This is an API error, not a uni-api error. |
|
so why uni-ani not try to use next API if it faces problem one? |
|
Please provide the uni-api configuration file for me to check. (Remember to remove sensitive information). |
|
Docker logs: INFO: Will watch for changes in these directories: ['/home']
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
INFO: Started reloader process [1] using WatchFiles
INFO: Started server process [8]
INFO: Waiting for application startup.
INFO: Application startup complete.
2024-11-05 19:03:23,791 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:24,426 - uni-api - WARNING - API key sk-********** 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:24,427 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:24,427 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:25,074 - uni-api - WARNING - API key sk-*************** 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:25,075 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:25,075 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:25,692 - uni-api - WARNING - API key sk-************** 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:25,692 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:25,693 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:26,044 - uni-api - WARNING - API key sk-************** 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:26,044 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:26,044 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:26,731 - uni-api - WARNING - API key sk-************* 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:26,732 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:26,732 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:27,369 - uni-api - WARNING - API key sk-************ 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:27,369 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:27,369 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:28,110 - uni-api - WARNING - API key sk-************ 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:28,110 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:28,110 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:28,780 - uni-api - WARNING - API key sk-************** 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:28,780 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:28,780 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:29,450 - uni-api - WARNING - API key sk-************* 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:29,451 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:29,451 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:30,152 - uni-api - WARNING - API key sk-************* 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:30,152 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:30,153 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:30,888 - uni-api - WARNING - API key sk-************ 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:30,888 - uni-api - ERROR - Error 500 with provider gpt-god: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
2024-11-05 19:03:30,888 - uni-api - INFO - provider: gpt-god model: gpt-4o-mini engine: gpt
2024-11-05 19:03:30,888 - uni-api - WARNING - All API keys are rate limited!
2024-11-05 19:03:30,888 - uni-api - WARNING - API key sk-***************** 已进入冷却状态，冷却时间 60 秒
2024-11-05 19:03:30,888 - uni-api - ERROR - Error 429 with provider gpt-god: Too many requests
INFO: 10.60.0.2:40450 - "POST /v1/chat/completions HTTP/1.1" 429 Too Many Requests
providers:
- provider: openrouter
base_url: https://openrouter.ai/api/v1/chat/completions
api: sk-or-v1-*********
model:
- 'liquid/lfm-40b:free': lfm-40b
- 'meta-llama/llama-3-8b-instruct:free': llama-3-8b-instruct
- 'meta-llama/llama-3.1-8b-instruct:free': llama-3.1-8b-instruct
- 'meta-llama/llama-3.1-70b-instruct:free': llama-3.1-70b-instruct
- 'meta-llama/llama-3.1-405b-instruct:free': llama-3.1-405b-instruct
- 'meta-llama/llama-3.2-1b-instruct:free': llama-3.2-1b-instruct
- 'meta-llama/llama-3.2-3b-instruct:free': llama-3.2-3b-instruct
- 'meta-llama/llama-3.2-11b-vision-instruct:free': llama-3.2-11b-vision-instruct
