phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-06 22:10:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: rebase and implement file API methods

Browse source 
Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>
This commit is contained in:
Varsha Prasad Narsing 2025-06-25 16:59:29 -07:00
parent 61bddfe70e
commit 3d27b7054c
13 changed files with 195 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/vector_io/vector_io.py
View file

@ -306,6 +306,7 @@ class VectorIO(Protocol):
vector_db_id: str,
chunks: list[Chunk],
ttl_seconds: int | None = None,
params: dict[str, Any] | None = None,
) -> None:
"""Insert chunks into a vector database.
@ -315,6 +316,7 @@ class VectorIO(Protocol):
If `metadata` is provided, you configure how Llama Stack formats the chunk during generation.
If `embedding` is not provided, it will be computed later.
:param ttl_seconds: The time to live of the chunks.
:param params: Optional parameters for the insertion operation, such as distance_metric for vector databases.
"""
...