You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The *context_agent* app is the app that provides AI agent functionality in Nextcloud and acts as a backend for the :ref:`Nextcloud Assistant app<ai-app-assistant>`. Nextcloud can provide customer support upon request, please talk to your account manager for the possibilities.
8
8
9
+
When the Context Agent app is installed the AI Chat in Nextcloud Assistant will be able to interact with your Nextcloud apps via virtual integrations that are called "tools".
10
+
11
+
Currently implemented tools:
12
+
13
+
* List the user's calendars
14
+
15
+
* Example prompt: *"List my calendars"*
16
+
17
+
* List the user's talk conversations
18
+
19
+
* Example prompt: *"List my talk conversations"*
20
+
21
+
* List messages in a talk conversation
22
+
23
+
* Example prompt: *"List the latest messages in my conversation with Andrew"*
24
+
25
+
* Find a person in the user's contacts
26
+
27
+
* Example prompt: *"What is Andrew's Email address?"*
28
+
29
+
* Ask a question to context chat
30
+
31
+
* Example prompt: *"What is the company's sick leave process?"*
32
+
33
+
* Get coordinates for an Address from Open Street Maps Nomatim
34
+
35
+
* Example prompt: *"List my calendars"*
36
+
37
+
* Get the current weather at a location
38
+
39
+
* Example prompt: *"How is the weather in Berlin?"*
40
+
41
+
* Schedule an event in the user's calendar
42
+
43
+
* Example prompt: *"Make schedule an event with Andrew tomorrow at noon."*
44
+
45
+
* Send a message to a talk conversation
46
+
47
+
* Example prompt: *"Can you send a joke to Andrew in talk?"*
* Uses contacts to look up Andrew's email and then sends an email
63
+
9
64
Requirements
10
65
------------
11
66
@@ -31,7 +86,7 @@ Model requirements
31
86
32
87
This app requires underlying Large language models to support tool calling. The default model in *llm2* does *not* support tool calling. Instead we recommend:
33
88
34
-
* Qwen 2.5 8B or higher
89
+
* Qwen 2.5 8B or higher (May not work well with languages other than English)
35
90
* Watt Tool 8B or higher
36
91
37
92
See :ref:`llm2 documentation <ai-app-llm2>` on how to configure alternate models.
0 commit comments