CaIon
6ac7878863
🔧 refactor(endpoint types): comment out unused endpoint types in constants
2025-07-04 15:53:46 +08:00
CaIon
7e298f8ad1
✨ feat: refactor environment variable initialization and introduce new constant types for API and context keys
2025-07-03 13:10:25 +08:00
CaIon
a9e5d99ea3
refactor: token counter logic
2025-06-21 00:54:40 +08:00
CaIon
f124404f07
🔧 fix(stream_scanner): improve resource management and error handling in StreamScannerHandler
2025-06-11 00:18:16 +08:00
CaIon
896e1d978f
🔧 fix(token_counter): enhance token encoder caching and concurrency handling
2025-06-10 18:55:21 +08:00
CaIon
6c4f64c397
🔧 fix(token_counter): refactor token encoder initialization and retrieval logic
2025-06-10 18:51:26 +08:00
CaIon
d1f493bf17
🔧 fix(token_counter): update token encoder implementation and dependencies
2025-06-10 18:04:49 +08:00
Xyfacai
b778cd2b23
refactor: message content 改成 any
...
refactor: message content 改成 any
2025-06-07 23:47:22 +08:00
CaIon
4825404d37
feat: enhance image decoding logic to handle base64 file types and improve error handling
2025-05-15 14:51:33 +08:00
CaIon
e097d5a538
feat: add video URL support in MediaContent and update token counting logic
2025-05-03 21:12:07 +08:00
CaIon
ee4f27d01b
refactor: simplify model prefix checks and update message role for o-series models
2025-04-17 16:50:52 +08:00
CaIon
cca9c0479f
feat: enhance file handling and logging in the application
2025-04-11 16:23:54 +08:00
1808837298@qq.com
dd393cd0d9
feat: support dify upload image file
2025-03-15 19:10:12 +08:00
1808837298@qq.com
bd48f43410
feat: claude relay
2025-03-12 21:31:46 +08:00
1808837298@qq.com
4f194f4e6a
feat: Implement cache token ratio for more precise token pricing
2025-03-08 01:30:50 +08:00
1808837298@qq.com
7dbb6b017c
feat: Add self-use mode for model ratio and price configuration
...
- Introduce `SelfUseModeEnabled` setting to allow flexible model ratio configuration
- Update error handling to provide more informative messages when model ratios are not set
- Modify pricing and relay logic to support self-use mode
- Add UI toggle for enabling self-use mode in operation settings
- Implement fallback mechanism for model ratios when self-use mode is enabled
2025-03-01 21:13:48 +08:00
1808837298@qq.com
13ab0f8e4f
fix: gemini&claude tool call format #795 #766
2025-02-26 23:56:10 +08:00
1808837298@qq.com
7ff4cebdbe
feat: Enhance token counting and content parsing for messages
2025-02-24 14:18:15 +08:00
1808837298@qq.com
f5e3063f33
feat: Improve embedding request handling and support across channels
...
- Update EmbeddingRequest DTO to support more flexible input types
- Add input parsing method to handle various input formats
- Implement ConvertEmbeddingRequest for multiple channel adaptors
- Remove relayMode parameter from EmbeddingHelper
- Add input validation for embedding requests
- Simplify embedding request conversion for different channels
2025-02-12 14:39:36 +08:00
1808837298@qq.com
ef4c1a2e48
fix: retry prompt tokens
2025-01-02 16:33:00 +08:00
CalciumIon
2b38e8ed8d
feat: add multi-file type support for Gemini and Claude
...
- Add file data DTO for structured file handling
- Implement file decoder service
- Update Claude and Gemini relay channels to handle various file types
- Reorganize worker service to cf_worker for clarity
- Update token counter and image service for new file types
2024-12-29 00:00:24 +08:00
CalciumIon
d2297d2723
feat: update o1 default token encoder
2024-12-27 15:03:10 +08:00
CalciumIon
62ae46b552
feat: support azure stream_options
2024-12-26 22:51:06 +08:00
1808837298@qq.com
8de79382f0
feat: azure realtime
...
(cherry picked from commit 75ff3d98f06103dc2df1f8817bd3fcbf433e0f20)
2024-11-05 19:27:55 +08:00
1808837298@qq.com
74f9006b40
feat: realtime
...
(cherry picked from commit d4966246e68dbdcdab45ec5c5141362834d74425)
2024-11-05 19:27:47 +08:00
1808837298@qq.com
33af069fae
feat: realtime
...
(cherry picked from commit a5529df3e1a4c08a120e8c05203a7d885b0fe8d8)
2024-11-05 19:24:14 +08:00
CalciumIon
139a104b26
feat: support gpt-4o-audio-preview
2024-11-04 15:27:12 +08:00
CalciumIon
e3b3fdec48
feat: update chatgpt-4o token encoder
2024-09-05 18:35:34 +08:00
CalciumIon
e2cf6b1e14
feat: support gpt-4o-mini image tokens
2024-07-19 12:59:37 +08:00
CalciumIon
ae00a99cf5
feat: 媒体请求计费选项
2024-07-18 17:04:19 +08:00
1808837298@qq.com
ecdcb379fe
feat: update token encoder
2024-05-30 23:15:06 +08:00
1808837298@qq.com
4dd5233f49
Merge remote-tracking branch 'origin/main'
2024-05-30 21:46:22 +08:00
1808837298@qq.com
d2a0d9f73b
feat: update tiktoken
2024-05-30 21:45:58 +08:00
1808837298@qq.com
099068f543
feat: 支持设置worker访问请求中的图片地址
2024-05-28 17:59:53 +08:00
1808837298@qq.com
36fac2baa2
feat: 增加重置模型倍率功能 ( close #62 )
2024-05-24 15:28:16 +08:00
1808837298@qq.com
bfbbe67fcd
refactor: 重构敏感词
2024-05-23 23:59:55 +08:00
CaIon
a3de309175
chore: token counter
2024-05-18 15:14:49 +08:00
CaIon
a3b3e6cc38
chore: update InitTokenEncoders ( #255 )
2024-05-15 16:32:00 +08:00
CaIon
9dcec2772d
chore: update tiktoken ( #254 )
2024-05-15 14:18:29 +08:00
CaIon
1c6fd87909
fix: 规范claude返回格式
2024-04-26 02:56:35 +08:00
CaIon
a3ccc92f55
fix: close #218
2024-04-24 14:44:24 +08:00
CaIon
783e8fd74a
refactor: 重构计费代码
2024-04-23 23:51:27 +08:00
CaIon
2841669246
feat: 完善函数计费
2024-04-23 23:01:06 +08:00
CaIon
bdc65bdba2
feat: 启用函数计费
2024-04-22 16:35:56 +08:00
CaIon
6114c9bb96
fix: CountTokenInput
2024-03-26 18:49:53 +08:00
CaIon
3cf2f0d5cb
fix: CountTokenInput
2024-03-26 18:21:38 +08:00
CaIon
67332bc8df
fix: 模型固定价格为空时错误使用默认价格
2024-03-23 17:19:29 +08:00
CaIon
a232afe9fd
feat: 统一错误提示
2024-03-20 20:36:55 +08:00
CaIon
7a663d26ec
feat: 初步兼容敏感词过滤
2024-03-20 17:07:42 +08:00
CaIon
c2965eb835
feat: support claude3 not stream
2024-03-08 18:26:18 +08:00
