Fetching metadata from the HF Docker repository...
-
🐛 Bug: Fix the bug where the 201 status code is mistakenly considered an error.
-
🐛 Bug: Fix the bug where the embedding URL for GLM and GitHub models is incorrect.
-
✨ Feature: Add feature: support wildcard matching like gpt* to match models such as gpt-3.5 and gpt-4.
-
🐛 Bug: Fix the bug where Gemini cannot use non-streaming output.
-
✨ Feature: Add support for frontend page operation configuration files.
-
✨ Feature: 1. Add support for experimental frontend.
2. Add support for configuration files without listing models.
-
✨ Feature: Add database, count the first character time.
📖 Docs: Update documentation
-
🤖 Models: Add support for the cohere series models
📖 Docs: Update documentation
-
🐛 Bug: Fix the bug where the timestamp is a decimal.
-
📖 Docs: Update the documentation, add an English README.
-
✨ Feature: Add feature: Add support for rate limiting.
-
🐛 Bug: Fix the bug where the channel status is not sorted by success rate.
-
✨ Feature: Add feature: Add support for weighted load balancing.
-
✨ Feature: Add features: Add API channel success rate statistics, channel status records.
-
🐛 Bug: Fix the bug of tool use request body format error
-
Add feature: support load balancing for multiple keys in a single channel, enabled by default.
-
Fix the bug of incorrect request body format for tool use.
-
update README
-
Add feature: support vertex claude API using tool use functionality.
-
✨ Feature: Add feature: Support vertex ai API and vertex tool use invocation.
-
✨ Feature: Add feature: support Gemini API tool use
-
Fix renaming model original name can also be requested
-
Fix the bug causing errors in the GPT channel when using the Wu API.
-
Optimize log display
-
🐛 Bug: 1. Fix the bug where system_prompt is undefined
2. Fix the bug where the log display is incomplete.
-
Add GPT format test module
Fix the bug of decoding error in reading stream response.
-
Support setting whether to poll for each API key separately.
-
Fix Claude response reception logic
