Jeremy JIANG
36a03f465b
feat: update Zhipu model prices ( #2020 )
2025-02-02 22:06:07 +08:00
JustSong
c81ee68dd0
feat: improve error logging for token encoder initialization with offline usage guidance
2025-02-02 17:24:23 +08:00
JustSong
4f68f3e1b3
chore: update log content
2025-01-31 20:16:56 +08:00
JustSong
0bab887b2d
chore: update log content
2025-01-31 20:15:04 +08:00
JustSong
dc470ce82e
feat: show stream & elapsed time in log detail
2025-01-31 19:34:22 +08:00
JustSong
ea0721d525
feat: update log content format
2025-01-31 18:15:43 +08:00
Fennng
09911a301d
feat: support hunyuan-embedding ( #2035 )
...
* feat: support hunyuan-embedding
* chore: improve implementation
---------
Co-authored-by: LUO Feng <luofeng@flowpp.com>
Co-authored-by: JustSong <quanpengsong@gmail.com>
2025-01-31 16:48:02 +08:00
Laisky.Cai
d88e07fd9a
feat: add deepseek-reasoner & gemini-2.0-flash-thinking-exp-01-21 ( #2045 )
...
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
* feat: add MILLI_USD constant and update pricing for deepseek services
* feat: add support for new Gemini model version 'gemini-2.0-flash-thinking-exp-01-21'
2025-01-31 15:15:59 +08:00
Qiying Wang
a858292b54
feat: support gpt-4o-2024-11-20 ( #1941 )
CI / Unit tests (push) Has been cancelled
CI / commit_lint (push) Has been cancelled
2024-12-22 19:49:50 +08:00
Yuwei Ba
ff589b5e4a
chore: update model mapping implementation for audio ( #1932 )
...
* fixed model mapping
* chore: update implementation
---------
Co-authored-by: JustSong <quanpengsong@gmail.com>
2024-12-22 19:33:11 +08:00
ZhangTianrong
59eae186a3
fix: remove the duplicate claude-3-5-haiku-20241022 in Anthropic's base model list ( #1957 )
...
* Update constants.go
Remove the duplicate `claude-3-5-haiku-20241022` causing issue 1928
* fix: fix syntax error
---------
Co-authored-by: JustSong <quanpengsong@gmail.com>
2024-12-22 18:58:29 +08:00
Wei Tingjiang
49ffb1c60d
feat: enhance response handling to support gemini-2.0-thinking ( #1995 )
2024-12-22 18:25:44 +08:00
longkeyy
2f16649896
feat: update qwen model and price ( #1966 )
2024-12-22 18:22:57 +08:00
Laisky.Cai
e9f117ff72
feat: add gemini-2.0-flash-exp and fix race condition in processChannelRelayError ( #1983 )
...
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
2024-12-21 20:32:30 +08:00
Laisky.Cai
6bb5247bd6
feat: add support for new OpenAI models and update billing ratios ( #1990 )
2024-12-21 20:28:51 +08:00
Laisky.Cai
305ce14fe3
feat: support replicate chat models ( #1989 )
...
* feat: add Replicate adaptor and integrate into channel and API types
* feat: support llm chat on replicate
2024-12-21 14:41:19 +08:00
JustSong
6ab87f8a08
feat: add warning in log when system prompt is reset
CI / Unit tests (push) Has been cancelled
CI / commit_lint (push) Has been cancelled
2024-11-10 17:18:46 +08:00
JustSong
6eb0770a89
feat: support set system prompt for channel ( close #1920 )
2024-11-10 14:53:34 +08:00
JustSong
92cd46d64f
feat: able to use ENFORCE_INCLUDE_USAGE to enforce include usage in response
CI / Unit tests (push) Waiting to run
CI / commit_lint (push) Waiting to run
2024-11-10 00:36:08 +08:00
lihangfu
2b2dc2c733
fix: update Spark Lite's domain to lite ( #1896 )
2024-11-09 23:55:55 +08:00
JustSong
a3d7df7f89
feat: update GeneralOpenAIRequest
2024-11-09 23:43:08 +08:00
wanthigh
c368232f50
fix: changeoptional field to pointer type ( #1907 )
...
* fix:修复在渠道配置中设置模型重定向时，temperature为0被忽略的问题
* fix: set optional fields to pointer type
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-11-09 23:31:46 +08:00
Laisky.Cai
cbfc983dc3
feat: add new claude models ( #1910 )
...
