llama-stack-mirror/llama_stack/providers
Ashwin Bharambe d47f2c0ba8 feat(responses)!: improve responses + conversations implementations
This PR updates the Conversation item related types and improves a
couple critical parts of the implemenation:

- it creates a streaming output item for the final assistant message output by
  the model. until now we only added content parts and included that
  message in the final response.

- rewrites the conversation update code completely to account for items
  other than messages (tool calls, outputs, etc.)
2025-10-14 14:42:12 -07:00
..
inline feat(responses)!: improve responses + conversations implementations 2025-10-14 14:42:12 -07:00
registry refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183) 2025-10-14 10:44:20 -04:00
remote refactor: use extra_body to pass in input_type params for asymmetric embedding models for NVIDIA Inference Provider (#3804) 2025-10-14 13:52:55 -07:00
utils refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183) 2025-10-14 10:44:20 -04:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
datatypes.py feat: combine ProviderSpec datatypes (#3378) 2025-09-18 16:10:00 +02:00