diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html index 18f4f49b9..a1a3217c4 100644 --- a/docs/_static/llama-stack-spec.html +++ b/docs/_static/llama-stack-spec.html @@ -3318,7 +3318,7 @@ "name": "limit", "in": "query", "description": "A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20.", - "required": true, + "required": false, "schema": { "type": "integer" } @@ -3327,7 +3327,7 @@ "name": "order", "in": "query", "description": "Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order.", - "required": true, + "required": false, "schema": { "type": "string" } @@ -13128,9 +13128,7 @@ }, "additionalProperties": false, "required": [ - "query", - "max_num_results", - "rewrite_query" + "query" ], "title": "OpenaiSearchVectorStoreRequest" }, diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml index 4dbcd3ac9..15593d060 100644 --- a/docs/_static/llama-stack-spec.yaml +++ b/docs/_static/llama-stack-spec.yaml @@ -2323,7 +2323,7 @@ paths: description: >- A limit on the number of objects to be returned. Limit can range between 1 and 100, and the default is 20. - required: true + required: false schema: type: integer - name: order @@ -2331,7 +2331,7 @@ paths: description: >- Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and `desc` for descending order. - required: true + required: false schema: type: string - name: after @@ -9189,8 +9189,6 @@ components: additionalProperties: false required: - query - - max_num_results - - rewrite_query title: OpenaiSearchVectorStoreRequest VectorStoreSearchResponse: type: object diff --git a/llama_stack/apis/vector_io/vector_io.py b/llama_stack/apis/vector_io/vector_io.py index 5f54539a4..c14a88c5e 100644 --- a/llama_stack/apis/vector_io/vector_io.py +++ b/llama_stack/apis/vector_io/vector_io.py @@ -193,8 +193,8 @@ class VectorIO(Protocol): @webmethod(route="/openai/v1/vector_stores", method="GET") async def openai_list_vector_stores( self, - limit: int = 20, - order: str = "desc", + limit: int | None = 20, + order: str | None = "desc", after: str | None = None, before: str | None = None, ) -> VectorStoreListResponse: @@ -256,9 +256,9 @@ class VectorIO(Protocol): vector_store_id: str, query: str | list[str], filters: dict[str, Any] | None = None, - max_num_results: int = 10, + max_num_results: int | None = 10, ranking_options: dict[str, Any] | None = None, - rewrite_query: bool = False, + rewrite_query: bool | None = False, ) -> VectorStoreSearchResponse: """Search for chunks in a vector store. diff --git a/llama_stack/distribution/routers/vector_io.py b/llama_stack/distribution/routers/vector_io.py index 30b19c436..601109963 100644 --- a/llama_stack/distribution/routers/vector_io.py +++ b/llama_stack/distribution/routers/vector_io.py @@ -151,8 +151,8 @@ class VectorIORouter(VectorIO): async def openai_list_vector_stores( self, - limit: int = 20, - order: str = "desc", + limit: int | None = 20, + order: str | None = "desc", after: str | None = None, before: str | None = None, ) -> VectorStoreListResponse: @@ -239,9 +239,9 @@ class VectorIORouter(VectorIO): vector_store_id: str, query: str | list[str], filters: dict[str, Any] | None = None, - max_num_results: int = 10, + max_num_results: int | None = 10, ranking_options: dict[str, Any] | None = None, - rewrite_query: bool = False, + rewrite_query: bool | None = False, ) -> VectorStoreSearchResponse: logger.debug(f"VectorIORouter.openai_search_vector_store: {vector_store_id}") # Route based on vector store ID diff --git a/llama_stack/providers/remote/vector_io/chroma/chroma.py b/llama_stack/providers/remote/vector_io/chroma/chroma.py index de41f388c..5f5be539d 100644 --- a/llama_stack/providers/remote/vector_io/chroma/chroma.py +++ b/llama_stack/providers/remote/vector_io/chroma/chroma.py @@ -6,7 +6,7 @@ import asyncio import json import logging -from typing import Any, Literal +from typing import Any from urllib.parse import urlparse import chromadb @@ -203,8 +203,8 @@ class ChromaVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): async def openai_list_vector_stores( self, - limit: int = 20, - order: str = "desc", + limit: int | None = 20, + order: str | None = "desc", after: str | None = None, before: str | None = None, ) -> VectorStoreListResponse: @@ -236,9 +236,8 @@ class ChromaVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): vector_store_id: str, query: str | list[str], filters: dict[str, Any] | None = None, - max_num_results: int = 10, + max_num_results: int | None = 10, ranking_options: dict[str, Any] | None = None, - rewrite_query: bool = False, - search_mode: Literal["keyword", "vector", "hybrid"] = "vector", + rewrite_query: bool | None = False, ) -> VectorStoreSearchResponse: raise NotImplementedError("OpenAI Vector Stores API is not supported in Chroma") diff --git a/llama_stack/providers/remote/vector_io/milvus/milvus.py b/llama_stack/providers/remote/vector_io/milvus/milvus.py index 9360ef36a..ae59af599 100644 --- a/llama_stack/providers/remote/vector_io/milvus/milvus.py +++ b/llama_stack/providers/remote/vector_io/milvus/milvus.py @@ -9,7 +9,7 @@ import hashlib import logging import os import uuid -from typing import Any, Literal +from typing import Any from numpy.typing import NDArray from pymilvus import MilvusClient @@ -201,8 +201,8 @@ class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): async def openai_list_vector_stores( self, - limit: int = 20, - order: str = "desc", + limit: int | None = 20, + order: str | None = "desc", after: str | None = None, before: str | None = None, ) -> VectorStoreListResponse: @@ -234,10 +234,9 @@ class MilvusVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): vector_store_id: str, query: str | list[str], filters: dict[str, Any] | None = None, - max_num_results: int = 10, + max_num_results: int | None = 10, ranking_options: dict[str, Any] | None = None, - rewrite_query: bool = False, - search_mode: Literal["keyword", "vector", "hybrid"] = "vector", + rewrite_query: bool | None = False, ) -> VectorStoreSearchResponse: raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant") diff --git a/llama_stack/providers/remote/vector_io/qdrant/qdrant.py b/llama_stack/providers/remote/vector_io/qdrant/qdrant.py index cff62bff5..9e802fd6a 100644 --- a/llama_stack/providers/remote/vector_io/qdrant/qdrant.py +++ b/llama_stack/providers/remote/vector_io/qdrant/qdrant.py @@ -6,7 +6,7 @@ import logging import uuid -from typing import Any, Literal +from typing import Any from numpy.typing import NDArray from qdrant_client import AsyncQdrantClient, models @@ -203,8 +203,8 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): async def openai_list_vector_stores( self, - limit: int = 20, - order: str = "desc", + limit: int | None = 20, + order: str | None = "desc", after: str | None = None, before: str | None = None, ) -> VectorStoreListResponse: @@ -236,9 +236,8 @@ class QdrantVectorIOAdapter(VectorIO, VectorDBsProtocolPrivate): vector_store_id: str, query: str | list[str], filters: dict[str, Any] | None = None, - max_num_results: int = 10, + max_num_results: int | None = 10, ranking_options: dict[str, Any] | None = None, - rewrite_query: bool = False, - search_mode: Literal["keyword", "vector", "hybrid"] = "vector", + rewrite_query: bool | None = False, ) -> VectorStoreSearchResponse: raise NotImplementedError("OpenAI Vector Stores API is not supported in Qdrant") diff --git a/llama_stack/providers/utils/memory/openai_vector_store_mixin.py b/llama_stack/providers/utils/memory/openai_vector_store_mixin.py index 345171828..c2a63f3c5 100644 --- a/llama_stack/providers/utils/memory/openai_vector_store_mixin.py +++ b/llama_stack/providers/utils/memory/openai_vector_store_mixin.py @@ -8,7 +8,7 @@ import logging import time import uuid from abc import ABC, abstractmethod -from typing import Any, Literal +from typing import Any from llama_stack.apis.vector_dbs import VectorDB from llama_stack.apis.vector_io import ( @@ -161,12 +161,15 @@ class OpenAIVectorStoreMixin(ABC): async def openai_list_vector_stores( self, - limit: int = 20, - order: str = "desc", + limit: int | None = 20, + order: str | None = "desc", after: str | None = None, before: str | None = None, ) -> VectorStoreListResponse: """Returns a list of vector stores.""" + limit = limit or 20 + order = order or "desc" + # Get all vector stores all_stores = list(self.openai_vector_stores.values()) @@ -274,12 +277,16 @@ class OpenAIVectorStoreMixin(ABC): vector_store_id: str, query: str | list[str], filters: dict[str, Any] | None = None, - max_num_results: int = 10, + max_num_results: int | None = 10, ranking_options: dict[str, Any] | None = None, - rewrite_query: bool = False, - search_mode: Literal["keyword", "vector", "hybrid"] = "vector", + rewrite_query: bool | None = False, + # search_mode: Literal["keyword", "vector", "hybrid"] = "vector", ) -> VectorStoreSearchResponse: """Search for chunks in a vector store.""" + # TODO: Add support in the API for this + search_mode = "vector" + max_num_results = max_num_results or 10 + if vector_store_id not in self.openai_vector_stores: raise ValueError(f"Vector store {vector_store_id} not found")