* feat: Add new models to ModelList in constants.go
* feat: update model lists and mappings for Claude 3.5 versions
---------
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
2024-11-09 22:48:54 +08:00
Ryo Shen
8ec092ba44
feat: add support for xAI ( #1915 )
CI / Unit tests (push) Has been cancelled
CI / commit_lint (push) Has been cancelled
2024-11-07 23:52:38 +08:00
shaoyun
b0b88a79ff
feat: added support for Claude 3.5 Haiku ( #1912 )
2024-11-07 23:51:17 +08:00
JustSong
f75a17f8eb
feat: always return usage in stream mode
2024-10-27 17:58:44 +08:00
Wei Tingjiang
6f13a3bb3c
feat: update Gemini adaptor to support custom response format ( #1892 )
2024-10-27 17:10:50 +08:00
shaoyun
f092eed1db
feat: add support for Claude Sonnet 3.5 v2 ( #1888 )
2024-10-27 17:10:02 +08:00
longkeyy
629378691b
feat: update groq model and price ( #1864 )
2024-10-27 17:07:24 +08:00
Pan, Wen-Ming
a4d6e7a886
feat: add Vertex AI gemini-1.5-pro-002 and gemini-1.5-flash-002 ( #1854 )
2024-10-27 17:04:41 +08:00
lihangfu
e32cb0b844
feat: support SparkDesk-v3.5-32K ( #1832 )
...
Co-authored-by: lihangfu <hfli8@iflytek.com>
2024-10-27 17:02:54 +08:00
byte911
88acc5a614
fix: return the usage info if not null ( #1792 )
...
Usage is missing.
2024-09-22 16:41:10 +08:00
lihangfu
32f90a79a8
feat: support SparkDesk-v3.1-128K ( #1732 )
...
* feat: 支持SparkDesk-v3.1-128K以及hunyuan-vision
* feat: 支持SparkDesk-v3.1-128K以及hunyuan-vision
---------
Co-authored-by: lihangfu <hfli8@iflytek.com>
2024-09-22 16:29:09 +08:00
TAKO
649ecbf29c
feat: support new openai models (4o 0806, chatgpt-4o-latest) ( #1721 )
...
* feat: support new model gpt-4o-2024-08-06
* feat: support new model chatgpt-4o-latest
2024-09-21 23:01:19 +08:00
forrestlinfeng
c9ac670ba1
feat: update stepfun models ( #1740 )
...
Co-authored-by: chenlinfeng <chenlinfeng@step.ai>
2024-09-21 22:48:46 +08:00
leavegee
15f815c23c
fix: fix ali embedding model always use v1 ( #1747 )
...
* fix:ali embedding model: v2 and v3
* chore: use ctxkey.RequestModel to eliminate hardcoding
---------
Co-authored-by: xuejia <gexuejia@djbx.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-09-21 22:40:06 +08:00
majian
89b63ca96f
feat: ResponseFormat support json_schema ( #1759 )
...
* feat: responseFormat support json_schema
* chore: rename struct name
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-09-21 22:35:24 +08:00
TAKO
2af6f6a166
feat: add Cloudflare New Free Model Llama 3.1 8b ( #1703 )
2024-08-06 23:49:48 +08:00
MotorBottle
04bb3ef392
feat: add Max Tokens and Context Window Setting Options for Ollama Channel ( #1694 )
...
* Update main.go with max_tokens param
* Update model.go with max_tokens param
* Update model.go
* Update main.go
* Update main.go
* Adds num_ctx param for Ollama Channel
* Added num_ctx param for ollama adapter
* Added num_ctx param for ollama adapter
* Improved data process logic
2024-08-06 23:44:37 +08:00
longkeyy
b4bfa418a8
feat: update gemini model and price ( #1705 )
2024-08-06 23:43:33 +08:00
SLKun
e7e99e558a
feat: update Ollama embedding API to latest version with multi-text embedding support ( #1715 )
2024-08-06 23:43:20 +08:00
Shenghang Tsai
402fcf7f79
feat: add SiliconFlow ( #1717 )
...
* Add SiliconFlow
* Update README.md
* Update README.md
* Update channel.constants.js
* Update ChannelConstants.js
* Update channel.constants.js
* Update ChannelConstants.js
* Update compatible.go
* Update README.md
2024-08-06 23:42:25 +08:00
Laisky.Cai
c936198ac8
feat: add Proxy channel type and relay mode ( #1678 )
...
Add the Proxy channel type and relay mode to support proxying requests to custom upstream services.
2024-07-22 22:51:19 +08:00
TAKO
296ab013b8
feat: support gpt-4o mini ( #1665 )
...
* feat: support gpt-4o mini
* feat: fix gpt-4o mini image price
2024-07-22 22:44:08 +08:00
igophper
39383e5532
fix: support embedding models for doubao ( #1662 )
...
Fixes #1594
2024-07-22 22:38:50 +08:00
Laisky.Cai
adba54acd3
fix: implement improved headers for anthropic to support 8k outputs ( #1654 )
2024-07-16 23:48:54 +08:00
zijiren
6209ff9ea9
feat: vertexai support proxy url(example: cloudflare ai gateway) and fix some vertexai bug ( #1642 )
...
* feat: vertexai support proxy url(example: cloudflare ai gateway)
* fix: do resp model mapping
* fix: missing system
* fix: stream need query alt=sse
2024-07-16 01:02:06 +08:00
F1ynn Zhan9
422a4e8ee5
feat: add field stop in GeneralOpenAIRequest ( #1637 )
2024-07-14 17:57:16 +08:00
LiuVaayne
cf9b5f0b92
feat: support claude and gemini in vertex ai ( #1621 )
...
* feat: support claude and gemini in vertex ai
* fix: do not show api key field in channel page when the type is VertexAI
* fix: update getToken function to include channelId in cache key
2024-07-13 14:59:28 +08:00
Ghostz
65acb94f45
fix: text filed check for 4v request ( #1634 )
2024-07-13 14:57:08 +08:00
zijiren
6ad169975f
fix: impl cloudflare worker ai gateway ( #1617 )
2024-07-09 22:57:06 +08:00
Qiying Wang
f636c50c84
fix: duplicate [DONE] ( #1629 )
2024-07-09 22:43:59 +08:00
Qiying Wang
720fe2dfeb
feat: refactor AwsClaude to Aws to support both llama3 and claude ( #1601 )
...
* feat: refactor AwsClaude to Aws to support both llama3 and claude
* fix: aws llama3 ratio
2024-07-06 13:19:41 +08:00
Jason
e090e76c86
feat: add Novita AI as model provider ( #1609 )
2024-07-06 13:16:46 +08:00
zijiren
efd30a40b3
feat: cloudflare support native openai api ( #1596 )
2024-07-06 13:12:30 +08:00
Mikey
0fc07ea558
feat: add support for Claude 3 tool use (function calling) ( #1587 )
...
* feat: add tool support for AWS & Claude
* fix: add {} for openai compatibility in streaming tool_use
2024-07-02 00:12:01 +08:00
igophper
fecaece71b
fix: fix size not support during image generation ( #1564 )
...
Fixes #1224 , #1068
2024-06-30 19:52:33 +08:00
Shi Jilin
c135d74f13
feat: support Spark4.0 Ultra ( #1575 )
...
* fix: fix SparkDesk Function Call (修复 Spark Pro/Max函数调用只会返回普通对话回答而不是Function Call回答的问题
* feat: support Spark4.0 Ultra
2024-06-30 19:38:02 +08:00
lihangfu
d0369b114f
feat: support spark4.0 ultra ( #1569 )
...
* feat: 支持v3最新协议的腾讯混元（#1452）
* feat: 支持Spark4.0 Ultra
---------
Co-authored-by: lihangfu <hfli8@iflytek.com>
2024-06-30 19:37:07 +08:00
zijiren
b21b3b5b46
refactor: abusing goroutines and channel ( #1561 )
...
* refactor: abusing goroutines
* fix: trim data prefix
* refactor: move functions to render package
* refactor: add back trim & flush
---------
Co-authored-by: JustSong <quanpengsong@gmail.com>
2024-06-30 18:36:33 +08:00
shaoyun
ae1cd29f94
feat: added support for Claude Sonnet 3.5 ( #1567 )
2024-06-30 16:25:25 +08:00
Ghostz
5a58426859
fix minimax empty log ( #1560 )
2024-06-30 16:09:16 +08:00
JustSong
3777517f64
chore: add ut
2024-06-23 14:28:55 +08:00
Shi Jilin
ff196b75a7
fix: fix sparkdesk function call
2024-06-20 22:56:59 +08:00
lihangfu
279caf82dc
feat: support tencent v3 api ( #1542 )
...
Co-authored-by: lihangfu <hfli8@iflytek.com>
2024-06-20 00:23:08 +08:00
Wei Tingjiang
b1520b308b
Try to fix Gemini streaming return being truncated by FinishReason. ( #1477 )
...
1
2024-06-14 00:30:47 +08:00
Zhong Liu
c1971870fa
fix: support for Spark Lite model ( #1526 )
...
* fix: Support for Spark Lite model
* fix: fix panic
* fix: fix xunfei version config
---------
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-06-13 00:07:26 +08:00
wagxuebing
f83894c83f
fix: xunfei interface call 4001 error ( #1499 )
...
Co-authored-by: lynnssb <lynntobing@gmail.com>
2024-06-12 23:12:58 +08:00
fxsome
e9981fff36
feat: post all messages for cloudflare ( #1515 )
2024-06-08 13:34:23 +08:00
取梦为饮
98669d5d48
feat: add support for bytedance's doubao ( #1438 )
...