- 'meta-llama/llama-3.2-90b-vision-instruct:free': llama-3.2-90b-vision-instruct
- 'nousresearch/hermes-3-llama-3.1-405b:free': hermes-3-llama-3.1-405b
- 'google/gemma-2-9b-it:free': gemma-2-9b-it
- 'google/gemini-flash-1.5-8b-exp': gemini-1.5-flash-8b
- 'google/gemini-flash-1.5-exp': gemini-1.5-flash
- 'google/gemini-pro-1.5-exp': gemini-1.5-pro
- 'qwen/qwen-2-7b-instruct:free': qwen-2-7b-instruct
- 'mistralai/mistral-7b-instruct:free': mistral-7b-instruct
- 'microsoft/phi-3-mini-128k-instruct:free': phi-3-mini-128k-instruct
- 'microsoft/phi-3-medium-128k-instruct:free': phi-3-medium-128k-instruct
- 'gryphe/mythomist-7b:free': mythomist-7b
- 'openchat/openchat-7b:free': openchat-7b
- 'undi95/toppy-m-7b:free': toppy-m-7b
- 'huggingfaceh4/zephyr-7b-beta:free': zephyr-7b-beta
- 'gryphe/mythomax-l2-13b:free': mythomax-l2-13b
- 'openai/shap-e': shap-e
tools: true
engine: openrouter
preferences:
api_key_rate_limit:
gemini-1.5-pro: 2/min,50/day
gemini-1.5-flash: 15/min,200/day
gemini-1.5-flash-8b: 15/min,200/day
default: 20/min,200/day
api_key_cooldown_period: 60
- provider: groq
base_url: https://api.groq.com/openai/v1/chat/completions
api: gsk_******************
model:
- distil-whisper-large-v3-en
- gemma2-9b-it
- gemma-7b-it
- llama3-groq-70b-8192-tool-use-preview
- llama3-groq-8b-8192-tool-use-preview
- llama-3.1-70b-versatile
- llama-3.1-8b-instant
- llama-3.2-1b-preview
- llama-3.2-3b-preview
- llama-3.2-11b-vision-preview
- llama-3.2-90b-vision-preview
- llama-guard-3-8b
- llama3-70b-8192
- llama3-8b-8192
- mixtral-8x7b-32768
- whisper-large-v3
- whisper-large-v3-turbo
tools: true
preferences:
api_key_rate_limit:
llama-3.2-90b-vision-preview: 15/min,3500/day
llama-3.2-11b-text-preview: 30/min,7000/day
llama-3.2-11b-vision-preview: 30/min,7000/day
llama-3.2-1b-preview: 30/min,7000/day
llama-3.2-3b-preview: 30/min,7000/day
llama-3.2-90b-text-preview: 30/min,7000/day
default: 30/min,14400/day
api_key_cooldown_period: 60
- provider: gemini
base_url: https://generativelanguage.googleapis.com/v1beta
api: ********************
model:
- gemini-1.0-pro
- gemini-1.5-pro
- gemini-1.5-flash
- gemini-1.5-flash-8b
- text-embedding-004
tools: true
engine: gemini
preferences:
api_key_rate_limit:
gemini-1.5-pro: 2/min,50/day
text-embedding-004: 1500/min
default: 15/min,1500/day
api_key_cooldown_period: 60
- provider: cloudflare
api: **************
cf_account_id: ***************
model:
- '@cf/meta/llama-3.1-8b-instruct': llama-3.1-8b
- '@cf/meta/llama-3.1-8b-instruct'
preferences:
api_key_rate_limit: 100000/day
api_key_cooldown_period: 60
- provider: gpt-god
base_url: https://api.gptgod.online/v1/chat/completions
api:
- sk-**********
- sk-*********
- sk-**********
- sk-************
- sk-*********
- sk-*************
- sk-**********
- sk-*************
- sk-********
- sk-******
- sk-***********
model:
- batch-get-gpts
- claude-1-100k
- claude-1.3
- claude-1.3-100k
- claude-3-haiku-20240307
- cogvideox-result
- code-llama-13b
- code-llama-34b
- code-llama-7b
- codellama-70b-instruct
- dbrx-instruct
- deepseek-chat
- deepseek-coder
- flux
- flux-chat
- flux-result
- flame-2-13b
- flame-2-70b
- flame-3-70b
- flame-3-8b
- flame-3.1-70b
- flame-3.1-8b
- gemma-2b-it
- get-gpts
- gglm-3-turbo
- gglm-4-flash
- gglm-4-on
- gpt-3.5-turbo
- gpt-3.5-turbo-16k
- gpt-4o-mini
- chatgpt-4o-latest
- gpt-4o
- gpt-4o-2024-05-13
- gpt-4o-2024-08-06
- gpt-4o-all
- google-palm
- kling-task
- llama-2-7b
- llama-3-sonar-large-32k-chat
- llama-3-sonar-large-32k-online
- llama-3-sonar-small-32k-chat
- llama-3-sonar-small-32k-online
- llava-v1.5-7b-wrapper
- luma-pro-task
- luma-task
- luma-vip-task
- long-pocket
- mixtral-8x22b
- mixtral-8x7b
- mixtral-8x7b-instruct
- playground-v2.5
- runway-video-task
- runway-vip-video-task
- search-gpts
- search-gpts-chat
- stable-diffusion
- stable-diffusion-3-2b
- suno-concat
- text-embedding-3-large
- text-embedding-3-small
- text-embedding-ada-002
- twin-1.5-pro-001
- twin-1.5-pro-002
- vidu-task-get
- whisper-1
tools: true
preferences:
api_key_rate_limit:
chatgpt-4o-latest: 6/min,60/day
gpt-4o: 6/min,60/day
gpt-4o-2024-05-13: 6/min,60/day
