Alex
492c071cc7
Merge 3aae552167 into 3809375694
2025-04-19 16:15:25 +08:00
Jasper Hu
2d7229d2b8
feat: 支持 OpenAI 新模型 o3 与 o4-mini，并适配新参数
2025-04-18 20:36:07 +01:00
AC
04cbadb197
Enhance API and Chat Actions with Improved Provider Handling
...
- Added logging to `getClientApi` for better debugging of provider input and standardized provider names.
- Updated `ChatActions` to handle lowercase provider IDs, converting them to TitleCase for consistency with the ServiceProvider enum.
- Implemented defaulting to OpenAI when provider ID is missing and added relevant logging for session updates.
- Enhanced logging in `useChatStore` to track API call preparations and provider configurations.
2025-04-06 17:03:18 +08:00
AC
fc9688a1f7
feat(bedrock): Integrate AWS Bedrock as a new LLM provider
...
Adds support for using models hosted on AWS Bedrock, specifically Anthropic Claude models.
Key changes:
- Added '@aws-sdk/client-bedrock-runtime' dependency.
- Updated constants, server config, and auth logic for Bedrock.
- Implemented backend API handler () to communicate with the Bedrock API, handling streaming and non-streaming responses, and formatting output to be OpenAI compatible.
- Updated dynamic API router () to dispatch requests to the Bedrock handler.
- Created frontend client () and updated client factory ().
- Updated with necessary Bedrock environment variables (AWS keys, region, enable flag) and an example for using to alias Bedrock models.
2025-04-06 00:46:35 +08:00
RiverRay
f7cde17919
Merge pull request #6292 from Little-LittleProgrammer/feature/alibaba-omni-support
...
feat(alibaba): Added alibaba vision model and omni model support
2025-03-01 10:25:16 +08:00
Kadxy
2d4180f5be
fix: update request payload to use filtered messages in Deepseek API
2025-02-28 13:59:30 +08:00
Kadxy
9f0182b55e
fix: enforce that the first message (excluding system messages) is a user message in the Deepseek API
2025-02-28 13:54:58 +08:00
EvanWu
b709ee3983
feat(alibaba): Added alibaba vision model and omni model support
2025-02-24 20:18:07 +08:00
suruiqiang
cf140d4228
Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into ali_bytedance_reasoning_content
2025-02-12 17:54:50 +08:00
suruiqiang
476d946f96
fix bug (trim eats space or \n mistakenly), optimize timeout by model
2025-02-12 17:49:54 +08:00
suruiqiang
9714258322
support deepseek-r1@OpenAI's reasoning_content, parse <think></think> from stream
2025-02-11 18:57:16 +08:00
RiverRay
77c78b230a
Merge pull request #6193 from siliconflow/get-models-siliconflow
...
Model listing of SiliconFlow
2025-02-11 18:37:22 +08:00
suruiqiang
b0758cccde
optimization
2025-02-11 16:08:30 +08:00
suruiqiang
98a11e56d2
support alibaba and bytedance's reasoning_content
2025-02-11 12:46:46 +08:00
Shenghang Tsai
86f86962fb
Support VLM on SiliconFlow
2025-02-10 13:39:06 +08:00
Shenghang Tsai
2137aa65bf
Model listing of SiliconFlow
2025-02-10 11:03:49 +08:00
suruiqiang
97a4aafc92
Merge remote-tracking branch 'remotes/origin/main' into bug_fix
2025-02-09 09:46:07 +08:00
RiverRay
c6199dbf9f
Merge pull request #6186 from siliconflow/fix-truc-of-reasoning-model
...
Fix formatting of reasoning model on SiliconFlow
2025-02-08 23:40:39 +08:00
Shenghang Tsai
acf75ce68f
Remove unnecessary trimming
2025-02-08 16:34:17 +08:00
suruiqiang
1ae5fdbf01
mini optimizations
2025-02-08 16:15:10 +08:00
Shenghang Tsai
2a3996e0d6
Update siliconflow.ts
2025-02-08 14:38:12 +08:00
suruiqiang
a5a9768245
change request timeout for thinking mode
2025-02-07 16:34:14 +08:00
suruiqiang
3fe55b4f7f
fix bug that gemini has multiple candidates part
2025-02-07 16:20:07 +08:00
suruiqiang
f30c6a4348
fix doubao and grok not upload image
2025-02-07 16:14:19 +08:00
Shenghang Tsai
ad9ab9d45a
New provider SiliconFlow and Its Latest DeekSeek Models
...
Update README.md
Update constant.ts
Update README_CN.md
2025-02-04 16:59:26 +08:00
Sky
8f12beb8f0
support o3-mini
2025-02-02 21:43:30 +00:00
river
143be69a7f
chore: remove log
2025-01-31 00:50:03 +08:00
Kadxy
dabb7c70d5
feat: Remove reasoning_contentfor DeepSeek API messages
2025-01-31 00:30:08 +08:00
Kadxy
c449737127
feat: Support DeepSeek API streaming with thinking mode
2025-01-31 00:07:52 +08:00
suruiqiang
b948d6bf86
bug fix
2024-12-29 11:24:57 +08:00
suruiqiang
7380c8a2c1
Merge branch 'main' of https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web into add_deepseek
2024-12-29 08:43:25 +08:00
Dogtiti
8a22c9d6db
feature: support glm-4v
2024-12-28 23:33:06 +08:00
RiverRay
13430ea3e2
Merge pull request #5965 from zmhuanf/temp
...
Fix issue #5964 : Prevents character loss in gemini-2.0-flash-thinking-exp-1219 responses
2024-12-28 22:02:02 +08:00
Dogtiti
bc322be448
fix: type error
2024-12-28 20:24:08 +08:00
Dogtiti
a867adaf04
fix: size
2024-12-28 20:23:51 +08:00
Dogtiti
0cb186846a
feature: support glm Cogview
2024-12-28 20:23:44 +08:00
suruiqiang
081daf937e
since #5984 , add DeepSeek as a new ModelProvider (with deepseek-chat&deepseek-corder models), so that user can use openai and deepseek at same time with different api url&key
2024-12-27 16:57:26 +08:00
zmhuanf
87b5e3bf62
修复bug；
2024-12-22 15:44:47 +08:00
code-october
ef24d3e633
use stream when request o1
2024-11-21 03:46:10 +00:00
DDMeaqua
b41c012d27
chore: shouldStream
2024-11-13 15:12:46 +08:00
DDMeaqua
0628ddfc6f
chore: update
2024-11-13 14:27:41 +08:00
DDMeaqua
7eda14f138
fix: [ #5308 ] gemini对话总结
2024-11-13 14:24:44 +08:00
DDMeaqua
d5bda2904d
chore: o1模型使用max_completion_tokens
2024-11-07 19:45:27 +08:00
Dogtiti
44fc5b5cbf
fix: onfinish responseRes
2024-11-04 17:00:45 +08:00
Dogtiti
36bfa2ef7c
Merge pull request #5741 from ConnectAI-E/feat-glm
...
feat: [#5714 ] 支持GLM
2024-11-01 13:57:30 +08:00
DDMeaqua
afe12c212e
chore: update
2024-11-01 13:53:43 +08:00
DDMeaqua
d357b45e84
feat: [ #5714 ] 支持GLM
2024-10-30 19:24:03 +08:00
lloydzhou
f0b3e10a6c
hotfix for gemini invald argument #5715
2024-10-25 18:19:22 +08:00
lloydzhou
f89872b833
hotfix for gemini invald argument #5715
2024-10-25 18:12:09 +08:00
lloydzhou
e791cd441d
add xai
2024-10-23 11:55:25 +08:00
