mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
feat: Add missing Vector Store Files API surface (#2468)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Integration Tests / test-matrix (http, 3.11, tool_runtime) (push) Failing after 13s
Integration Tests / test-matrix (http, 3.11, providers) (push) Failing after 13s
Integration Tests / test-matrix (http, 3.11, datasets) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.11, inspect) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.12, agents) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.12, scoring) (push) Failing after 13s
Integration Tests / test-matrix (library, 3.11, inspect) (push) Failing after 12s
Integration Tests / test-matrix (library, 3.11, tool_runtime) (push) Failing after 12s
Integration Tests / test-matrix (http, 3.12, post_training) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.12, inference) (push) Failing after 19s
Integration Tests / test-matrix (http, 3.12, inspect) (push) Failing after 22s
Integration Tests / test-matrix (http, 3.12, vector_io) (push) Failing after 17s
Integration Tests / test-matrix (http, 3.11, post_training) (push) Failing after 23s
Integration Tests / test-matrix (library, 3.11, datasets) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.11, vector_io) (push) Failing after 20s
Integration Tests / test-matrix (library, 3.11, inference) (push) Failing after 16s
Integration Tests / test-matrix (http, 3.11, agents) (push) Failing after 26s
Integration Tests / test-matrix (http, 3.12, tool_runtime) (push) Failing after 19s
Python Package Build Test / build (3.11) (push) Failing after 5s
Integration Tests / test-matrix (library, 3.12, post_training) (push) Failing after 6s
Python Package Build Test / build (3.12) (push) Failing after 3s
Integration Tests / test-matrix (http, 3.12, providers) (push) Failing after 18s
Integration Tests / test-matrix (library, 3.12, providers) (push) Failing after 10s
Integration Tests / test-matrix (library, 3.11, post_training) (push) Failing after 17s
Integration Tests / test-matrix (library, 3.11, vector_io) (push) Failing after 15s
Integration Tests / test-matrix (library, 3.11, scoring) (push) Failing after 18s
Integration Tests / test-matrix (library, 3.12, datasets) (push) Failing after 13s
Integration Tests / test-matrix (library, 3.12, scoring) (push) Failing after 8s
Python Package Build Test / build (3.13) (push) Failing after 5s
Integration Tests / test-matrix (http, 3.11, scoring) (push) Failing after 24s
Integration Tests / test-matrix (library, 3.11, agents) (push) Failing after 20s
Integration Tests / test-matrix (library, 3.12, inspect) (push) Failing after 10s
Integration Tests / test-matrix (library, 3.12, tool_runtime) (push) Failing after 7s
Integration Tests / test-matrix (library, 3.11, providers) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.12, datasets) (push) Failing after 21s
Integration Tests / test-matrix (library, 3.12, inference) (push) Failing after 12s
Integration Tests / test-matrix (library, 3.12, agents) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.11, inference) (push) Failing after 22s
Unit Tests / unit-tests (3.11) (push) Failing after 7s
Update ReadTheDocs / update-readthedocs (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 7s
Integration Tests / test-matrix (library, 3.12, vector_io) (push) Failing after 48s
Test External Providers / test-external-providers (venv) (push) Failing after 43s
Unit Tests / unit-tests (3.13) (push) Failing after 52s
Pre-commit / pre-commit (push) Successful in 2m4s
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Integration Tests / test-matrix (http, 3.11, tool_runtime) (push) Failing after 13s
Integration Tests / test-matrix (http, 3.11, providers) (push) Failing after 13s
Integration Tests / test-matrix (http, 3.11, datasets) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.11, inspect) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.12, agents) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.12, scoring) (push) Failing after 13s
Integration Tests / test-matrix (library, 3.11, inspect) (push) Failing after 12s
Integration Tests / test-matrix (library, 3.11, tool_runtime) (push) Failing after 12s
Integration Tests / test-matrix (http, 3.12, post_training) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.12, inference) (push) Failing after 19s
Integration Tests / test-matrix (http, 3.12, inspect) (push) Failing after 22s
Integration Tests / test-matrix (http, 3.12, vector_io) (push) Failing after 17s
Integration Tests / test-matrix (http, 3.11, post_training) (push) Failing after 23s
Integration Tests / test-matrix (library, 3.11, datasets) (push) Failing after 14s
Integration Tests / test-matrix (http, 3.11, vector_io) (push) Failing after 20s
Integration Tests / test-matrix (library, 3.11, inference) (push) Failing after 16s
Integration Tests / test-matrix (http, 3.11, agents) (push) Failing after 26s
Integration Tests / test-matrix (http, 3.12, tool_runtime) (push) Failing after 19s
Python Package Build Test / build (3.11) (push) Failing after 5s
Integration Tests / test-matrix (library, 3.12, post_training) (push) Failing after 6s
Python Package Build Test / build (3.12) (push) Failing after 3s
Integration Tests / test-matrix (http, 3.12, providers) (push) Failing after 18s
Integration Tests / test-matrix (library, 3.12, providers) (push) Failing after 10s
Integration Tests / test-matrix (library, 3.11, post_training) (push) Failing after 17s
Integration Tests / test-matrix (library, 3.11, vector_io) (push) Failing after 15s
Integration Tests / test-matrix (library, 3.11, scoring) (push) Failing after 18s
Integration Tests / test-matrix (library, 3.12, datasets) (push) Failing after 13s
Integration Tests / test-matrix (library, 3.12, scoring) (push) Failing after 8s
Python Package Build Test / build (3.13) (push) Failing after 5s
Integration Tests / test-matrix (http, 3.11, scoring) (push) Failing after 24s
Integration Tests / test-matrix (library, 3.11, agents) (push) Failing after 20s
Integration Tests / test-matrix (library, 3.12, inspect) (push) Failing after 10s
Integration Tests / test-matrix (library, 3.12, tool_runtime) (push) Failing after 7s
Integration Tests / test-matrix (library, 3.11, providers) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.12, datasets) (push) Failing after 21s
Integration Tests / test-matrix (library, 3.12, inference) (push) Failing after 12s
Integration Tests / test-matrix (library, 3.12, agents) (push) Failing after 15s
Integration Tests / test-matrix (http, 3.11, inference) (push) Failing after 22s
Unit Tests / unit-tests (3.11) (push) Failing after 7s
Update ReadTheDocs / update-readthedocs (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 7s
Integration Tests / test-matrix (library, 3.12, vector_io) (push) Failing after 48s
Test External Providers / test-external-providers (venv) (push) Failing after 43s
Unit Tests / unit-tests (3.13) (push) Failing after 52s
Pre-commit / pre-commit (push) Successful in 2m4s
# What does this PR do? This adds the ability to list, retrieve, update, and delete Vector Store Files. It implements these new APIs for the faiss and sqlite-vec providers, since those are the two that also have the rest of the vector store files implementation. Closes #2445 ## Test Plan ### test_openai_vector_stores Integration Tests There are a number of new integration tests added, which I ran for each provider as outlined below. faiss (from ollama distro): ``` INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run llama_stack/templates/ollama/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ pytest -sv tests/integration/vector_io/test_openai_vector_stores.py \ --embedding-model=all-MiniLM-L6-v2 ``` sqlite-vec (from starter distro): ``` llama stack run llama_stack/templates/starter/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ pytest -sv tests/integration/vector_io/test_openai_vector_stores.py \ --embedding-model=all-MiniLM-L6-v2 ``` ### file_search verification tests I also ensured the file_search verification tests continue to work, both for faiss and sqlite-vec. faiss (ollama distro): ``` INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \ llama stack run llama_stack/templates/ollama/run.yaml pytest -sv tests/verifications/openai_api/test_responses.py \ -k'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=meta-llama/Llama-3.2-3B-Instruct ``` sqlite-vec (starter distro): ``` llama stack run llama_stack/templates/starter/run.yaml pytest -sv tests/verifications/openai_api/test_responses.py \ -k'file_search' \ --base-url=http://localhost:8321/v1/openai/v1 \ --model=together/meta-llama/Llama-3.2-3B-Instruct-Turbo ``` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
parent
a2f054607d
commit
f394c7f2d9
11 changed files with 1991 additions and 122 deletions
|
@ -38,6 +38,15 @@ class QueryChunksResponse(BaseModel):
|
|||
scores: list[float]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreFileCounts(BaseModel):
|
||||
completed: int
|
||||
cancelled: int
|
||||
failed: int
|
||||
in_progress: int
|
||||
total: int
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreObject(BaseModel):
|
||||
"""OpenAI Vector Store object."""
|
||||
|
@ -47,7 +56,7 @@ class VectorStoreObject(BaseModel):
|
|||
created_at: int
|
||||
name: str | None = None
|
||||
usage_bytes: int = 0
|
||||
file_counts: dict[str, int] = Field(default_factory=dict)
|
||||
file_counts: VectorStoreFileCounts
|
||||
status: str = "completed"
|
||||
expires_after: dict[str, Any] | None = None
|
||||
expires_at: int | None = None
|
||||
|
@ -168,6 +177,10 @@ class VectorStoreFileLastError(BaseModel):
|
|||
message: str
|
||||
|
||||
|
||||
VectorStoreFileStatus = Literal["completed"] | Literal["in_progress"] | Literal["cancelled"] | Literal["failed"]
|
||||
register_schema(VectorStoreFileStatus, name="VectorStoreFileStatus")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreFileObject(BaseModel):
|
||||
"""OpenAI Vector Store File object."""
|
||||
|
@ -178,11 +191,41 @@ class VectorStoreFileObject(BaseModel):
|
|||
chunking_strategy: VectorStoreChunkingStrategy
|
||||
created_at: int
|
||||
last_error: VectorStoreFileLastError | None = None
|
||||
status: Literal["completed"] | Literal["in_progress"] | Literal["cancelled"] | Literal["failed"]
|
||||
status: VectorStoreFileStatus
|
||||
usage_bytes: int = 0
|
||||
vector_store_id: str
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreListFilesResponse(BaseModel):
|
||||
"""Response from listing vector stores."""
|
||||
|
||||
object: str = "list"
|
||||
data: list[VectorStoreFileObject]
|
||||
first_id: str | None = None
|
||||
last_id: str | None = None
|
||||
has_more: bool = False
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreFileContentsResponse(BaseModel):
|
||||
"""Response from retrieving the contents of a vector store file."""
|
||||
|
||||
file_id: str
|
||||
filename: str
|
||||
attributes: dict[str, Any]
|
||||
content: list[VectorStoreContent]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class VectorStoreFileDeleteResponse(BaseModel):
|
||||
"""Response from deleting a vector store file."""
|
||||
|
||||
id: str
|
||||
object: str = "vector_store.file.deleted"
|
||||
deleted: bool = True
|
||||
|
||||
|
||||
class VectorDBStore(Protocol):
|
||||
def get_vector_db(self, vector_db_id: str) -> VectorDB | None: ...
|
||||
|
||||
|
@ -358,3 +401,78 @@ class VectorIO(Protocol):
|
|||
:returns: A VectorStoreFileObject representing the attached file.
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="GET")
|
||||
async def openai_list_files_in_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
limit: int | None = 20,
|
||||
order: str | None = "desc",
|
||||
after: str | None = None,
|
||||
before: str | None = None,
|
||||
filter: VectorStoreFileStatus | None = None,
|
||||
) -> VectorStoreListFilesResponse:
|
||||
"""List files in a vector store.
|
||||
|
||||
:param vector_store_id: The ID of the vector store to list files from.
|
||||
:returns: A VectorStoreListFilesResponse containing the list of files.
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="GET")
|
||||
async def openai_retrieve_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileObject:
|
||||
"""Retrieves a vector store file.
|
||||
|
||||
:param vector_store_id: The ID of the vector store containing the file to retrieve.
|
||||
:param file_id: The ID of the file to retrieve.
|
||||
:returns: A VectorStoreFileObject representing the file.
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content", method="GET")
|
||||
async def openai_retrieve_vector_store_file_contents(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileContentsResponse:
|
||||
"""Retrieves the contents of a vector store file.
|
||||
|
||||
:param vector_store_id: The ID of the vector store containing the file to retrieve.
|
||||
:param file_id: The ID of the file to retrieve.
|
||||
:returns: A list of InterleavedContent representing the file contents.
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="POST")
|
||||
async def openai_update_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
attributes: dict[str, Any],
|
||||
) -> VectorStoreFileObject:
|
||||
"""Updates a vector store file.
|
||||
|
||||
:param vector_store_id: The ID of the vector store containing the file to update.
|
||||
:param file_id: The ID of the file to update.
|
||||
:param attributes: The updated key-value attributes to store with the file.
|
||||
:returns: A VectorStoreFileObject representing the updated file.
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="DELETE")
|
||||
async def openai_delete_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
file_id: str,
|
||||
) -> VectorStoreFileDeleteResponse:
|
||||
"""Delete a vector store file.
|
||||
|
||||
:param vector_store_id: The ID of the vector store containing the file to delete.
|
||||
:param file_id: The ID of the file to delete.
|
||||
:returns: A VectorStoreFileDeleteResponse indicating the deletion status.
|
||||
"""
|
||||
...
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue