Aiharara
e83f2bad84
Fix provider comparison issue in model comparison
...
Fixed an issue where comparing models using the provider object directly resulted in errors. Changed to compare provider.id to ensure the comparison is based on a unique identifier, accurately determining if the models are the same.
If the provider comparison fails, more models will be stored in persistStore. Although this issue is not immediately visible in the frontend due to subsequent processing, it leads to increased memory usage and longer startup times with each page reload.
2025-04-29 04:51:14 +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
suruiqiang
2173c82bb5
add deepseek-reasoner, and change deepseek's summary model to deepseek-chat
2025-01-23 18:47:22 +08:00
suruiqiang
0d5e66a9ae
not insert mcpSystemPrompt if not ENABLE_MCP
2025-01-23 18:24:38 +08:00
Kadxy
a3d3ce3f4c
Merge branch 'main' into feat-mcp
2025-01-19 23:28:12 +08:00
Kadxy
8aa9a500fd
feat: Optimize MCP configuration logic
2025-01-15 16:52:54 +08:00
Kadxy
0c14ce6417
fix: MCP execution content matching failed.
2025-01-09 13:41:17 +08:00
Kadxy
f2a2b40d2c
feat: carry mcp primitives content as a system prompt
2025-01-09 10:20:56 +08:00
Kadxy
77be190d76
feat: carry mcp primitives content as a system prompt
2025-01-09 10:09:46 +08:00
lvguanjun
840c151ab9
fix: prevent message sync between forked sessions by generating unique IDs
2025-01-05 11:22:53 +08:00
code-october
266e9efd2e
rename the function
2024-12-30 09:13:12 +00:00
code-october
57c88c0717
修复 VISION_MDOELS 在 docker 运行阶段不生效的问题
2024-12-30 08:58:41 +00:00
Kadxy
fe67f79050
feat: MCP message type
2024-12-29 09:24:52 +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
Kadxy
e1ba8f1b0f
feat: Send MCP response as a user
2024-12-29 08:29:02 +08:00
Kadxy
664879b9df
feat: Create all MCP Servers at startup
2024-12-28 21:06:26 +08:00
Dogtiti
0cb186846a
feature: support glm Cogview
2024-12-28 20:23:44 +08:00
Kadxy
c3108ad333
feat: simple MCP example
2024-12-28 14:31:43 +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
Dogtiti
e44ebe3f0e
feat: realtime config
2024-11-07 21:28:23 +08:00
Dogtiti
d544eead38
feat: realtime chat ui
2024-11-06 21:14:45 +08:00
Dogtiti
85cdcab850
fix: botMessage reply date
2024-11-06 14:53:08 +08:00
Dogtiti
106461a1e7
Merge branch 'main' of https://github.com/ConnectAI-E/ChatGPT-Next-Web into feature/update-target-session
2024-11-06 11:08:41 +08:00
Dogtiti
c4e19dbc59
fix: updateCurrentSession => updateTargetSession
2024-11-06 11:06:18 +08:00
Dogtiti
f3603e59fa
Merge pull request #5769 from ryanhex53/fix-model-multi@
...
Custom model names can include the `@` symbol by itself.
2024-11-06 10:49:28 +08:00
ryanhex53
8e2484fcdf
Refactor: Replace all provider split occurrences with getModelProvider utility method
2024-11-05 13:52:54 +00:00
ryanhex53
b844045d23
Custom model names can include the @ symbol by itself.
...
To specify the model's provider, append it after the model name using `@` as before.
This format supports cases like `google vertex ai` with a model name like `claude-3-5-sonnet@20240620`.
For instance, `claude-3-5-sonnet@20240620@vertex-ai` will be split by `split(/@(?!.*@)/)` into:
`[ 'claude-3-5-sonnet@20240620', 'vertex-ai' ]`, where the former is the model name and the latter is the custom provider.
2024-11-05 07:44:12 +00:00
Dogtiti
e49466fa05
feat: update real 'currentSession'
2024-11-04 21:25:56 +08:00
Dogtiti
44fc5b5cbf
fix: onfinish responseRes
2024-11-04 17:00:45 +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
e791cd441d
add xai
2024-10-23 11:55:25 +08:00
lloydzhou
8455fefc8a
add xai
2024-10-23 11:40:06 +08:00
lloydzhou
2419083adf
Merge remote-tracking branch 'connectai/main' into feature/H0llyW00dzZ-updater
2024-10-14 17:04:12 +08:00
Lloyd Zhou
b016771555
Merge pull request #5599 from ConnectAI-E/feature/allow-send-image-only
...
feat: allow send image only
2024-10-14 15:11:28 +08:00
code-october
6792d6e475
支持前端使能/禁用代码折叠
2024-10-11 11:19:36 +00:00
lloydzhou
2eebfcf6fe
client app tauri updater #2966
2024-10-11 11:29:22 +08:00
Lloyd Zhou
ba58018a15
Merge pull request #5211 from ConnectAI-E/feature/jest
...
feat: jest
2024-10-10 21:02:05 +08:00
lloydzhou
93ca303b6c
fix ts error
2024-10-09 13:49:33 +08:00
lloydzhou
a925b424a8
fix compressModel, related #5426 , fix #5606 #5603 #5575
2024-10-09 13:42:25 +08:00
Dogtiti
7d55a6d0e4
feat: allow send image only
2024-10-08 21:31:01 +08:00
Dogtiti
acf9fa36f9
Merge branch 'main' of https://github.com/ConnectAI-E/ChatGPT-Next-Web into feature/jest
2024-10-08 10:30:47 +08:00
lloydzhou
919ee51dca
hover show errorMsg when plugin run error
2024-10-01 13:58:50 +08:00
lloydzhou
6293b95a3b
update default api base url
2024-09-30 10:13:11 +08:00
lloydzhou
9be58f3eb4
fix ts error
2024-09-30 01:30:20 +08:00
lloydzhou
a50c282d01
remove DEFAULT_API_HOST
2024-09-30 01:19:20 +08:00
lloydzhou
b5f6e5a598
update
2024-09-30 00:38:30 +08:00
Lloyd Zhou
fcba50f041
Merge pull request #5547 from ConnectAI-E/hotfix/plugin-opration-id
...
Hotfix/plugin opration
2024-09-29 16:15:02 +08:00
Dogtiti
c6ebd6e73c
fix: default model
2024-09-27 17:00:24 +08:00
lloydzhou
22aa1698b4
try using method and path when operationId is undefined #5525
2024-09-27 13:31:49 +08:00
