Reference16r1:Apps/PbxManager/App myApps ConferenceTranscriptions: Difference between revisions
Jump to navigation
Jump to search
m →Summary prompt: added examples link |
→LLM (Model): Added some extra info for the LLM |
||
| Line 21: | Line 21: | ||
===== LLM (Model) ===== | ===== LLM (Model) ===== | ||
The actual LLM (model) you intend to use. These are requested using the [https://sdk.innovaphone.com/16r1/web1/com.innovaphone.assistant/com.innovaphone.assistant.htm local assistant JavaScript API] | The actual LLM (model) you intend to use. These are requested using the [https://sdk.innovaphone.com/16r1/web1/com.innovaphone.assistant/com.innovaphone.assistant.htm local assistant JavaScript API] offered by the Assistant App Service. That model will create the summary using the defined prompt and the collected transcript | ||
==Related Articles== | ==Related Articles== | ||
* [[{{NAMESPACE}}:Concept App Service Conference Transcriptions|Reference16r1:Concept App Service Conference Transcriptions]] | * [[{{NAMESPACE}}:Concept App Service Conference Transcriptions|Reference16r1:Concept App Service Conference Transcriptions]] | ||
Latest revision as of 16:30, 28 January 2026
With the conference-transcription PBX-Manager plugin, the needed app object can be created and configured. In addition, the app object can be assigned to specific config templates, if any exist.
Add an app object
- Name
- The name displayed for the app object which must be unique.
- SIP
- The sip from the app object which must be unique.
Conference Transcriptions API
Transcript auto deletion
Transcripts and summaries are stored in the database. You may choose to auto delete them after a certain time.
Summary prompt
At the end of a conference the transcript is send to the LLM you have chosen in order to create the summary. You may adapt the prompt to your liking. You may find examples here
LLM (Model)
The actual LLM (model) you intend to use. These are requested using the local assistant JavaScript API offered by the Assistant App Service. That model will create the summary using the defined prompt and the collected transcript