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
Sorry for the delay. Hacking with new agent executor costs me more time than expected. But it's fun and enlightening. As a result, work on rerank models will delay to next release.
8
+
9
+
* Features
10
+
* New `LLMCompilerAgentExecutor` as default executor in `mini-assistant`. Please see [this notebook](https://github.com/RobinQu/instinct-notebook) for evaluation results.
11
+
*`POST /v1/threads/runs`, which is missed in last released endpoint, is added.
12
+
*`xn::steps::branch` and `BranchStepFunction` for binary branch composing.
13
+
* Improvements
14
+
* Migrate `instinct-lab` to [standalone repo](https://github.com/RobinQu/instinct-notebook/). Benchmarks and experimental code will be moved there.
15
+
* Many typos in `mini-assistant` API endpoints.
16
+
* Add more trace logs in debug mode.
17
+
*`BaseChatModel` and `BaseLLM` supports runtime configuration with `configure(const ModelOverrides&)` method.
0 commit comments