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 Llama Stack can be run as a standalone server and accessed via its the REST
51
+
API. However, instead of direct communication via the REST API (and JSON
52
+
format), there is an even better alternative. It is based on the so-called
53
+
Llama Stack Client. It is a library available for Python, Swift, Node.js or
54
+
Kotlin, which "wraps" the REST API stack in a suitable way, which is easier for
55
+
many applications.
56
+
57
+
## Llama Stack as separate server
58
+
59
+
If Llama Stack runs as a separate server, the Lightspeed service needs to be configured to be able to access it. For example, if server runs on localhost:8321, the service configuration should look like:
60
+
61
+
```yaml
62
+
name: foo bar baz
63
+
service:
64
+
host: localhost
65
+
port: 8080
66
+
auth_enabled: false
67
+
workers: 1
68
+
color_log: true
69
+
access_log: true
70
+
llama_stack:
71
+
use_as_library_client: false
72
+
url: http://localhost:8321
73
+
user_data_collection:
74
+
feedback_disabled: false
75
+
feedback_storage: "/tmp/data/feedback"
76
+
transcripts_disabled: false
77
+
transcripts_storage: "/tmp/data/transcripts"
78
+
```
79
+
80
+
## Llama Stack as client library
81
+
82
+
There are situations in which it is not advisable to run two processors (one with Llama Stack, the other with a service). In these cases, the stack can be run directly within the client application. For such situations, the configuration file could look like:
0 commit comments