From b7dd3f5c56b867c02b28ec78c878c579ce2061d1 Mon Sep 17 00:00:00 2001 From: ehhuang Date: Mon, 27 Oct 2025 14:26:06 -0700 Subject: [PATCH] chore!: BREAKING CHANGE: vector_db_id -> vector_store_id (#3923) # What does this PR do? ## Test Plan CI vector_io tests will fail until next client sync passed with https://github.com/llamastack/llama-stack-client-python/pull/286 checked out locally --- client-sdks/stainless/openapi.yml | 20 +++++++------- .../providers/vector_io/inline_sqlite-vec.mdx | 20 +++++++------- docs/static/deprecated-llama-stack-spec.html | 4 +-- docs/static/deprecated-llama-stack-spec.yaml | 4 +-- .../static/experimental-llama-stack-spec.html | 4 +-- .../static/experimental-llama-stack-spec.yaml | 4 +-- docs/static/llama-stack-spec.html | 16 ++++++------ docs/static/llama-stack-spec.yaml | 16 ++++++------ docs/static/stainless-llama-stack-spec.html | 20 +++++++------- docs/static/stainless-llama-stack-spec.yaml | 20 +++++++------- src/llama_stack/apis/agents/agents.py | 4 +-- src/llama_stack/apis/tools/rag_tool.py | 8 +++--- src/llama_stack/apis/vector_io/vector_io.py | 12 ++++----- src/llama_stack/core/routers/vector_io.py | 16 ++++++------ .../agents/meta_reference/agent_instance.py | 8 +++--- .../agents/meta_reference/persistence.py | 6 ++--- .../inline/tool_runtime/rag/memory.py | 26 +++++++++---------- .../providers/inline/vector_io/faiss/faiss.py | 12 ++++----- .../inline/vector_io/sqlite_vec/sqlite_vec.py | 12 ++++----- .../providers/registry/vector_io.py | 10 +++---- .../remote/vector_io/chroma/chroma.py | 12 ++++----- .../remote/vector_io/milvus/milvus.py | 12 ++++----- .../remote/vector_io/pgvector/pgvector.py | 8 +++--- .../remote/vector_io/qdrant/qdrant.py | 12 ++++----- .../remote/vector_io/weaviate/weaviate.py | 12 ++++----- .../utils/memory/openai_vector_store_mixin.py | 8 +++--- .../vector_io/test_openai_vector_stores.py | 12 ++++----- tests/integration/vector_io/test_vector_io.py | 14 +++++----- tests/unit/rag/test_rag_query.py | 18 ++++++------- 29 files changed, 175 insertions(+), 175 deletions(-) diff --git a/client-sdks/stainless/openapi.yml b/client-sdks/stainless/openapi.yml index 7b03cd03e..85c7186af 100644 --- a/client-sdks/stainless/openapi.yml +++ b/client-sdks/stainless/openapi.yml @@ -9862,7 +9862,7 @@ components: $ref: '#/components/schemas/RAGDocument' description: >- List of documents to index in the RAG system - vector_db_id: + vector_store_id: type: string description: >- ID of the vector database to store the document embeddings @@ -9873,7 +9873,7 @@ components: additionalProperties: false required: - documents - - vector_db_id + - vector_store_id - chunk_size_in_tokens title: InsertRequest DefaultRAGQueryGeneratorConfig: @@ -10044,7 +10044,7 @@ components: $ref: '#/components/schemas/InterleavedContent' description: >- The query content to search for in the indexed documents - vector_db_ids: + vector_store_ids: type: array items: type: string @@ -10057,7 +10057,7 @@ components: additionalProperties: false required: - content - - vector_db_ids + - vector_store_ids title: QueryRequest RAGQueryResult: type: object @@ -10281,7 +10281,7 @@ components: InsertChunksRequest: type: object properties: - vector_db_id: + vector_store_id: type: string description: >- The identifier of the vector database to insert the chunks into. @@ -10300,13 +10300,13 @@ components: description: The time to live of the chunks. additionalProperties: false required: - - vector_db_id + - vector_store_id - chunks title: InsertChunksRequest QueryChunksRequest: type: object properties: - vector_db_id: + vector_store_id: type: string description: >- The identifier of the vector database to query. @@ -10326,7 +10326,7 @@ components: description: The parameters of the query. additionalProperties: false required: - - vector_db_id + - vector_store_id - query title: QueryChunksRequest QueryChunksResponse: @@ -11844,7 +11844,7 @@ components: description: Type of the step in an agent turn. const: memory_retrieval default: memory_retrieval - vector_db_ids: + vector_store_ids: type: string description: >- The IDs of the vector databases to retrieve context from. @@ -11857,7 +11857,7 @@ components: - turn_id - step_id - step_type - - vector_db_ids + - vector_store_ids - inserted_context title: MemoryRetrievalStep description: >- diff --git a/docs/docs/providers/vector_io/inline_sqlite-vec.mdx b/docs/docs/providers/vector_io/inline_sqlite-vec.mdx index 98a372250..bfa2f29de 100644 --- a/docs/docs/providers/vector_io/inline_sqlite-vec.mdx +++ b/docs/docs/providers/vector_io/inline_sqlite-vec.mdx @@ -72,14 +72,14 @@ description: | Example with hybrid search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7}, ) # Using RRF ranker response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={ "mode": "hybrid", @@ -91,7 +91,7 @@ description: | # Using weighted ranker response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={ "mode": "hybrid", @@ -105,7 +105,7 @@ description: | Example with explicit vector search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7}, ) @@ -114,7 +114,7 @@ description: | Example with keyword search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7}, ) @@ -277,14 +277,14 @@ The SQLite-vec provider supports three search modes: Example with hybrid search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7}, ) # Using RRF ranker response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={ "mode": "hybrid", @@ -296,7 +296,7 @@ response = await vector_io.query_chunks( # Using weighted ranker response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={ "mode": "hybrid", @@ -310,7 +310,7 @@ response = await vector_io.query_chunks( Example with explicit vector search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7}, ) @@ -319,7 +319,7 @@ response = await vector_io.query_chunks( Example with keyword search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7}, ) diff --git a/docs/static/deprecated-llama-stack-spec.html b/docs/static/deprecated-llama-stack-spec.html index 4ae6add60..e06943cf6 100644 --- a/docs/static/deprecated-llama-stack-spec.html +++ b/docs/static/deprecated-llama-stack-spec.html @@ -4390,7 +4390,7 @@ "const": "memory_retrieval", "default": "memory_retrieval" }, - "vector_db_ids": { + "vector_store_ids": { "type": "string", "description": "The IDs of the vector databases to retrieve context from." }, @@ -4404,7 +4404,7 @@ "turn_id", "step_id", "step_type", - "vector_db_ids", + "vector_store_ids", "inserted_context" ], "title": "MemoryRetrievalStep", diff --git a/docs/static/deprecated-llama-stack-spec.yaml b/docs/static/deprecated-llama-stack-spec.yaml index 3bcfde02e..6635b58cf 100644 --- a/docs/static/deprecated-llama-stack-spec.yaml +++ b/docs/static/deprecated-llama-stack-spec.yaml @@ -3252,7 +3252,7 @@ components: description: Type of the step in an agent turn. const: memory_retrieval default: memory_retrieval - vector_db_ids: + vector_store_ids: type: string description: >- The IDs of the vector databases to retrieve context from. @@ -3265,7 +3265,7 @@ components: - turn_id - step_id - step_type - - vector_db_ids + - vector_store_ids - inserted_context title: MemoryRetrievalStep description: >- diff --git a/docs/static/experimental-llama-stack-spec.html b/docs/static/experimental-llama-stack-spec.html index 2ad81d4f2..22473ec11 100644 --- a/docs/static/experimental-llama-stack-spec.html +++ b/docs/static/experimental-llama-stack-spec.html @@ -2865,7 +2865,7 @@ "const": "memory_retrieval", "default": "memory_retrieval" }, - "vector_db_ids": { + "vector_store_ids": { "type": "string", "description": "The IDs of the vector databases to retrieve context from." }, @@ -2879,7 +2879,7 @@ "turn_id", "step_id", "step_type", - "vector_db_ids", + "vector_store_ids", "inserted_context" ], "title": "MemoryRetrievalStep", diff --git a/docs/static/experimental-llama-stack-spec.yaml b/docs/static/experimental-llama-stack-spec.yaml index f15add8cf..0a52bc89b 100644 --- a/docs/static/experimental-llama-stack-spec.yaml +++ b/docs/static/experimental-llama-stack-spec.yaml @@ -2085,7 +2085,7 @@ components: description: Type of the step in an agent turn. const: memory_retrieval default: memory_retrieval - vector_db_ids: + vector_store_ids: type: string description: >- The IDs of the vector databases to retrieve context from. @@ -2098,7 +2098,7 @@ components: - turn_id - step_id - step_type - - vector_db_ids + - vector_store_ids - inserted_context title: MemoryRetrievalStep description: >- diff --git a/docs/static/llama-stack-spec.html b/docs/static/llama-stack-spec.html index 5d8b62db3..d70afb2d3 100644 --- a/docs/static/llama-stack-spec.html +++ b/docs/static/llama-stack-spec.html @@ -11412,7 +11412,7 @@ }, "description": "List