@lobehub/chat 1.33.4 → 1.34.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.i18nrc.js +8 -2
- package/.releaserc.js +10 -1
- package/CHANGELOG.md +51 -16624
- package/changelog/CHANGELOG.v0.md +16621 -0
- package/changelog/v0.json +6064 -0
- package/changelog/v1.json +3356 -0
- package/docs/changelog/2024-11-25-november-providers.mdx +19 -0
- package/docs/changelog/2024-11-25-november-providers.zh-CN.mdx +17 -0
- package/docs/changelog/index.json +12 -0
- package/docs/changelog/schema.json +70 -0
- package/docs/self-hosting/advanced/auth/clerk.mdx +19 -23
- package/docs/self-hosting/advanced/auth/clerk.zh-CN.mdx +5 -4
- package/docs/self-hosting/advanced/auth/next-auth/authelia.mdx +2 -4
- package/docs/self-hosting/advanced/auth/next-auth/authelia.zh-CN.mdx +3 -5
- package/docs/self-hosting/advanced/auth/next-auth/authentik.zh-CN.mdx +2 -2
- package/docs/self-hosting/advanced/auth/next-auth/casdoor.mdx +49 -44
- package/docs/self-hosting/advanced/auth/next-auth/casdoor.zh-CN.mdx +42 -41
- package/docs/self-hosting/advanced/auth/next-auth/logto.mdx +29 -21
- package/docs/self-hosting/advanced/auth/next-auth/logto.zh-CN.mdx +2 -1
- package/docs/self-hosting/advanced/auth.mdx +10 -10
- package/docs/self-hosting/advanced/auth.zh-CN.mdx +10 -10
- package/docs/self-hosting/advanced/feature-flags.zh-CN.mdx +1 -1
- package/docs/self-hosting/advanced/model-list.mdx +1 -1
- package/docs/self-hosting/advanced/s3/cloudflare-r2.mdx +17 -12
- package/docs/self-hosting/advanced/s3/tencent-cloud.mdx +33 -20
- package/docs/self-hosting/advanced/s3.mdx +31 -28
- package/docs/self-hosting/advanced/s3.zh-CN.mdx +1 -0
- package/docs/self-hosting/advanced/webrtc.mdx +1 -0
- package/docs/self-hosting/environment-variables/s3.mdx +4 -3
- package/docs/self-hosting/environment-variables/s3.zh-CN.mdx +1 -0
- package/docs/self-hosting/environment-variables.mdx +6 -9
- package/docs/self-hosting/platform/alibaba-cloud.mdx +1 -2
- package/docs/self-hosting/platform/alibaba-cloud.zh-CN.mdx +1 -2
- package/docs/self-hosting/platform/btpanel.mdx +7 -13
- package/docs/self-hosting/platform/btpanel.zh-CN.mdx +8 -13
- package/docs/self-hosting/platform/docker.zh-CN.mdx +2 -1
- package/docs/self-hosting/platform/netlify.zh-CN.mdx +2 -1
- package/docs/self-hosting/server-database/docker.mdx +18 -5
- package/docs/self-hosting/server-database/docker.zh-CN.mdx +9 -6
- package/docs/self-hosting/server-database/netlify.mdx +0 -1
- package/docs/self-hosting/server-database/railway.mdx +0 -1
- package/docs/self-hosting/server-database/repocloud.mdx +5 -2
- package/docs/self-hosting/server-database/repocloud.zh-CN.mdx +23 -3
- package/docs/self-hosting/server-database/sealos.mdx +3 -0
- package/docs/self-hosting/server-database/vercel.mdx +35 -32
- package/docs/self-hosting/server-database/vercel.zh-CN.mdx +25 -25
- package/docs/self-hosting/server-database/zeabur.mdx +2 -2
- package/docs/self-hosting/server-database/zeabur.zh-CN.mdx +3 -4
- package/docs/self-hosting/server-database.mdx +23 -8
- package/docs/self-hosting/start.mdx +8 -2
- package/docs/usage/features/database.zh-CN.mdx +1 -1
- package/docs/usage/foundation/text2image.mdx +1 -2
- package/docs/usage/foundation/text2image.zh-CN.mdx +1 -3
- package/docs/usage/providers/ai21.mdx +14 -15
- package/docs/usage/providers/ai21.zh-CN.mdx +1 -3
- package/docs/usage/providers/ai360.mdx +14 -15
- package/docs/usage/providers/ai360.zh-CN.mdx +1 -3
- package/docs/usage/providers/cloudflare.mdx +1 -1
- package/docs/usage/providers/fireworksai.mdx +19 -19
- package/docs/usage/providers/fireworksai.zh-CN.mdx +1 -3
- package/docs/usage/providers/github.mdx +22 -21
- package/docs/usage/providers/github.zh-CN.mdx +6 -6
- package/docs/usage/providers/hunyuan.mdx +17 -18
- package/docs/usage/providers/hunyuan.zh-CN.mdx +1 -3
- package/docs/usage/providers/siliconcloud.mdx +14 -15
- package/docs/usage/providers/siliconcloud.zh-CN.mdx +3 -5
- package/docs/usage/providers/spark.mdx +17 -18
- package/docs/usage/providers/spark.zh-CN.mdx +1 -3
- package/docs/usage/providers/upstage.mdx +14 -15
- package/docs/usage/providers/upstage.zh-CN.mdx +1 -3
- package/docs/usage/providers/wenxin.mdx +17 -18
- package/docs/usage/providers/wenxin.zh-CN.mdx +1 -3
- package/docs/usage/providers/zeroone.mdx +2 -2
- package/locales/ar/chat.json +7 -0
- package/locales/ar/common.json +2 -0
- package/locales/ar/models.json +24 -0
- package/locales/ar/providers.json +3 -0
- package/locales/ar/setting.json +5 -0
- package/locales/ar/thread.json +5 -0
- package/locales/bg-BG/chat.json +7 -0
- package/locales/bg-BG/common.json +2 -0
- package/locales/bg-BG/models.json +24 -0
- package/locales/bg-BG/providers.json +3 -0
- package/locales/bg-BG/setting.json +5 -0
- package/locales/bg-BG/thread.json +5 -0
- package/locales/de-DE/chat.json +7 -0
- package/locales/de-DE/common.json +2 -0
- package/locales/de-DE/models.json +24 -0
- package/locales/de-DE/providers.json +3 -0
- package/locales/de-DE/setting.json +5 -0
- package/locales/de-DE/thread.json +5 -0
- package/locales/en-US/chat.json +7 -0
- package/locales/en-US/common.json +2 -0
- package/locales/en-US/models.json +24 -0
- package/locales/en-US/providers.json +3 -0
- package/locales/en-US/setting.json +5 -0
- package/locales/en-US/thread.json +5 -0
- package/locales/es-ES/chat.json +7 -0
- package/locales/es-ES/common.json +2 -0
- package/locales/es-ES/models.json +24 -0
- package/locales/es-ES/providers.json +3 -0
- package/locales/es-ES/setting.json +5 -0
- package/locales/es-ES/thread.json +5 -0
- package/locales/fa-IR/chat.json +7 -0
- package/locales/fa-IR/common.json +2 -0
- package/locales/fa-IR/models.json +24 -0
- package/locales/fa-IR/providers.json +3 -0
- package/locales/fa-IR/setting.json +5 -0
- package/locales/fa-IR/thread.json +5 -0
- package/locales/fr-FR/chat.json +7 -0
- package/locales/fr-FR/common.json +2 -0
- package/locales/fr-FR/models.json +24 -0
- package/locales/fr-FR/providers.json +3 -0
- package/locales/fr-FR/setting.json +5 -0
- package/locales/fr-FR/thread.json +5 -0
- package/locales/it-IT/chat.json +7 -0
- package/locales/it-IT/common.json +2 -0
- package/locales/it-IT/models.json +24 -0
- package/locales/it-IT/providers.json +3 -0
- package/locales/it-IT/setting.json +5 -0
- package/locales/it-IT/thread.json +5 -0
- package/locales/ja-JP/chat.json +7 -0
- package/locales/ja-JP/common.json +2 -0
- package/locales/ja-JP/models.json +24 -0
- package/locales/ja-JP/providers.json +3 -0
- package/locales/ja-JP/setting.json +5 -0
- package/locales/ja-JP/thread.json +5 -0
- package/locales/ko-KR/chat.json +7 -0
- package/locales/ko-KR/common.json +2 -0
- package/locales/ko-KR/models.json +24 -0
- package/locales/ko-KR/providers.json +3 -0
- package/locales/ko-KR/setting.json +5 -0
- package/locales/ko-KR/thread.json +5 -0
- package/locales/nl-NL/chat.json +7 -0
- package/locales/nl-NL/common.json +2 -0
- package/locales/nl-NL/models.json +24 -0
- package/locales/nl-NL/providers.json +3 -0
- package/locales/nl-NL/setting.json +5 -0
- package/locales/nl-NL/thread.json +5 -0
- package/locales/pl-PL/chat.json +7 -0
- package/locales/pl-PL/common.json +2 -0
- package/locales/pl-PL/models.json +24 -0
- package/locales/pl-PL/providers.json +3 -0
- package/locales/pl-PL/setting.json +5 -0
- package/locales/pl-PL/thread.json +5 -0
- package/locales/pt-BR/chat.json +7 -0
- package/locales/pt-BR/common.json +2 -0
- package/locales/pt-BR/models.json +24 -0
- package/locales/pt-BR/providers.json +3 -0
- package/locales/pt-BR/setting.json +5 -0
- package/locales/pt-BR/thread.json +5 -0
- package/locales/ru-RU/chat.json +7 -0
- package/locales/ru-RU/common.json +2 -0
- package/locales/ru-RU/models.json +24 -0
- package/locales/ru-RU/providers.json +3 -0
- package/locales/ru-RU/setting.json +5 -0
- package/locales/ru-RU/thread.json +5 -0
- package/locales/tr-TR/chat.json +7 -0
- package/locales/tr-TR/common.json +2 -0
- package/locales/tr-TR/models.json +24 -0
- package/locales/tr-TR/providers.json +3 -0
- package/locales/tr-TR/setting.json +5 -0
- package/locales/tr-TR/thread.json +5 -0
- package/locales/vi-VN/chat.json +7 -0
- package/locales/vi-VN/common.json +2 -0
- package/locales/vi-VN/models.json +24 -0
- package/locales/vi-VN/providers.json +3 -0
- package/locales/vi-VN/setting.json +5 -0
- package/locales/vi-VN/thread.json +5 -0
- package/locales/zh-CN/chat.json +7 -0
- package/locales/zh-CN/common.json +2 -0
- package/locales/zh-CN/models.json +24 -0
- package/locales/zh-CN/providers.json +3 -0
- package/locales/zh-CN/setting.json +5 -0
- package/locales/zh-CN/thread.json +5 -0
- package/locales/zh-TW/chat.json +7 -0
- package/locales/zh-TW/common.json +2 -0
- package/locales/zh-TW/models.json +24 -0
- package/locales/zh-TW/providers.json +3 -0
- package/locales/zh-TW/setting.json +5 -0
- package/locales/zh-TW/thread.json +5 -0
- package/package.json +6 -1
- package/scripts/changelogWorkflow/buildStaticChangelog.ts +135 -0
- package/scripts/changelogWorkflow/const.ts +11 -0
- package/scripts/changelogWorkflow/index.ts +10 -0
- package/src/app/(main)/chat/(workspace)/@conversation/default.tsx +2 -0
- package/src/app/(main)/chat/(workspace)/@conversation/features/ChatHydration/index.tsx +11 -2
- package/src/{features → app/(main)/chat/(workspace)/@conversation/features}/ChatInput/Desktop/Footer/index.tsx +7 -9
- package/src/app/(main)/chat/(workspace)/@conversation/features/ChatInput/Desktop/index.tsx +7 -2
- package/src/app/(main)/chat/(workspace)/@conversation/features/ChatList/ChatItem/Thread.tsx +62 -0
- package/src/app/(main)/chat/(workspace)/@conversation/features/ChatList/ChatItem/ThreadItem.tsx +68 -0
- package/src/app/(main)/chat/(workspace)/@conversation/features/ChatList/ChatItem/index.tsx +62 -2
- package/src/app/(main)/chat/(workspace)/@conversation/features/ThreadHydration.tsx +47 -0
- package/src/app/(main)/chat/(workspace)/@portal/_layout/Desktop.tsx +3 -2
- package/src/app/(main)/chat/(workspace)/@portal/_layout/Mobile.tsx +47 -6
- package/src/app/(main)/chat/(workspace)/@topic/features/SkeletonList.tsx +3 -2
- package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/ByTimeMode/index.tsx +10 -3
- package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/FlatMode/index.tsx +1 -1
- package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/ThreadItem/Content.tsx +164 -0
- package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/ThreadItem/index.tsx +98 -0
- package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/{TopicItem.tsx → TopicItem/index.tsx} +33 -22
- package/src/app/(main)/chat/(workspace)/_layout/Desktop/Portal.tsx +12 -5
- package/src/app/(main)/chat/(workspace)/_layout/Mobile/index.tsx +1 -2
- package/src/const/message.ts +2 -0
- package/src/const/settings/systemAgent.ts +1 -0
- package/src/database/server/migrations/0012_add_thread.sql +39 -0
- package/src/database/server/migrations/meta/0012_snapshot.json +3671 -0
- package/src/database/server/migrations/meta/_journal.json +7 -0
- package/src/database/server/models/_template.ts +2 -2
- package/src/database/server/models/message.ts +1 -0
- package/src/database/server/models/thread.ts +79 -0
- package/src/database/server/schemas/lobechat/message.ts +2 -1
- package/src/database/server/schemas/lobechat/relations.ts +13 -1
- package/src/database/server/schemas/lobechat/topic.ts +30 -1
- package/src/database/server/utils/idGenerator.ts +1 -0
- package/src/features/ChatInput/ActionBar/Token/TokenTag.tsx +6 -4
- package/src/features/ChatInput/ActionBar/Token/index.tsx +24 -5
- package/src/features/ChatInput/ActionBar/config.ts +3 -2
- package/src/features/ChatInput/Desktop/index.tsx +15 -7
- package/src/features/ChatInput/Mobile/index.tsx +4 -4
- package/src/features/Conversation/Actions/Assistant.tsx +24 -5
- package/src/features/Conversation/Actions/User.tsx +21 -4
- package/src/features/Conversation/Actions/index.ts +1 -66
- package/src/features/Conversation/Messages/{Tool → Assistant/ToolCallItem}/Inspector/index.tsx +3 -1
- package/src/features/Conversation/Messages/{Tool/index.tsx → Assistant/ToolCallItem/Tool.tsx} +10 -11
- package/src/features/Conversation/Messages/Assistant/ToolCallItem/index.tsx +5 -3
- package/src/features/Conversation/Messages/Assistant/index.tsx +22 -14
- package/src/features/Conversation/Messages/index.ts +0 -2
- package/src/features/Conversation/components/AutoScroll.tsx +1 -1
- package/src/features/Conversation/components/ChatItem/ActionsBar.tsx +79 -5
- package/src/features/Conversation/components/ChatItem/InPortalThreadContext.ts +3 -0
- package/src/features/Conversation/components/ChatItem/index.tsx +16 -5
- package/src/features/Conversation/components/MarkdownElements/LobeArtifact/Render/index.tsx +9 -1
- package/src/features/Conversation/components/ThreadDivider/index.tsx +19 -0
- package/src/features/Conversation/hooks/useChatListActionsBar.tsx +19 -4
- package/src/features/Portal/Thread/Chat/ChatInput/Footer.tsx +90 -0
- package/src/features/Portal/Thread/Chat/ChatInput/TextArea.tsx +30 -0
- package/src/features/Portal/Thread/Chat/ChatInput/index.tsx +66 -0
- package/src/features/Portal/Thread/Chat/ChatInput/useSend.ts +50 -0
- package/src/features/Portal/Thread/Chat/ChatItem.tsx +62 -0
- package/src/features/Portal/Thread/Chat/ChatList.tsx +49 -0
- package/src/features/Portal/Thread/Chat/ThreadDivider/index.tsx +19 -0
- package/src/features/Portal/Thread/Chat/index.tsx +28 -0
- package/src/features/Portal/Thread/Header/Active.tsx +35 -0
- package/src/features/Portal/Thread/Header/New.tsx +37 -0
- package/src/features/Portal/Thread/Header/Title.tsx +18 -0
- package/src/features/Portal/Thread/Header/index.tsx +20 -0
- package/src/features/Portal/Thread/hook.ts +8 -0
- package/src/features/Portal/Thread/index.ts +12 -0
- package/src/features/Portal/router.tsx +2 -1
- package/src/hooks/useFetchTopics.ts +7 -1
- package/src/locales/default/chat.ts +8 -1
- package/src/locales/default/common.ts +3 -0
- package/src/locales/default/index.ts +2 -0
- package/src/locales/default/setting.ts +5 -0
- package/src/locales/default/thread.ts +5 -0
- package/src/server/routers/lambda/index.ts +2 -0
- package/src/server/routers/lambda/thread.ts +83 -0
- package/src/services/thread.ts +54 -0
- package/src/store/chat/initialState.ts +3 -0
- package/src/store/chat/selectors.ts +2 -1
- package/src/store/chat/slices/aiChat/actions/__tests__/generateAIChat.test.ts +1 -1
- package/src/store/chat/slices/aiChat/actions/__tests__/rag.test.ts +1 -1
- package/src/store/chat/slices/aiChat/actions/generateAIChat.ts +31 -8
- package/src/store/chat/slices/aiChat/actions/rag.ts +1 -1
- package/src/store/chat/slices/message/selectors.test.ts +3 -3
- package/src/store/chat/slices/message/selectors.ts +50 -29
- package/src/store/chat/slices/plugin/action.ts +26 -8
- package/src/store/chat/slices/portal/action.ts +1 -0
- package/src/store/chat/slices/portal/initialState.ts +1 -0
- package/src/store/chat/slices/portal/selectors/thread.ts +17 -0
- package/src/store/chat/slices/portal/selectors.ts +2 -0
- package/src/store/chat/slices/thread/action.ts +326 -0
- package/src/store/chat/slices/thread/initialState.ts +34 -0
- package/src/store/chat/slices/thread/reducer.ts +48 -0
- package/src/store/chat/slices/thread/selectors/index.ts +202 -0
- package/src/store/chat/slices/thread/selectors/util.ts +22 -0
- package/src/store/chat/slices/topic/action.ts +5 -1
- package/src/store/chat/store.ts +5 -2
- package/src/store/global/initialState.ts +4 -0
- package/src/store/global/selectors.ts +4 -0
- package/src/store/user/slices/settings/selectors/systemAgent.ts +2 -0
- package/src/types/message/index.ts +17 -1
- package/src/types/topic/index.ts +1 -0
- package/src/types/topic/thread.ts +42 -0
- package/src/types/user/settings/systemAgent.ts +1 -0
- package/src/app/(main)/chat/(workspace)/@portal/features/Header.tsx +0 -11
- package/src/app/(main)/chat/(workspace)/_layout/Mobile/PortalModal.tsx +0 -35
- /package/src/{features → app/(main)/chat/(workspace)/@conversation/features}/ChatInput/Desktop/Footer/SendMore.tsx +0 -0
- /package/src/{features → app/(main)/chat/(workspace)/@conversation/features}/ChatInput/Desktop/Footer/ShortcutHint.tsx +0 -0
- /package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/{DefaultContent.tsx → TopicItem/DefaultContent.tsx} +0 -0
- /package/src/app/(main)/chat/(workspace)/@topic/features/TopicListContent/{TopicContent.tsx → TopicItem/TopicContent.tsx} +0 -0
- /package/src/features/Conversation/Messages/{Tool → Assistant/ToolCallItem}/Inspector/PluginResultJSON.tsx +0 -0
- /package/src/features/Conversation/Messages/{Tool → Assistant/ToolCallItem}/Inspector/Settings.tsx +0 -0
- /package/src/features/Conversation/Messages/{Tool → Assistant/ToolCallItem}/Inspector/style.ts +0 -0
@@ -9,13 +9,12 @@ tags:
|
|
9
9
|
- API Key
|
10
10
|
- Web UI
|
11
11
|
---
|
12
|
+
|
12
13
|
# Using AI21 Labs in LobeChat
|
13
14
|
|
14
15
|
<Image
|
15
|
-
cover
|
16
|
-
src={
|
17
|
-
'https://github.com/user-attachments/assets/ae03eab5-a319-4d2a-a5f6-1683ab7739ee'
|
18
|
-
}
|
16
|
+
cover
|
17
|
+
src={'https://github.com/user-attachments/assets/ae03eab5-a319-4d2a-a5f6-1683ab7739ee'}
|
19
18
|
/>
|
20
19
|
|
21
20
|
[AI21 Labs](https://www.ai21.com/) is a company focused on artificial intelligence, offering advanced language models and API services designed to help developers and businesses leverage natural language processing technology. Their flagship product, the "Jamba" series of models, can perform complex language understanding and generation tasks, widely utilized in fields such as content creation and conversational systems.
|
@@ -30,9 +29,9 @@ This article will guide you on how to use AI21 Labs within LobeChat.
