mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat: introduce API leveling, post_training, eval to v1alpha (#3449)
# What does this PR do? Rather than have a single `LLAMA_STACK_VERSION`, we need to have a `_V1`, `_V1ALPHA`, and `_V1BETA` constant. This also necessitated addition of `level` to the `WebMethod` so that routing can be handeled properly. For backwards compat, the `v1` routes are being kept around and marked as `deprecated`. When used, the server will log a deprecation warning. Deprecation log: <img width="1224" height="134" alt="Screenshot 2025-09-25 at 2 43 36 PM" src="https://github.com/user-attachments/assets/0cc7c245-dafc-48f0-be99-269fb9a686f9" /> move: 1. post_training to `v1alpha` as it is under heavy development and not near its final state 2. eval: job scheduling is not implemented. Relies heavily on the datasetio API which is under development missing implementations of specific routes indicating the structure of those routes might change. Additionally eval depends on the `inference` API which is going to be deprecated, eval will likely need a major API surface change to conform to using completions properly implements leveling in #3317 note: integration tests will fail until the SDK is regenerated with v1alpha/inference as opposed to v1/inference ## Test Plan existing tests should pass with newly generated schema. Conformance will also pass as these routes are not the ones we currently test for stability Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern
GitHub
parent
65e01b5684
commit
c88c4ff2c6
35 changed files with 1507 additions and 260 deletions
|
|
@ -15,6 +15,7 @@ from pydantic import BaseModel, Field
|
|||
|
||||
from llama_stack.apis.inference import InterleavedContent
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.version import LLAMA_STACK_API_V1
|
||||
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
|
||||
from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id
|
||||
from llama_stack.schema_utils import json_schema_type, webmethod
|
||||
|
|
@ -437,7 +438,7 @@ class VectorIO(Protocol):
|
|||
|
||||
# this will just block now until chunks are inserted, but it should
|
||||
# probably return a Job instance which can be polled for completion
|
||||
@webmethod(route="/vector-io/insert", method="POST")
|
||||
@webmethod(route="/vector-io/insert", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def insert_chunks(
|
||||
self,
|
||||
vector_db_id: str,
|
||||
|
|
@ -455,7 +456,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/vector-io/query", method="POST")
|
||||
@webmethod(route="/vector-io/query", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def query_chunks(
|
||||
self,
|
||||
vector_db_id: str,
|
||||
|
|
@ -472,7 +473,7 @@ class VectorIO(Protocol):
|
|||
...
|
||||
|
||||
# OpenAI Vector Stores API endpoints
|
||||
@webmethod(route="/openai/v1/vector_stores", method="POST")
|
||||
@webmethod(route="/openai/v1/vector_stores", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_create_vector_store(
|
||||
self,
|
||||
name: str | None = None,
|
||||
|
|
@ -498,7 +499,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores", method="GET")
|
||||
@webmethod(route="/openai/v1/vector_stores", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_vector_stores(
|
||||
self,
|
||||
limit: int | None = 20,
|
||||
|
|
@ -516,7 +517,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="GET")
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_retrieve_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -528,7 +529,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="POST")
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_update_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -546,7 +547,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE")
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}", method="DELETE", level=LLAMA_STACK_API_V1)
|
||||
async def openai_delete_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -558,7 +559,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/search", method="POST")
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/search", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_search_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -584,7 +585,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="POST")
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="POST", level=LLAMA_STACK_API_V1)
|
||||
async def openai_attach_file_to_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -602,7 +603,7 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="GET")
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files", method="GET", level=LLAMA_STACK_API_V1)
|
||||
async def openai_list_files_in_vector_store(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -624,7 +625,9 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="GET")
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="GET", level=LLAMA_STACK_API_V1
|
||||
)
|
||||
async def openai_retrieve_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -638,7 +641,11 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content", method="GET")
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content",
|
||||
method="GET",
|
||||
level=LLAMA_STACK_API_V1,
|
||||
)
|
||||
async def openai_retrieve_vector_store_file_contents(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -652,7 +659,9 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="POST")
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="POST", level=LLAMA_STACK_API_V1
|
||||
)
|
||||
async def openai_update_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
@ -668,7 +677,9 @@ class VectorIO(Protocol):
|
|||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="DELETE")
|
||||
@webmethod(
|
||||
route="/openai/v1/vector_stores/{vector_store_id}/files/{file_id}", method="DELETE", level=LLAMA_STACK_API_V1
|
||||
)
|
||||
async def openai_delete_vector_store_file(
|
||||
self,
|
||||
vector_store_id: str,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue