uni-api / main.py

Commit History

resolve conflicts
3b027cd

yym68686 commited on

resolve conflicts
021d784

yym68686 commited on

🐛 Bug: Fix the bug where tokens cannot be calculated.
c23690b

yym68686 commited on

🐛 Bug: Fix the bug where request information cannot be stored in the database.
25e0bb8

yym68686 commited on

✨ Feature: Add feature: Support setting AUTO_RETRY to a number to customize the retry count.
e995487

yym68686 commited on

✨ Feature: Add feature: Support for text-to-speech endpoint /v1/audio/speech
483c524

yym68686 commited on

🐛 Bug: Fix the bug where errors are not correctly returned when there is a syntax error in the configuration file.
6f7d288

yym68686 commited on

🐛 Bug: Fix the bug where using wildcard configuration for weights fails to find available channels.
765297f

yym68686 commited on

🐛 Bug: Fix the bug of infinite loop error when there is only one weighted channel.
83b5b1b

yym68686 commited on

🐛 Bug: 1. Fix the bug where different base URLs use the same client.
ac2ca17

yym68686 commited on

✨ Feature: Add feature: Support socks5 proxy
9871738

yym68686 commited on

🐛 Bug: Remove redundant error-catching code snippets
1130ba9

yym68686 commited on

🐛 Bug: Fix bugs caused by concurrent errors in multiple database write operations.
2f00898

yym68686 commited on

🐛 Bug: Fix the bug where the global timeout configuration does not take effect.
4fe51b7

yym68686 commited on

🐛 Bug: Fix the bug where the 201 status code is mistakenly considered an error.
3d5dc7e

yym68686 commited on

✨ Feature: Add feature: Support setting model timeout at the channel level
0a213f9

yym68686 commited on

🐛 Bug: Fix the bug of undefined review content.
d2272e8

yym68686 commited on

💻 Code: Optimize log display: add error provider name display.
08f4342

yym68686 commited on

✨ Feature: Add feature: Support that as long as the prefix of the API key exists in the configuration file, the API key is valid.
ecf5650

yym68686 commited on

🐛 Bug: The bug where the provider's name, which is purely numeric, was not converted to a string has been fixed.
478e740

yym68686 commited on

🐛 Bug: Fix the bug where the response body error returned by the error report incorrectly uses raise.
9bde0e5

yym68686 commited on

🐛 Bug: Fix the issue where an error is returned directly when Authorization is empty.
11f264c

yym68686 commited on

✨ Feature: Add feature: support setting rate limit for each model individually
cdf3ed9

yym68686 commited on

💻 Code: Add log display for model not found.
a80a859

yym68686 commited on

💻 Code: Optimize to reduce unnecessary log output.
a5e6e34

yym68686 commited on

💻 Code: Modify the default behavior of API key cooldown, change it to default off for API key cooldown. When there is only one API key in the channel, it will not cooldown under any circumstances. When API_KEY_COOLDOWN_PERIOD is 0, it will not cooldown. After enabling cooldown, any error with the API key will trigger a cooldown.
d30f0dd

yym68686 commited on

🐛 Bug: Fix the bug of incorrect function parameters entering the cooldown state.
68795da

yym68686 commited on

🐛 Bug: 1. Fix the bug where the closed client cannot be found when closing the request client.
76819d6

yym68686 commited on

📖 Docs: Update documentation
ec66323

yym68686 commited on

💻 Code: When there is only one optional provider, cooling will not take effect.
44f121d

yym68686 commited on

🐛 Bug: Fixed the bug with limited concurrency and removed unnecessary asynchronous mutex locks.
eefdfa1

yym68686 commited on

🐛 Bug: Fix the bug where Vercel fails to start successfully.
467f256

yym68686 commited on

🐛 Bug: Fix the bug where Vercel fails to start successfully.
52d3f47

yym68686 commited on

🐛 Bug: Fix the bug of incorrect weight allocation
f2a60ff

yym68686 commited on

✨ Feature: Add feature: Support model-level cooling. When a model under a channel reports an error, it does not affect other models under the same channel, only the model that reported the error is cooled.
f2794a6

yym68686 commited on

🐛 Bug: Fix the bug in the chart display.
ec63db6

yym68686 commited on

🐛 Bug: Fixed the bug where the cooling model could not take effect in this request.
bdb98ff

yym68686 commited on

✨ Feature: Add feature: Support channel cooldown. When an API channel response fails, the channel will automatically be excluded and cooled down for a period of time, during which no requests will be made to that channel. After the cooldown period ends, the model will automatically be restored until it fails again, triggering another cooldown.
fc4b826

yym68686 commited on

🪞 Frontend: Fixed the bug where the chart size was displayed incorrectly when there was no data.
3035b10

yym68686 commited on

🐛 Bug: Fix the bug in the moral check database update error.
a20c06f

yym68686 commited on

🪞 Frontend: Add request model statistics bar chart
4f0c23d

yym68686 commited on

💰 Sponsors: Thanks to @PowerHunter for the CNY 200 sponsorship, sponsorship information has been added to the README.
25f3a29

yym68686 commited on

🐛 Bug: Fix the bug where the model cannot be found.
2f54462

yym68686 commited on

🐛 Bug: Fix the bug where weight polling cannot match the model.
8583e53

yym68686 commited on

🐛 Bug: Fix the bug where weight polling did not check if the weight channel conforms to the request model.
5b1ad67

yym68686 commited on

📖 Docs: Add /docs/markdown endpoint to output markdown API documentation
84daa54

yym68686 commited on

📖 Docs: Update documentation
ee53a1b

yym68686 commited on

🐛 Bug: Fix the bug that did not check if weights were None.
54d814c

yym68686 commited on

🪞 Frontend: Added sidebar support to the front end, removed the menu bar.
c9427f3

yym68686 commited on

🐛 Bug: Fix the bug of weight load balancing round-robin.
b2991c2

yym68686 commited on