CaIon
1fededceb3
feat: refactor token estimation logic
...
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
2025-12-02 21:34:39 +08:00
CaIon
c8bbf7bed8
feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels
2025-11-21 18:17:01 +08:00
Seefs
5010f2d004
format: package name -> github.com/QuantumNous/new-api ( #2017 )
2025-10-11 15:30:09 +08:00
CaIon
16997a695d
refactor: token counter logic
2025-06-21 00:54:40 +08:00
1808837298@qq.com
1307a23f01
feat: realtime
...
(cherry picked from commit d4966246e68dbdcdab45ec5c5141362834d74425)
2024-11-05 19:27:47 +08:00
CalciumIon
2041a2e4a7
fix: gemini stream finish reason ( close #378 )
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
2024-07-19 17:16:20 +08:00
CalciumIon
917c16903c
refactor: 重构流模式逻辑
2024-07-15 18:04:05 +08:00
CalciumIon
976e1f0921
fix: stream options
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
2024-07-08 21:54:32 +08:00
CalciumIon
876bed4600
feat: support claude stream_options
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
2024-07-08 01:45:43 +08:00
1808837298@qq.com
313c16f360
refactor: 重构敏感词
2024-05-23 23:59:55 +08:00
CaIon
5aad98d736
feat: 统一错误提示
2024-03-20 20:36:55 +08:00
CaIon
14892a6582
feat: 初步兼容敏感词过滤
2024-03-20 17:07:42 +08:00
1808837298@qq.com
1735981217
feat: 初步重构
2024-02-29 01:08:18 +08:00