|
|
30
29
|
- Copy and save the generated API key
|
31
30
|
|
32
31
|
<Image
|
33
|
-
alt={'Copy API Key'}
|
34
|
-
inStep
|
35
|
-
src={'https://github.com/user-attachments/assets/a42ba52b-491e-4993-8e2f-217aa1776e0f'}
|
32
|
+
alt={'Copy API Key'}
|
33
|
+
inStep
|
34
|
+
src={'https://github.com/user-attachments/assets/a42ba52b-491e-4993-8e2f-217aa1776e0f'}
|
36
35
|
/>
|
37
36
|
|
38
37
|
### Step 2: Configure AI21 Labs in LobeChat
|
@@ -41,25 +40,25 @@ src={'https://github.com/user-attachments/assets/a42ba52b-491e-4993-8e2f-217aa17
|
|
41
40
|
- Under `Language Model`, find the setting for `AI21 Labs`
|
42
41
|
|
43
42
|
<Image
|
44
|
-
alt={'Enter API Key'}
|
45
|
-
inStep
|
46
|
-
src={'https://github.com/user-attachments/assets/9336d6c5-2a83-4aa9-854e-75e245b665cb'}
|
43
|
+
alt={'Enter API Key'}
|
44
|
+
inStep
|
45
|
+
src={'https://github.com/user-attachments/assets/9336d6c5-2a83-4aa9-854e-75e245b665cb'}
|
47
46
|
/>
|
48
47
|
|
49
48
|
- Enter the API key you obtained
|
50
49
|
- Choose an AI21 Labs model for your AI assistant to begin the conversation
|
51
50
|
|
52
51
|
<Image
|
53
|
-
alt={'Select AI21 Labs Model and Start Conversation'}
|
54
|
-
inStep
|
55
|
-
src={'https://github.com/user-attachments/assets/63e5ced7-1d23-44e1-b933-cc3b5df47eab'}
|
52
|
+
alt={'Select AI21 Labs Model and Start Conversation'}
|
53
|
+
inStep
|
54
|
+
src={'https://github.com/user-attachments/assets/63e5ced7-1d23-44e1-b933-cc3b5df47eab'}
|
56
55
|
/>
|
57
56
|
|
58
57
|
<Callout type={'warning'}>
|
59
|
-
During use, you may need to pay the API service provider; please refer to the relevant fee policy
|
58
|
+
During use, you may need to pay the API service provider; please refer to the relevant fee policy
|
59
|
+
of AI21 Labs.
|
60
60
|
</Callout>
|
61
61
|
|
62
62
|
</Steps>
|
63
63
|
|
64
64
|
Now you are ready to engage in conversations using the models provided by AI21 Labs in LobeChat.
|
65
|
-
|
@@ -12,9 +12,7 @@ tags:
|
|
12
12
|
|
13
13
|
<Image
|
14
14
|
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/ae03eab5-a319-4d2a-a5f6-1683ab7739ee'
|
17
|
-
}
|
15
|
+
src={'https://github.com/user-attachments/assets/ae03eab5-a319-4d2a-a5f6-1683ab7739ee'}
|
18
16
|
/>
|
19
17
|
|
20
18
|
[AI21 Labs](https://www.ai21.com/) 是一家专注于人工智能的公司,提供先进的语言模型和API服务,旨在帮助开发者和企业利用自然语言处理技术。其旗舰产品 "Jamba" 系列模型能够进行复杂的语言理解和生成任务,广泛应用于内容创作、对话系统等领域。
|
@@ -7,13 +7,12 @@ tags:
|
|
7
7
|
- API Key
|
8
8
|
- Web UI
|
9
9
|
---
|
10
|
+
|
10
11
|
# Using the 360AI in LobeChat
|
11
12
|
|
12
13
|
<Image
|
13
|
-
cover
|
14
|
-
src={
|
15
|
-
'https://github.com/user-attachments/assets/e617def1-ce50-4acc-974b-12f5ed592a0e'
|
16
|
-
}
|
14
|
+
cover
|
15
|
+
src={'https://github.com/user-attachments/assets/e617def1-ce50-4acc-974b-12f5ed592a0e'}
|
17
16
|
/>
|
18
17
|
|
19
18
|
The [360AI](https://ai.360.com/) is a cognitive general model independently developed by 360 Company, aimed at providing powerful natural language processing capabilities for enterprises and developers. This model has been upgraded to version 4.0 and supports various application scenarios, including conversational services, image generation, vector database services, and more.
|
@@ -28,9 +27,9 @@ This article will guide you on how to use the 360AI in LobeChat.
|
|
28
27
|
- Create an API key and copy it
|
29
28
|
|
30
29
|
<Image
|
31
|
-
alt={'Create API Key'}
|
32
|
-
inStep
|
33
|
-
src={'https://github.com/user-attachments/assets/72da7af1-e180-4759-84a5-a6f6ca28392e'}
|
30
|
+
alt={'Create API Key'}
|
31
|
+
inStep
|
32
|
+
src={'https://github.com/user-attachments/assets/72da7af1-e180-4759-84a5-a6f6ca28392e'}
|
34
33
|
/>
|
35
34
|
|
36
35
|
### Step 2: Configure 360AI in LobeChat
|
@@ -39,25 +38,25 @@ src={'https://github.com/user-attachments/assets/72da7af1-e180-4759-84a5-a6f6ca2
|
|
39
38
|
- Under `Language Models`, find the option for `360`
|
40
39
|
|
41
40
|
<Image
|
42
|
-
alt={'Enter API Key'}
|
43
|
-
inStep
|
44
|
-
src={'https://github.com/user-attachments/assets/a53deb11-2c14-441a-8a5c-a0f3a74e2a63'}
|
41
|
+
alt={'Enter API Key'}
|
42
|
+
inStep
|
43
|
+
src={'https://github.com/user-attachments/assets/a53deb11-2c14-441a-8a5c-a0f3a74e2a63'}
|
45
44
|
/>
|
46
45
|
|
47
46
|
- Enter the API key you obtained
|
48
47
|
- Choose a 360AI model for your AI assistant to start chatting
|
49
48
|
|
50
49
|
<Image
|
51
|
-
alt={'Select 360 Model and Start Chatting'}
|
52
|
-
inStep
|
53
|
-
src={'https://github.com/user-attachments/assets/452d0b48-5ff7-4f42-a46e-68a62b87632b'}
|
50
|
+
alt={'Select 360 Model and Start Chatting'}
|
51
|
+
inStep
|
52
|
+
src={'https://github.com/user-attachments/assets/452d0b48-5ff7-4f42-a46e-68a62b87632b'}
|
54
53
|
/>
|
55
54
|
|
56
55
|
<Callout type={'warning'}>
|
57
|
-
Please note that you may need to pay the API service provider during use, refer to the relevant
|
56
|
+
Please note that you may need to pay the API service provider during use, refer to the relevant
|
57
|
+
pricing policy of the 360AI.
|
58
58
|
</Callout>
|
59
59
|
|
60
60
|
</Steps>
|
61
61
|
|
62
62
|
You can now use the models provided by the 360AI for conversations in LobeChat.
|
63
|
-
|
@@ -12,9 +12,7 @@ tags:
|
|
12
12
|
|
13
13
|
<Image
|
14
14
|
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/e617def1-ce50-4acc-974b-12f5ed592a0e'
|
17
|
-
}
|
15
|
+
src={'https://github.com/user-attachments/assets/e617def1-ce50-4acc-974b-12f5ed592a0e'}
|
18
16
|
/>
|
19
17
|
|
20
18
|
[360智脑](https://ai.360.com/)是360公司自主研发的认知型通用大模型,旨在为企业和开发者提供强大的自然语言处理能力。该模型已升级至4.0版本,能够支持多种应用场景,包括对话服务、图片生成、向量数据库服务等。
|
@@ -48,7 +48,7 @@ This document will guide you on how to use Cloudflare Workers AI in LobeChat:
|
|
48
48
|
<Callout type={"warning"}>
|
49
49
|
|
50
50
|
- Please store your API token securely, as it will only be displayed once. If you accidentally lose it, you will need to create a new token.
|
51
|
-
|
51
|
+
|
52
52
|
</Callout>
|
53
53
|
|
54
54
|
### Step 2: Configure Cloudflare Workers AI in LobeChat
|
@@ -9,13 +9,12 @@ tags:
|
|
9
9
|
- API Key
|
10
10
|
- Web UI
|
11
11
|
---
|
12
|
+
|
12
13
|
# Using Fireworks AI in LobeChat
|
13
14
|
|
14
15
|
<Image
|
15
|
-
cover
|
16
|
-
src={
|
17
|
-
'https://github.com/user-attachments/assets/facdc83c-e789-4649-8060-7f7a10a1b1dd'
|
18
|
-
}
|
16
|
+
cover
|
17
|
+
src={'https://github.com/user-attachments/assets/facdc83c-e789-4649-8060-7f7a10a1b1dd'}
|
19
18
|
/>
|
20
19
|
|
21
20
|
[Fireworks.ai](https://fireworks.ai/) is a high-performance generative AI model inference platform that allows users to access and utilize various models through its API. The platform supports multiple modalities, including text and visual language models, and offers features like function calls and JSON schemas to enhance the flexibility of application development.
|
@@ -30,21 +29,22 @@ This article will guide you on how to use Fireworks AI in LobeChat.
|
|
30
29
|
- Create a new API key
|
31
30
|
|
32
31
|
<Image
|
33
|
-
alt={'Create API Key'}
|
34
|
-
inStep
|
35
|
-
src={'https://github.com/user-attachments/assets/eb027093-5ceb-4a9d-8850-b791fbf69a71'}
|
32
|
+
alt={'Create API Key'}
|
33
|
+
inStep
|
34
|
+
src={'https://github.com/user-attachments/assets/eb027093-5ceb-4a9d-8850-b791fbf69a71'}
|
36
35
|
/>
|
37
36
|
|
38
37
|
- Copy and securely save the generated API key
|
39
38
|
|
40
39
|
<Image
|
41
|
-
alt={'Save API Key'}
|
42
|
-
inStep
|
43
|
-
src={'https://github.com/user-attachments/assets/28590f7f-bfee-4215-b50b-8feddbf72366'}
|
40
|
+
alt={'Save API Key'}
|
41
|
+
inStep
|
42
|
+
src={'https://github.com/user-attachments/assets/28590f7f-bfee-4215-b50b-8feddbf72366'}
|
44
43
|
/>
|
45
44
|
|
46
45
|
<Callout type={'warning'}>
|
47
|
-
Please store the key securely, as it will appear only once. If you accidentally lose it, you will
|
46
|
+
Please store the key securely, as it will appear only once. If you accidentally lose it, you will
|
47
|
+
need to create a new key.
|
48
48
|
</Callout>
|
49
49
|
|
50
50
|
### Step 2: Configure Fireworks AI in LobeChat
|
@@ -53,25 +53,25 @@ Please store the key securely, as it will appear only once. If you accidentally
|
|
53
53
|
- Under `Language Model`, locate the settings for `Fireworks AI`
|
54
54
|
|
55
55
|
<Image
|
56
|
-
alt={'Enter API Key'}
|
57
|
-
inStep
|
58
|
-
src={'https://github.com/user-attachments/assets/12c1957d-f050-4235-95da-d55ddedfa6c9'}
|
56
|
+
alt={'Enter API Key'}
|
57
|
+
inStep
|
58
|
+
src={'https://github.com/user-attachments/assets/12c1957d-f050-4235-95da-d55ddedfa6c9'}
|
59
59
|
/>
|
60
60
|
|
61
61
|
- Enter the obtained API key
|
62
62
|
- Select a Fireworks AI model for your AI assistant to start a conversation
|
63
63
|
|
64
64
|
<Image
|
65
|
-
alt={'Select Fireworks AI Model and Start Conversation'}
|
66
|
-
inStep
|
67
|
-
src={'https://github.com/user-attachments/assets/378df8df-8ec4-436e-8451-fbc52705faee'}
|
65
|
+
alt={'Select Fireworks AI Model and Start Conversation'}
|
66
|
+
inStep
|
67
|
+
src={'https://github.com/user-attachments/assets/378df8df-8ec4-436e-8451-fbc52705faee'}
|
68
68
|
/>
|
69
69
|
|
70
70
|
<Callout type={'warning'}>
|
71
|
-
Please note that you may need to pay fees to the API service provider during use; refer to
|
71
|
+
Please note that you may need to pay fees to the API service provider during use; refer to
|
72
|
+
Fireworks AI's pricing policy for details.
|
72
73
|
</Callout>
|
73
74
|
|
74
75
|
</Steps>
|
75
76
|
|
76
77
|
You are now ready to use the models provided by Fireworks AI for conversations in LobeChat.
|
77
|
-
|
@@ -12,9 +12,7 @@ tags:
|
|
12
12
|
|
13
13
|
<Image
|
14
14
|
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/facdc83c-e789-4649-8060-7f7a10a1b1dd'
|
17
|
-
}
|
15
|
+
src={'https://github.com/user-attachments/assets/facdc83c-e789-4649-8060-7f7a10a1b1dd'}
|
18
16
|
/>
|
19
17
|
|
20
18
|
[Fireworks.ai](https://fireworks.ai/) 是一个高性能的生成式 AI 模型推理平台,允许用户通过其 API 访问和使用各种模型。该平台支持多种模态,包括文本和视觉语言模型,并提供函数调用和 JSON 模式等功能,以增强应用开发的灵活性。
|
@@ -8,13 +8,12 @@ tags:
|
|
8
8
|
- API Key
|
9
9
|
- Web UI
|
10
10
|
---
|
11
|
+
|
11
12
|
# Using GitHub Models in LobeChat
|
12
13
|
|
13
14
|
<Image
|
14
|
-
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/3050839a-cb16-485d-8bae-1bc2f9ade632'
|
17
|
-
}
|
15
|
+
cover
|
16
|
+
src={'https://github.com/user-attachments/assets/3050839a-cb16-485d-8bae-1bc2f9ade632'}
|
18
17
|
/>
|
19
18
|
|
20
19
|
[GitHub Models](https://github.com/marketplace/models) is a new feature recently launched by GitHub, designed to provide developers with a free platform to access and experiment with various AI models. GitHub Models offers an interactive sandbox environment where users can test different model parameters and prompts, and observe the responses of the models. The platform supports advanced language models, including OpenAI's GPT-4o, Meta's Llama 3.1, and Mistral's Large 2, covering a wide range of applications from large-scale language models to task-specific models.
|
@@ -26,13 +25,15 @@ This article will guide you on how to use GitHub Models in LobeChat.
|
|
26
25
|
Currently, the usage of the Playground and free API is subject to limits on the number of requests per minute, the number of requests per day, the number of tokens per request, and the number of concurrent requests. If you hit the rate limit, you will need to wait for the limit to reset before making further requests. The rate limits vary for different models (low, high, and embedding models). For model type information, please refer to the GitHub Marketplace.
|
27
26
|
|
28
27
|
<Image
|
29
|
-
alt={'GitHub Models Rate Limits'}
|
30
|
-
inStep
|
31
|
-
src={'https://github.com/user-attachments/assets/21c52e2a-b2f8-4de8-a5d4-cf3444608db7'}
|
28
|
+
alt={'GitHub Models Rate Limits'}
|
29
|
+
inStep
|
30
|
+
src={'https://github.com/user-attachments/assets/21c52e2a-b2f8-4de8-a5d4-cf3444608db7'}
|
32
31
|
/>
|
33
32
|
|
34
33
|
<Callout type="note">
|
35
|
-
These limits are subject to change at any time. For specific information, please refer to the
|
34
|
+
These limits are subject to change at any time. For specific information, please refer to the
|
35
|
+
[GitHub Official
|
36
|
+
Documentation](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits).
|
36
37
|
</Callout>
|
37
38
|
|
38
39
|
---
|
@@ -46,17 +47,17 @@ src={'https://github.com/user-attachments/assets/21c52e2a-b2f8-4de8-a5d4-cf34446
|
|
46
47
|
- Create and configure a new access token.
|
47
48
|
|
48
49
|
<Image
|
49
|
-
alt={'Creating Access Token'}
|
50
|
-
inStep
|
51
|
-
src={'https://github.com/user-attachments/assets/8570db14-dac6-4279-ab71-04a072c15490'}
|
50
|
+
alt={'Creating Access Token'}
|
51
|
+
inStep
|
52
|
+
src={'https://github.com/user-attachments/assets/8570db14-dac6-4279-ab71-04a072c15490'}
|
52
53
|
/>
|
53
54
|
|
54
55
|
- Copy and save the generated token from the results returned.
|
55
56
|
|
56
57
|
<Image
|
57
|
-
alt={'Saving Access Token'}
|
58
|
-
inStep
|
59
|
-
src={'https://github.com/user-attachments/assets/3c1a492d-a3d4-4570-9e74-785c2942ca41'}
|
58
|
+
alt={'Saving Access Token'}
|
59
|
+
inStep
|
60
|
+
src={'https://github.com/user-attachments/assets/3c1a492d-a3d4-4570-9e74-785c2942ca41'}
|
60
61
|
/>
|
61
62
|
|
62
63
|
<Callout type={"warning"}>
|
@@ -64,6 +65,7 @@ src={'https://github.com/user-attachments/assets/3c1a492d-a3d4-4570-9e74-785c294
|
|
64
65
|
- During the testing phase of GitHub Models, users must apply to join the [waitlist](https://github.com/marketplace/models/waitlist/join) in order to gain access.
|
65
66
|
|
66
67
|
- Please store the access token securely, as it will only be displayed once. If you accidentally lose it, you will need to create a new token.
|
68
|
+
|
67
69
|
</Callout>
|
68
70
|
|
69
71
|
### Step 2: Configure GitHub Models in LobeChat
|
@@ -72,21 +74,20 @@ src={'https://github.com/user-attachments/assets/3c1a492d-a3d4-4570-9e74-785c294
|
|
72
74
|
- Under `Language Models`, find the GitHub settings.
|
73
75
|
|
74
76
|
<Image
|
75
|
-
alt={'Entering Access Token'}
|
76
|
-
inStep
|
77
|
-
src={'https://github.com/user-attachments/assets/a00f06cc-da7c-41e8-a4d5-d4b675a22673'}
|
77
|
+
alt={'Entering Access Token'}
|
78
|
+
inStep
|
79
|
+
src={'https://github.com/user-attachments/assets/a00f06cc-da7c-41e8-a4d5-d4b675a22673'}
|
78
80
|
/>
|
79
81
|
|
80
82
|
- Enter the access token you obtained.
|
81
83
|
- Select a GitHub model for your AI assistant to start the conversation.
|
82
84
|
|
83
85
|
<Image
|
84
|
-
alt={'Selecting GitHub Model and Starting Conversation'}
|
85
|
-
inStep
|
86
|
-
src={'https://github.com/user-attachments/assets/aead3c6c-891e-47c3-9f34-bdc33875e0c2'}
|
86
|
+
alt={'Selecting GitHub Model and Starting Conversation'}
|
87
|
+
inStep
|
88
|
+
src={'https://github.com/user-attachments/assets/aead3c6c-891e-47c3-9f34-bdc33875e0c2'}
|
87
89
|
/>
|
88
90
|
|
89
91
|
</Steps>
|
90
92
|
|
91
93
|
You are now ready to use the models provided by GitHub for conversations within LobeChat.
|
92
|
-
|
@@ -13,9 +13,7 @@ tags:
|
|
13
13
|
|
14
14
|
<Image
|
15
15
|
cover
|
16
|
-
src={
|
17
|
-
'https://github.com/user-attachments/assets/3050839a-cb16-485d-8bae-1bc2f9ade632'
|
18
|
-
}
|
16
|
+
src={'https://github.com/user-attachments/assets/3050839a-cb16-485d-8bae-1bc2f9ade632'}
|
19
17
|
/>
|
20
18
|
|
21
19
|
[GitHub Models](https://github.com/marketplace/models) 是 GitHub 最近推出的一项新功能,旨在为开发者提供一个免费的平台来访问和实验多种 AI 模型。GitHub Models 提供了一个互动沙盒环境,用户可以在此测试不同的模型参数和提示语,观察模型的响应。该平台支持多种先进的语言模型,包括 OpenAI 的 GPT-4o、Meta 的 Llama 3.1 和 Mistral 的 Large 2 等,覆盖了从大规模语言模型到特定任务模型的广泛应用。
|
@@ -24,7 +22,7 @@ tags:
|
|
24
22
|
|
25
23
|
## GitHub Models 速率限制
|
26
24
|
|
27
|
-
当前 Playground 和免费 API 的使用受到每分钟请求数、每日请求数、每个请求的令牌数以及并发请求数的限制。若达到速率限制,则需等待限制重置后方可继续发出请求。不同模型(低、高及嵌入模型)的速率限制有所不同。
|
25
|
+
当前 Playground 和免费 API 的使用受到每分钟请求数、每日请求数、每个请求的令牌数以及并发请求数的限制。若达到速率限制,则需等待限制重置后方可继续发出请求。不同模型(低、高及嵌入模型)的速率限制有所不同。 模型类型信息请参阅 GitHub Marketplace。
|
28
26
|
|
29
27
|
<Image
|
30
28
|
alt={'GitHub Models 速率限制'}
|
@@ -33,7 +31,8 @@ tags:
|
|
33
31
|
/>
|
34
32
|
|
35
33
|
<Callout type="note">
|
36
|
-
这些限制可能随时更改,具体信息请参考 [GitHub
|
34
|
+
这些限制可能随时更改,具体信息请参考 [GitHub
|
35
|
+
官方文档](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits)。
|
37
36
|
</Callout>
|
38
37
|
|
39
38
|
---
|
@@ -63,7 +62,8 @@ tags:
|
|
63
62
|
<Callout type={"warning"}>
|
64
63
|
- GitHub Models 测试期间,要使用 GitHub Models,用户需要申请加入[等待名单(waitlist)](https://github.com/marketplace/models/waitlist/join) 通过后才能获得访问权限。
|
65
64
|
|
66
|
-
|
65
|
+
- 请安全地存储访问令牌,因为它只会出现一次。如果您意外丢失它,您将需要创建一个新令牌。
|
66
|
+
|
67
67
|
</Callout>
|
68
68
|
|
69
69
|
### 步骤二:在 LobeChat 中配置 GitHub Models
|
@@ -9,13 +9,12 @@ tags:
|
|
9
9
|
- API Key
|
10
10
|
- Web UI
|
11
11
|
---
|
12
|
+
|
12
13
|
# Using Tencent Hunyuan in LobeChat
|
13
14
|
|
14
15
|
<Image
|
15
|
-
cover
|
16
|
-
src={
|
17
|
-
'https://github.com/user-attachments/assets/467bb431-ca0d-4bb4-ac17-e5e2b764a770'
|
18
|
-
}
|
16
|
+
cover
|
17
|
+
src={'https://github.com/user-attachments/assets/467bb431-ca0d-4bb4-ac17-e5e2b764a770'}
|
19
18
|
/>
|
20
19
|
|
21
20
|
[Tencent Hunyuan](https://hunyuan.tencent.com/) is a large model launched by Tencent, designed to provide users with intelligent assistant services. It utilizes natural language processing technology to help users solve problems, offer suggestions, and generate content. By conversing with the model, users can quickly access the information they need, thereby enhancing work efficiency.
|
@@ -30,17 +29,17 @@ This article will guide you on how to use Tencent Hunyuan in LobeChat.
|
|
30
29
|
- Create an API key
|
31
30
|
|
32
31
|
<Image
|
33
|
-
alt={'Create API Key'}
|
34
|
-
inStep
|
35
|
-
src={'https://github.com/user-attachments/assets/5f344314-ecbc-41e6-9120-520a2d5352ff'}
|
32
|
+
alt={'Create API Key'}
|
33
|
+
inStep
|
34
|
+
src={'https://github.com/user-attachments/assets/5f344314-ecbc-41e6-9120-520a2d5352ff'}
|
36
35
|
/>
|
37
36
|
|
38
37
|
- Click `View`, and copy the API key from the pop-up panel, ensuring you save it securely
|
39
38
|
|
40
39
|
<Image
|
41
|
-
alt={'Save Key'}
|
42
|
-
inStep
|
43
|
-
src={'https://github.com/user-attachments/assets/659b5ac1-82f1-43bd-9d4b-a98491e05794'}
|
40
|
+
alt={'Save Key'}
|
41
|
+
inStep
|
42
|
+
src={'https://github.com/user-attachments/assets/659b5ac1-82f1-43bd-9d4b-a98491e05794'}
|
44
43
|
/>
|
45
44
|
|
46
45
|
### Step 2: Configure Tencent Hunyuan in LobeChat
|
@@ -49,25 +48,25 @@ src={'https://github.com/user-attachments/assets/659b5ac1-82f1-43bd-9d4b-a98491e
|
|
49
48
|
- Find the `Tencent Hunyuan` settings under `Language Models`
|
50
49
|
|
51
50
|
<Image
|
52
|
-
alt={'Enter API Key'}
|
53
|
-
inStep
|
54
|
-
src={'https://github.com/user-attachments/assets/796c94af-9bad-4e3c-b1c7-dbb17c215c56'}
|
51
|
+
alt={'Enter API Key'}
|
52
|
+
inStep
|
53
|
+
src={'https://github.com/user-attachments/assets/796c94af-9bad-4e3c-b1c7-dbb17c215c56'}
|
55
54
|
/>
|
56
55
|
|
57
56
|
- Enter the API key you obtained
|
58
57
|
- Select a Tencent Hunyuan model for your AI assistant to start the conversation
|
59
58
|
|
60
59
|
<Image
|
61
|
-
alt={'Select Tencent Hunyuan Model and Start Conversation'}
|
62
|
-
inStep
|
63
|
-
src={'https://github.com/user-attachments/assets/e3f44bc8-2fa5-441d-8934-943481472450'}
|
60
|
+
alt={'Select Tencent Hunyuan Model and Start Conversation'}
|
61
|
+
inStep
|
62
|
+
src={'https://github.com/user-attachments/assets/e3f44bc8-2fa5-441d-8934-943481472450'}
|
64
63
|
/>
|
65
64
|
|
66
65
|
<Callout type={'warning'}>
|
67
|
-
During usage, you may need to pay the API service provider, please refer to Tencent Hunyuan's
|
66
|
+
During usage, you may need to pay the API service provider, please refer to Tencent Hunyuan's
|
67
|
+
relevant pricing policy.
|
68
68
|
</Callout>
|
69
69
|
|
70
70
|
</Steps>
|
71
71
|
|
72
72
|
You can now engage in conversations using the models provided by Tencent Hunyuan in LobeChat.
|
73
|
-
|
@@ -12,9 +12,7 @@ tags:
|
|
12
12
|
|
13
13
|
<Image
|
14
14
|
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/467bb431-ca0d-4bb4-ac17-e5e2b764a770'
|
17
|
-
}
|
15
|
+
src={'https://github.com/user-attachments/assets/467bb431-ca0d-4bb4-ac17-e5e2b764a770'}
|
18
16
|
/>
|
19
17
|
|
20
18
|
[腾讯混元](https://hunyuan.tencent.com/)是由腾讯推出的一款大模型,旨在为用户提供智能助手服务。它能够通过自然语言处理技术,帮助用户解决问题、提供建议以及进行内容生成等任务。用户可以通过与模型的对话,快速获取所需信息,从而提高工作效率。
|
@@ -9,13 +9,12 @@ tags:
|
|
9
9
|
- API Key
|
10
10
|
- Web UI
|
11
11
|
---
|
12
|
+
|
12
13
|
# Using SiliconCloud in LobeChat
|
13
14
|
|
14
15
|
<Image
|
15
|
-
cover
|
16
|
-
src={
|
17
|
-
'https://github.com/user-attachments/assets/9a78bbb9-7c96-4f32-9b66-e57f92660410'
|
18
|
-
}
|
16
|
+
cover
|
17
|
+
src={'https://github.com/user-attachments/assets/9a78bbb9-7c96-4f32-9b66-e57f92660410'}
|
19
18
|
/>
|
20
19
|
|
21
20
|
[SiliconCloud](https://siliconflow.cn/) is an AI service platform based on open-source foundational models, offering a variety of generative AI (GenAI) services.
|
@@ -30,9 +29,9 @@ This article will guide you on how to use SiliconCloud in LobeChat.
|
|
30
29
|
- Create an API Key and copy it
|
31
30
|
|
32
31
|
<Image
|
33
|
-
alt={'Create API Key'}
|
34
|
-
inStep
|
35
|
-
src={'https://github.com/user-attachments/assets/872756dc-305e-4e63-9fb7-60550280fc12'}
|
32
|
+
alt={'Create API Key'}
|
33
|
+
inStep
|
34
|
+
src={'https://github.com/user-attachments/assets/872756dc-305e-4e63-9fb7-60550280fc12'}
|
36
35
|
/>
|
37
36
|
|
38
37
|
### Step 2: Configure SiliconCloud in LobeChat
|
@@ -41,25 +40,25 @@ src={'https://github.com/user-attachments/assets/872756dc-305e-4e63-9fb7-6055028
|
|
41
40
|
- Under `Language Model`, find the setting for `SiliconFlow`
|
42
41
|
|
43
42
|
<Image
|
44
|
-
alt={'Enter API Key'}
|
45
|
-
inStep
|
46
|
-
src={'https://github.com/user-attachments/assets/4c792f62-5203-4f13-8f23-df228f70d67f'}
|
43
|
+
alt={'Enter API Key'}
|
44
|
+
inStep
|
45
|
+
src={'https://github.com/user-attachments/assets/4c792f62-5203-4f13-8f23-df228f70d67f'}
|
47
46
|
/>
|
48
47
|
|
49
48
|
- Enter the API Key you obtained
|
50
49
|
- Choose a SiliconCloud model for your AI assistant to start the conversation
|
51
50
|
|
52
51
|
<Image
|
53
|
-
alt={'Select SiliconCloud Model and Start Conversation'}
|
54
|
-
inStep
|
55
|
-
src={'https://github.com/user-attachments/assets/f4dbbadb-7461-4370-a836-09c487fdd206'}
|
52
|
+
alt={'Select SiliconCloud Model and Start Conversation'}
|
53
|
+
inStep
|
54
|
+
src={'https://github.com/user-attachments/assets/f4dbbadb-7461-4370-a836-09c487fdd206'}
|
56
55
|
/>
|
57
56
|
|
58
57
|
<Callout type={'warning'}>
|
59
|
-
During usage, you may need to pay the API service provider, so please refer to SiliconCloud's
|
58
|
+
During usage, you may need to pay the API service provider, so please refer to SiliconCloud's
|
59
|
+
relevant pricing policy.
|
60
60
|
</Callout>
|
61
61
|
|
62
62
|
</Steps>
|
63
63
|
|
64
64
|
At this point, you can start chatting using the models provided by SiliconCloud in LobeChat.
|
65
|
-
|
@@ -8,13 +8,11 @@ tags:
|
|
8
8
|
- Web UI
|
9
9
|
---
|
10
10
|
|
11
|
-
# 在 LobeChat 中使用 SiliconCloud
|
11
|
+
# 在 LobeChat 中使用 SiliconCloud
|
12
12
|
|
13
13
|
<Image
|
14
14
|
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/9a78bbb9-7c96-4f32-9b66-e57f92660410'
|
17
|
-
}
|
15
|
+
src={'https://github.com/user-attachments/assets/9a78bbb9-7c96-4f32-9b66-e57f92660410'}
|
18
16
|
/>
|
19
17
|
|
20
18
|
[SiliconCloud](https://siliconflow.cn/) 是一个基于开源基础模型的人工智能服务平台,提供多种生成式AI(GenAI)服务。
|
@@ -34,7 +32,7 @@ tags:
|
|
34
32
|
src={'https://github.com/user-attachments/assets/872756dc-305e-4e63-9fb7-60550280fc12'}
|
35
33
|
/>
|
36
34
|
|
37
|
-
### 步骤二:在 LobeChat 中配置 SiliconCloud
|
35
|
+
### 步骤二:在 LobeChat 中配置 SiliconCloud
|
38
36
|
|
39
37
|
- 访问 LobeChat 的`设置`界面
|
40
38
|
- 在`语言模型`下找到 `SiliconFlow` 的设置项
|
@@ -8,13 +8,12 @@ tags:
|
|
8
8
|
- API Key
|
9
9
|
- Web UI
|
10
10
|
---
|
11
|
+
|
11
12
|
# Using iFLYTEK Spark in LobeChat
|
12
13
|
|
13
14
|
<Image
|
14
|
-
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/f3068287-8ade-4eca-9841-ea67d8ff1226'
|
17
|
-
}
|
15
|
+
cover
|
16
|
+
src={'https://github.com/user-attachments/assets/f3068287-8ade-4eca-9841-ea67d8ff1226'}
|
18
17
|
/>
|
19
18
|
|
20
19
|
[iFLYTEK Spark](https://xinghuo.xfyun.cn/) is a powerful AI model launched by iFLYTEK, equipped with cross-domain knowledge and language understanding capabilities, able to perform various tasks such as Q&A, conversations, and literary creation.
|
@@ -28,18 +27,18 @@ This guide will instruct you on how to use iFLYTEK Spark in LobeChat.
|
|
28
27
|
- Create an application
|
29
28
|
|
30
29
|
<Image
|
31
|
-
alt={'Create Application'}
|
32
|
-
inStep
|
33
|
-
src={'https://github.com/user-attachments/assets/1bf1a5f0-32ad-418c-a8d1-6c54740f50b9'}
|
30
|
+
alt={'Create Application'}
|
31
|
+
inStep
|
32
|
+
src={'https://github.com/user-attachments/assets/1bf1a5f0-32ad-418c-a8d1-6c54740f50b9'}
|
34
33
|
/>
|
35
34
|
|
36
35
|
- Select a large model to view details
|
37
36
|
- Copy the `API Password` from the top right corner under the HTTP service interface authentication information
|
38
37
|
|
39
38
|
<Image
|
40
|
-
alt={'Copy API Key'}
|
41
|
-
inStep
|
42
|
-
src={'https://github.com/user-attachments/assets/7239d611-1989-414b-a51c-444e47096d75'}
|
39
|
+
alt={'Copy API Key'}
|
40
|
+
inStep
|
41
|
+
src={'https://github.com/user-attachments/assets/7239d611-1989-414b-a51c-444e47096d75'}
|
43
42
|
/>
|
44
43
|
|
45
44
|
### Step 2: Configure iFLYTEK Spark in LobeChat
|
@@ -48,25 +47,25 @@ src={'https://github.com/user-attachments/assets/7239d611-1989-414b-a51c-444e470
|
|
48
47
|
- Find the iFLYTEK Spark settings under `Language Model`
|
49
48
|
|
50
49
|
<Image
|
51
|
-
alt={'Enter API Key'}
|
52
|
-
inStep
|
53
|
-
src={'https://github.com/user-attachments/assets/d693be02-e08c-43ae-8bde-1294f180aaf6'}
|
50
|
+
alt={'Enter API Key'}
|
51
|
+
inStep
|
52
|
+
src={'https://github.com/user-attachments/assets/d693be02-e08c-43ae-8bde-1294f180aaf6'}
|
54
53
|
/>
|
55
54
|
|
56
55
|
- Input the obtained API Key
|
57
56
|
- Choose an iFLYTEK Spark model for your AI assistant to start the conversation
|
58
57
|
|
59
58
|
<Image
|
60
|
-
alt={'Select iFLYTEK Spark Model and Start Conversation'}
|
61
|
-
inStep
|
62
|
-
src={'https://github.com/user-attachments/assets/8910186f-4609-4798-a588-2780dcf8db60'}
|
59
|
+
alt={'Select iFLYTEK Spark Model and Start Conversation'}
|
60
|
+
inStep
|
61
|
+
src={'https://github.com/user-attachments/assets/8910186f-4609-4798-a588-2780dcf8db60'}
|
63
62
|
/>
|
64
63
|
|
65
64
|
<Callout type={'warning'}>
|
66
|
-
During usage, you may need to pay the API service provider, please refer to the relevant pricing
|
65
|
+
During usage, you may need to pay the API service provider, please refer to the relevant pricing
|
66
|
+
policy of iFLYTEK Spark.
|
67
67
|
</Callout>
|
68
68
|
|
69
69
|
</Steps>
|
70
70
|
|
71
71
|
Now you can use the models provided by iFLYTEK Spark for conversations in LobeChat.
|
72
|
-
|
@@ -12,9 +12,7 @@ tags:
|
|
12
12
|
|
13
13
|
<Image
|
14
14
|
cover
|
15
|
-
src={
|
16
|
-
'https://github.com/user-attachments/assets/f3068287-8ade-4eca-9841-ea67d8ff1226'
|
17
|
-
}
|
15
|
+
src={'https://github.com/user-attachments/assets/f3068287-8ade-4eca-9841-ea67d8ff1226'}
|
18
16
|
/>
|
19
17
|
|
20
18
|
[讯飞星火](https://xinghuo.xfyun.cn/)是科大讯飞推出的一款强大的AI大模型,具备跨领域的知识和语言理解能力,能够执行问答、对话和文学创作等多种任务。
|