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
* Fix toolcalling timestamp bug
- 0.1.4 server started returning completed_at and started_at timestamp, but it's not compliant with the OffsetDateTime format that SDK expects. This is causing the agentTurnResponseStepComplete to be missing/incorrectly type-casted to unknown. This patch will ignore the timestamp for now, at least until 0.1.5 release next week when the format is corrected on server side.
* Update readme and bump version
Copy file name to clipboardExpand all lines: README.md
+7-5Lines changed: 7 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,9 @@ Features:
8
8
- Remote Inferencing: Perform inferencing tasks remotely with Llama models hosted on a remote connection (or serverless localhost).
9
9
- Simple Integration: With easy-to-use APIs, a developer can quickly integrate Llama Stack in their Android app. The difference with local vs remote inferencing is also minimal.
Note: The current recommended version is 0.1.4 Llama Stack server with 0.1.4.1 Kotlin client SDK. Kotlin SDK 0.1.4 has a known bug on tool calling, which will be fixed in upcoming Llama Stack server release.
12
14
13
15
*Tagged releases are stable versions of the project. While we strive to maintain a stable main branch, it's not guaranteed to be free of bugs or issues.*
14
16
@@ -24,7 +26,7 @@ The key files in the app are `ExampleLlamaStackLocalInference.kt`, `ExampleLlama
24
26
Add the following dependency in your `build.gradle.kts` file:
0 commit comments