gpt-4o-2024-08-06: 6/min,60/day
gpt-4o-all: 6/min,60/day
default: 30/min,1000/day
api_key_cooldown_period: 60
api_keys:
- api: sk-******************
model:
- batch-get-gpts
- claude-1-100k
- claude-1.3
- claude-1.3-100k
- claude-3-haiku-20240307
- code-llama-13b
- code-llama-34b
- code-llama-7b
- codellama-70b-instruct
- cogvideox-result
- dbrx-instruct
- deepseek-chat
- deepseek-coder
- distil-whisper-large-v3-en
- flame-2-13b
- flame-2-70b
- flame-3-70b
- flame-3-8b
- flame-3.1-70b
- flame-3.1-8b
- flux
- flux-chat
- flux-result
- gemini-1.0-pro
- gemini-1.5-flash
- gemini-1.5-flash-8b
- gemini-1.5-pro
- gemma-2b-it
- gemma-7b-it
- gemma2-9b-it
- gemma-2-9b-it
- get-gpts
- gglm-3-turbo
- gglm-4-flash
- gglm-4-on
- google-palm
- gpt-3.5-turbo
- gpt-3.5-turbo-16k
- gpt-4o-mini
- chatgpt-4o-latest
- gpt-4o
- gpt-4o-2024-05-13
- gpt-4o-2024-08-06
- gpt-4o-all
- hermes-3-llama-3.1-405b
- kling-task
- lfm-40b
- llama-2-7b
- llama-3-sonar-large-32k-chat
- llama-3-sonar-large-32k-online
- llama-3-sonar-small-32k-chat
- llama-3-sonar-small-32k-online
- llama-3.1-70b-versatile
- llama-3.1-8b
- llama-3.1-8b-instant
- llama-3.2-1b-preview
- llama-3.2-3b-preview
- llama-3.2-11b-vision-preview
- llama-3.2-90b-vision-preview
- llama-guard-3-8b
- llama3-70b-8192
- llama3-8b-8192
- llama3-groq-70b-8192-tool-use-preview
- llama3-groq-8b-8192-tool-use-preview
- llama-3-8b-instruct
- llama-3.1-8b-instruct
- llama-3.1-70b-instruct
- llama-3.1-405b-instruct
- llama-3.2-1b-instruct
- llama-3.2-3b-instruct
- llama-3.2-11b-vision-instruct
- llama-3.2-90b-vision-instruct
- long-pocket
- luma-pro-task
- luma-task
- luma-vip-task
- llava-v1.5-7b-wrapper
- mistral-7b-instruct
- mixtral-8x22b
- mythomax-l2-13b
- mixtral-8x7b
- mixtral-8x7b-32768
- mixtral-8x7b-instruct
- mythomist-7b
- openchat-7b
- phi-3-mini-128k-instruct
- phi-3-medium-128k-instruct
- playground-v2.5
- qwen-2-7b-instruct
- runway-video-task
- runway-vip-video-task
- search-gpts
- search-gpts-chat
- stable-diffusion
- stable-diffusion-3-2b
- suno-concat
- shap-e
- text-embedding-004
- text-embedding-3-large
- text-embedding-3-small
- text-embedding-ada-002
- twin-1.5-pro-001
- twin-1.5-pro-002
- toppy-m-7b
- vidu-task-get
- whisper-1
- whisper-large-v3
- whisper-large-v3-turbo
- zephyr-7b-beta
role: admin
preferences:
SCHEDULING_ALGORITHM: random
AUTO_RETRY: true
RATE_LIMIT: 60/min
ENABLE_MODERATION: false
preferences:
model_timeout:
gpt-4o: 10
claude-3-5-sonnet: 10
default: 10
o1-mini: 30
o1-preview: 100
cooldown_period: 300 |
|
it worked right before bumping to updated version of uni-api. and i have enough points from provider gpt-god on all API keys |
|
You deleted all the API keys. I hope you can keep the beginning part of all the APIs for gpt-god. If you delete them all, I won't be able to tell if uni-api has successfully switched APIs. |
|
However, I counted the number of API keys. Assuming the uni-api successfully switched the API key, all the API keys under gpt-god were tried. Therefore, it is possible that all your API keys have become invalid. |
|
yes. i double checked this APIs in another client - got same error. by the way - web version of gpt-god still working for me, and my token points still there, only API keys not work, so maybe gpt-god shadow banned all my accounts for abusing their API or their API service is just under maintaince or some problems. than it is just coincidence that it happened same time I updated uni-api. so i must admit that this case not related to uni-api. sorry and thanks |
|
btw, from my config above, you can see why i wish this enchancement in your ChatGPT project here :) |
|
it works now again. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2024-11-05 18:40:17,997 - uni-api - ERROR - Error 500 with provider gpt-1: {'code': -1, 'msg': 'MISCONF Redis is configured to save RDB snapshots, but it is currently not able to persist on disk. Commands that may modify the data set are disabled, because this instance is configured to report errors during writes if RDB snapshotting fails (stop-writes-on-bgsave-error optio
The text was updated successfully, but these errors were encountered: