Fix image language (#150)
|
Before Width: | Height: | Size: 237 KiB After Width: | Height: | Size: 92 KiB |
|
Before Width: | Height: | Size: 437 KiB After Width: | Height: | Size: 283 KiB |
|
Before Width: | Height: | Size: 415 KiB |
|
Before Width: | Height: | Size: 497 KiB |
|
Before Width: | Height: | Size: 427 KiB |
|
Before Width: | Height: | Size: 154 KiB |
|
Before Width: | Height: | Size: 265 KiB |
|
Before Width: | Height: | Size: 551 KiB |
|
Before Width: | Height: | Size: 283 KiB |
|
Before Width: | Height: | Size: 3.4 MiB |
|
Before Width: | Height: | Size: 31 KiB |
|
Before Width: | Height: | Size: 344 KiB |
|
Before Width: | Height: | Size: 193 KiB |
|
Before Width: | Height: | Size: 593 KiB After Width: | Height: | Size: 281 KiB |
|
Before Width: | Height: | Size: 559 KiB After Width: | Height: | Size: 275 KiB |
|
Before Width: | Height: | Size: 536 KiB After Width: | Height: | Size: 302 KiB |
|
Before Width: | Height: | Size: 564 KiB After Width: | Height: | Size: 300 KiB |
|
|
@ -4,7 +4,7 @@ In **Studio -- Application Orchestration**, click **Add Feature** to open the ap
|
|||
|
||||
The application toolbox provides various additional features for Dify's [applications](../#application_type):
|
||||
<!-- TODO CN IMG -->
|
||||
<figure><img src="/en/.gitbook/assets/guides/application_orchestrate/app_toolkits/image (237).png" alt=""><figcaption></figcaption></figure>
|
||||
<figure><img src="/en/.gitbook/assets/guides/application_orchestrate/app_toolkits/content_moderation.png" alt=""><figcaption></figcaption></figure>
|
||||
|
||||
### Conversation Opening
|
||||
|
||||
|
|
@ -18,18 +18,6 @@ Setting next step question suggestions allows the AI to generate 3 follow-up que
|
|||
|
||||
<figure><img src="/en/.gitbook/assets/guides/application_orchestrate/app_toolkits/image (241).png" alt=""><figcaption></figcaption></figure>
|
||||
|
||||
### Text-to-Speech
|
||||
|
||||
When enabled, this feature converts the AI's responses into natural-sounding speech.
|
||||
|
||||
<figure><img src="/en/.gitbook/assets/guides/application_orchestrate/app_toolkits/image (242).png" alt=""><figcaption></figcaption></figure>
|
||||
|
||||
### Speech-to-Text
|
||||
|
||||
When enabled, you can record audio within the application and automatically convert the speech into text.
|
||||
|
||||
<figure><img src="/en/.gitbook/assets/guides/application_orchestrate/app_toolkits/image (243).png" alt=""><figcaption></figcaption></figure>
|
||||
|
||||
### Citation and Attribution
|
||||
|
||||
When this feature is enabled, the large language model will cite content from the knowledge base when responding to questions. You can view specific citation details below the response, including the original text segment, segment number, and match score.
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ The prompt we are filling in here is:
|
|||
>
|
||||
> When I am ready, you can start asking questions.
|
||||
|
||||
.png>)
|
||||
<!-- .png>) TODO -->
|
||||
|
||||
For a better experience, we will add an opening dialogue: `"Hello, {{name}}. I'm your interviewer, Bob. Are you ready?"`
|
||||
|
||||
|
|
|
|||