phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 15:23:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Migrating VectorDB to use OpenAI compatible identifier

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-07-03 22:02:06 -04:00
parent b094960199
commit ddb29b306c
9 changed files with 44 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/distribution/routers/vector_io.py
View file

@ -5,6 +5,7 @@
# the root directory of this source tree.
import asyncio
import uuid
from typing import Any
from llama_stack.apis.common.content_types import (
@ -82,6 +83,7 @@ class VectorIORouter(VectorIO):
embedding_dimension: int | None = 384,
provider_id: str | None = None,
provider_vector_db_id: str | None = None,
provider_vector_db_name: str | None = None,
) -> None:
logger.debug(f"VectorIORouter.register_vector_db: {vector_db_id}, {embedding_model}")
await self.routing_table.register_vector_db(
@ -90,6 +92,7 @@ class VectorIORouter(VectorIO):
embedding_dimension,
provider_id,
provider_vector_db_id,
provider_vector_db_name,
)
async def insert_chunks(
@ -123,7 +126,7 @@ class VectorIORouter(VectorIO):
embedding_model: str | None = None,
embedding_dimension: int | None = None,
provider_id: str | None = None,
provider_vector_db_id: str | None = None,
provider_vector_db_id: str = "",
) -> VectorStoreObject:
logger.debug(f"VectorIORouter.openai_create_vector_store: name={name}, provider_id={provider_id}")
@ -135,17 +138,17 @@ class VectorIORouter(VectorIO):
embedding_model, embedding_dimension = embedding_model_info
logger.info(f"No embedding model specified, using first available: {embedding_model}")
vector_db_id = name
vector_db_id = f"vs_{uuid.uuid4()}"
registered_vector_db = await self.routing_table.register_vector_db(
vector_db_id,
embedding_model,
embedding_dimension,
provider_id,
provider_vector_db_id,
name,
)
return await self.routing_table.get_provider_impl(registered_vector_db.identifier).openai_create_vector_store(
vector_db_id,
name,
file_ids=file_ids,
expires_after=expires_after,
chunking_strategy=chunking_strategy,