* 增加豆包大模型支持
* chore: update channel options & add prompt
---------
Co-authored-by: 康龙彪 <longbiao.kang@i-tudou.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-06-08 13:26:26 +08:00
Wei Tingjiang
9321427c6e
feat: support gemini embeddings (text-embedding-004,embedding-001) ( #1475 )
...
* Refactor Gemini Adaptor to Support Embeddings
* Add new models to ModelList
2024-05-29 01:17:32 +08:00
JustSong
ceea4c6d4a
feat: support user content download proxy & relay proxy now
2024-05-29 01:14:00 +08:00
Mo
332c8db0b3
fix: add prefixes to image models to solve the problem of duplicate models ( #1469 )
...
* Add prefixes to image models to solve the problem of duplicate models
* Fix the issue that response_format is not set, causing the b64_json parameter to be ignored.
2024-05-28 01:32:57 +08:00
Dafei Zhao
a9211d66f6
fix: fix gpt-4o token encoding ( #1446 )
2024-05-28 01:26:07 +08:00
Qiying Wang
2457d00afb
feat: support gpt-4o ( #1431 )
2024-05-21 01:14:22 +08:00
JustSong
91b80ae879
fix: remove extra space
2024-05-07 23:57:34 +08:00
JustSong
2720e1a358
feat: support minimax's 6.5 models ( close #1395 )
2024-04-30 02:23:14 +08:00
JustSong
71f4403fd5
feat: add together.ai support ( #1298 )
2024-04-30 02:16:53 +08:00
JustSong
1f76c80553
fix: fix aws claude panic ( #1384 )
2024-04-29 22:49:06 +08:00
JustSong
7e027d2bd0
fix: fix minimax prompt & completion tokens is empty ( #1391 )
2024-04-29 22:35:47 +08:00
JustSong
30f373b623
fix: fix usage is empty ( close #1391 )
2024-04-29 22:29:13 +08:00
plusye
1c2654320e
fix: fix getPreConsumedQuota ( #1312 )
2024-04-27 16:07:06 +08:00
caixinjiang
6cffb116b7
fix: fix zhipu embedding error when input is array but not string ( #1306 )
...
* fix zhipu embedding error when input is array but not string
* fix: only use the first one
---------
Co-authored-by: 蔡新疆 <cxj@icc.link>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-04-27 16:05:14 +08:00
Qiying Wang
a84c7b38b7
fix: claude stream response parse ( #1334 )
2024-04-27 15:58:07 +08:00
NongMO
6170b91d1c
feat: support for the ollama vision model ( #1376 )
...
* feat: support for the ollama vision model
`llava` model, pass test
* Update main.go
format code
* chore: remove useless log
---------
Co-authored-by: nongqiqin <nongqiqin@tipdm.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-04-27 15:47:27 +08:00
JustSong
04b49aa0ec
chore: use StringContent() to convert response to text
2024-04-27 15:41:02 +08:00
Wei Tingjiang
ef88497f25
fix: refactor Gemini adaptor to support streaming content generation ( #1382 )
2024-04-27 15:39:59 +08:00
JustSong
007906216d
feat: support DeepL's model ( close #1126 )
2024-04-27 13:37:22 +08:00
JustSong
e64e7707a0
feat: support cohere's web search
2024-04-27 00:06:43 +08:00
JustSong
ea210b6ed7
chore: update ollama models
2024-04-26 23:12:39 +08:00
JustSong
9026ec7510
feat: support cloudflare now
2024-04-26 23:05:48 +08:00
JustSong
c317872097
feat: support deepseek now
2024-04-26 00:48:53 +08:00
JustSong
da0842272c
fix: add model to response ( close #1362 )
2024-04-24 22:19:58 +08:00
Ghostz
24f026d18e
feat: add cohere support ( #1355 )
...
* support cohere
* chore: tiny improvements
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2024-04-24 21:50:01 +08:00
Wei Tingjiang
779b747e9e
feat: add function and tools support for Gemini ( #1358 )
...
* Update model.go
* Support Gemini tool_calls.
* Fix gemini tool calls (also keep support functions).
* Fixed the problem of arguments not being stringified.
Fix panic: candidate.Content.Parts out of range
2024-04-24 21:26:45 +08:00
JustSong
3d149fedf4
chore: do not hardcode context key
2024-04-21 19:43:23 +08:00
JustSong
e30ebda0fe
chore: move config key to package ctxkey
2024-04-21 18:55:13 +08:00
JustSong
e5b3e37c46
feat: support bot prefix for coze
2024-04-21 18:04:56 +08:00
JustSong
8de489cf06
feat: support coze now
2024-04-21 17:59:57 +08:00
JustSong
541182102e
fix: ignore empty choice response for azure ( close #1324 )
2024-04-21 16:22:28 +08:00
