llama-stack-mirror/llama_stack/providers/inline
Ashwin Bharambe 2e5bfcd42a
Update Telemetry API so OpenAPI generation can work (#640)
We cannot use recursive types because not only does our OpenAPI
generator not like them, even if it did, it is not easy for all client
languages to automatically construct proper APIs (especially considering
garbage collection) around them. For now, we can return a `Dict[str,
SpanWithStatus]` instead of `SpanWithChildren` and rely on the client to
reconstruct the tree.

Also fixed a super subtle issue with the OpenAPI generation process
(monkey-patching of json_schema_type wasn't working because of import
reordering.)
2024-12-16 13:00:14 -08:00
..
agents add tracing back to the lib cli (#595) 2024-12-11 08:44:20 -08:00
datasetio Telemetry API redesign (#525) 2024-12-04 11:22:45 -08:00
eval Add ability to query and export spans to dataset (#574) 2024-12-05 21:07:30 -08:00
inference add embedding model by default to distribution templates (#617) 2024-12-13 12:48:00 -08:00
ios/inference impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00
memory Make embedding generation go through inference (#606) 2024-12-12 11:47:50 -08:00
meta_reference Telemetry API redesign (#525) 2024-12-04 11:22:45 -08:00
post_training/torchtune [3/n][torchtune integration] add validation logic (#600) 2024-12-13 16:35:06 -08:00
safety use logging instead of prints (#499) 2024-11-21 11:32:53 -08:00
scoring [/scoring] add ability to define aggregation functions for scoring functions & refactors (#597) 2024-12-11 10:03:42 -08:00
telemetry Update Telemetry API so OpenAPI generation can work (#640) 2024-12-16 13:00:14 -08:00
__init__.py impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00