of documents to index in the RAG system" }, - "vector_db_id": { + "vector_store_id": { "type": "string", "description": "ID of the vector database to store the document embeddings" }, @@ -11424,7 +11424,7 @@ "additionalProperties": false, "required": [ "documents", - "vector_db_id", + "vector_store_id", "chunk_size_in_tokens" ], "title": "InsertRequest" @@ -11615,7 +11615,7 @@ "$ref": "#/components/schemas/InterleavedContent", "description": "The query content to search for in the indexed documents" }, - "vector_db_ids": { + "vector_store_ids": { "type": "array", "items": { "type": "string" @@ -11630,7 +11630,7 @@ "additionalProperties": false, "required": [ "content", - "vector_db_ids" + "vector_store_ids" ], "title": "QueryRequest" }, @@ -11923,7 +11923,7 @@ "InsertChunksRequest": { "type": "object", "properties": { - "vector_db_id": { + "vector_store_id": { "type": "string", "description": "The identifier of the vector database to insert the chunks into." }, @@ -11941,7 +11941,7 @@ }, "additionalProperties": false, "required": [ - "vector_db_id", + "vector_store_id", "chunks" ], "title": "InsertChunksRequest" @@ -11949,7 +11949,7 @@ "QueryChunksRequest": { "type": "object", "properties": { - "vector_db_id": { + "vector_store_id": { "type": "string", "description": "The identifier of the vector database to query." }, @@ -11986,7 +11986,7 @@ }, "additionalProperties": false, "required": [ - "vector_db_id", + "vector_store_id", "query" ], "title": "QueryChunksRequest" diff --git a/docs/static/llama-stack-spec.yaml b/docs/static/llama-stack-spec.yaml index 435520356..78e56df28 100644 --- a/docs/static/llama-stack-spec.yaml +++ b/docs/static/llama-stack-spec.yaml @@ -8649,7 +8649,7 @@ components: $ref: '#/components/schemas/RAGDocument' description: >- List of documents to index in the RAG system - vector_db_id: + vector_store_id: type: string description: >- ID of the vector database to store the document embeddings @@ -8660,7 +8660,7 @@ components: additionalProperties: false required: - documents - - vector_db_id + - vector_store_id - chunk_size_in_tokens title: InsertRequest DefaultRAGQueryGeneratorConfig: @@ -8831,7 +8831,7 @@ components: $ref: '#/components/schemas/InterleavedContent' description: >- The query content to search for in the indexed documents - vector_db_ids: + vector_store_ids: type: array items: type: string @@ -8844,7 +8844,7 @@ components: additionalProperties: false required: - content - - vector_db_ids + - vector_store_ids title: QueryRequest RAGQueryResult: type: object @@ -9068,7 +9068,7 @@ components: InsertChunksRequest: type: object properties: - vector_db_id: + vector_store_id: type: string description: >- The identifier of the vector database to insert the chunks into. @@ -9087,13 +9087,13 @@ components: description: The time to live of the chunks. additionalProperties: false required: - - vector_db_id + - vector_store_id - chunks title: InsertChunksRequest QueryChunksRequest: type: object properties: - vector_db_id: + vector_store_id: type: string description: >- The identifier of the vector database to query. @@ -9113,7 +9113,7 @@ components: description: The parameters of the query. additionalProperties: false required: - - vector_db_id + - vector_store_id - query title: QueryChunksRequest QueryChunksResponse: diff --git a/docs/static/stainless-llama-stack-spec.html b/docs/static/stainless-llama-stack-spec.html index 2616a9917..dcd44ec6e 100644 --- a/docs/static/stainless-llama-stack-spec.html +++ b/docs/static/stainless-llama-stack-spec.html @@ -13084,7 +13084,7 @@ }, "description": "List of documents to index in the RAG system" }, - "vector_db_id": { + "vector_store_id": { "type": "string", "description": "ID of the vector database to store the document embeddings" }, @@ -13096,7 +13096,7 @@ "additionalProperties": false, "required": [ "documents", - "vector_db_id", + "vector_store_id", "chunk_size_in_tokens" ], "title": "InsertRequest" @@ -13287,7 +13287,7 @@ "$ref": "#/components/schemas/InterleavedContent", "description": "The query content to search for in the indexed documents" }, - "vector_db_ids": { + "vector_store_ids": { "type": "array", "items": { "type": "string" @@ -13302,7 +13302,7 @@ "additionalProperties": false, "required": [ "content", - "vector_db_ids" + "vector_store_ids" ], "title": "QueryRequest" }, @@ -13595,7 +13595,7 @@ "InsertChunksRequest": { "type": "object", "properties": { - "vector_db_id": { + "vector_store_id": { "type": "string", "description": "The identifier of the vector database to insert the chunks into." }, @@ -13613,7 +13613,7 @@ }, "additionalProperties": false, "required": [ - "vector_db_id", + "vector_store_id", "chunks" ], "title": "InsertChunksRequest" @@ -13621,7 +13621,7 @@ "QueryChunksRequest": { "type": "object", "properties": { - "vector_db_id": { + "vector_store_id": { "type": "string", "description": "The identifier of the vector database to query." }, @@ -13658,7 +13658,7 @@ }, "additionalProperties": false, "required": [ - "vector_db_id", + "vector_store_id", "query" ], "title": "QueryChunksRequest" @@ -15719,7 +15719,7 @@ "const": "memory_retrieval", "default": "memory_retrieval" }, - "vector_db_ids": { + "vector_store_ids": { "type": "string", "description": "The IDs of the vector databases to retrieve context from." }, @@ -15733,7 +15733,7 @@ "turn_id", "step_id", "step_type", - "vector_db_ids", + "vector_store_ids", "inserted_context" ], "title": "MemoryRetrievalStep", diff --git a/docs/static/stainless-llama-stack-spec.yaml b/docs/static/stainless-llama-stack-spec.yaml index 7b03cd03e..85c7186af 100644 --- a/docs/static/stainless-llama-stack-spec.yaml +++ b/docs/static/stainless-llama-stack-spec.yaml @@ -9862,7 +9862,7 @@ components: $ref: '#/components/schemas/RAGDocument' description: >- List of documents to index in the RAG system - vector_db_id: + vector_store_id: type: string description: >- ID of the vector database to store the document embeddings @@ -9873,7 +9873,7 @@ components: additionalProperties: false required: - documents - - vector_db_id + - vector_store_id - chunk_size_in_tokens title: InsertRequest DefaultRAGQueryGeneratorConfig: @@ -10044,7 +10044,7 @@ components: $ref: '#/components/schemas/InterleavedContent' description: >- The query content to search for in the indexed documents - vector_db_ids: + vector_store_ids: type: array items: type: string @@ -10057,7 +10057,7 @@ components: additionalProperties: false required: - content - - vector_db_ids + - vector_store_ids title: QueryRequest RAGQueryResult: type: object @@ -10281,7 +10281,7 @@ components: InsertChunksRequest: type: object properties: - vector_db_id: + vector_store_id: type: string description: >- The identifier of the vector database to insert the chunks into. @@ -10300,13 +10300,13 @@ components: description: The time to live of the chunks. additionalProperties: false required: - - vector_db_id + - vector_store_id - chunks title: InsertChunksRequest QueryChunksRequest: type: object properties: - vector_db_id: + vector_store_id: type: string description: >- The identifier of the vector database to query. @@ -10326,7 +10326,7 @@ components: description: The parameters of the query. additionalProperties: false required: - - vector_db_id + - vector_store_id - query title: QueryChunksRequest QueryChunksResponse: @@ -11844,7 +11844,7 @@ components: description: Type of the step in an agent turn. const: memory_retrieval default: memory_retrieval - vector_db_ids: + vector_store_ids: type: string description: >- The IDs of the vector databases to retrieve context from. @@ -11857,7 +11857,7 @@ components: - turn_id - step_id - step_type - - vector_db_ids + - vector_store_ids - inserted_context title: MemoryRetrievalStep description: >- diff --git a/src/llama_stack/apis/agents/agents.py b/src/llama_stack/apis/agents/agents.py index 6ad45cf99..9c3e9231b 100644 --- a/src/llama_stack/apis/agents/agents.py +++ b/src/llama_stack/apis/agents/agents.py @@ -149,13 +149,13 @@ class ShieldCallStep(StepCommon): class MemoryRetrievalStep(StepCommon): """A memory retrieval step in an agent turn. - :param vector_db_ids: The IDs of the vector databases to retrieve context from. + :param vector_store_ids: The IDs of the vector databases to retrieve context from. :param inserted_context: The context retrieved from the vector databases. """ step_type: Literal[StepType.memory_retrieval] = StepType.memory_retrieval # TODO: should this be List[str]? - vector_db_ids: str + vector_store_ids: str inserted_context: InterleavedContent diff --git a/src/llama_stack/apis/tools/rag_tool.py b/src/llama_stack/apis/tools/rag_tool.py index c508721f1..4e43bb284 100644 --- a/src/llama_stack/apis/tools/rag_tool.py +++ b/src/llama_stack/apis/tools/rag_tool.py @@ -190,13 +190,13 @@ class RAGToolRuntime(Protocol): async def insert( self, documents: list[RAGDocument], - vector_db_id: str, + vector_store_id: str, chunk_size_in_tokens: int = 512, ) -> None: """Index documents so they can be used by the RAG system. :param documents: List of documents to index in the RAG system - :param vector_db_id: ID of the vector database to store the document embeddings + :param vector_store_id: ID of the vector database to store the document embeddings :param chunk_size_in_tokens: (Optional) Size in tokens for document chunking during indexing """ ... @@ -205,13 +205,13 @@ class RAGToolRuntime(Protocol): async def query( self, content: InterleavedContent, - vector_db_ids: list[str], + vector_store_ids: list[str], query_config: RAGQueryConfig | None = None, ) -> RAGQueryResult: """Query the RAG system for context; typically invoked by the agent. :param content: The query content to search for in the indexed documents - :param vector_db_ids: List of vector database IDs to search within + :param vector_store_ids: List of vector database IDs to search within :param query_config: (Optional) Configuration parameters for the query operation :returns: RAGQueryResult containing the retrieved content and metadata """ diff --git a/src/llama_stack/apis/vector_io/vector_io.py b/src/llama_stack/apis/vector_io/vector_io.py index 6e855ab99..19703e7bb 100644 --- a/src/llama_stack/apis/vector_io/vector_io.py +++ b/src/llama_stack/apis/vector_io/vector_io.py @@ -529,17 +529,17 @@ 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 - # TODO: rename vector_db_id to vector_store_id once Stainless is working + # TODO: rename vector_store_id to vector_store_id once Stainless is working @webmethod(route="/vector-io/insert", method="POST", level=LLAMA_STACK_API_V1) async def insert_chunks( self, - vector_db_id: str, + vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None, ) -> None: """Insert chunks into a vector database. - :param vector_db_id: The identifier of the vector database to insert the chunks into. + :param vector_store_id: The identifier of the vector database to insert the chunks into. :param chunks: The chunks to insert. Each `Chunk` should contain content which can be interleaved text, images, or other types. `metadata`: `dict[str, Any]` and `embedding`: `List[float]` are optional. If `metadata` is provided, you configure how Llama Stack formats the chunk during generation. @@ -548,17 +548,17 @@ class VectorIO(Protocol): """ ... - # TODO: rename vector_db_id to vector_store_id once Stainless is working + # TODO: rename vector_store_id to vector_store_id once Stainless is working @webmethod(route="/vector-io/query", method="POST", level=LLAMA_STACK_API_V1) async def query_chunks( self, - vector_db_id: str, + vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None, ) -> QueryChunksResponse: """Query chunks from a vector database. - :param vector_db_id: The identifier of the vector database to query. + :param vector_store_id: The identifier of the vector database to query. :param query: The query to search for. :param params: The parameters of the query. :returns: A QueryChunksResponse. diff --git a/src/llama_stack/core/routers/vector_io.py b/src/llama_stack/core/routers/vector_io.py index 2b1701dc2..78b38ba95 100644 --- a/src/llama_stack/core/routers/vector_io.py +++ b/src/llama_stack/core/routers/vector_io.py @@ -73,27 +73,27 @@ class VectorIORouter(VectorIO): async def insert_chunks( self, - vector_db_id: str, + vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None, ) -> None: doc_ids = [chunk.document_id for chunk in chunks[:3]] logger.debug( - f"VectorIORouter.insert_chunks: {vector_db_id}, {len(chunks)} chunks, " + f"VectorIORouter.insert_chunks: {vector_store_id}, {len(chunks)} chunks, " f"ttl_seconds={ttl_seconds}, chunk_ids={doc_ids}{' and more...' if len(chunks) > 3 else ''}" ) - provider = await self.routing_table.get_provider_impl(vector_db_id) - return await provider.insert_chunks(vector_db_id, chunks, ttl_seconds) + provider = await self.routing_table.get_provider_impl(vector_store_id) + return await provider.insert_chunks(vector_store_id, chunks, ttl_seconds) async def query_chunks( self, - vector_db_id: str, + vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None, ) -> QueryChunksResponse: - logger.debug(f"VectorIORouter.query_chunks: {vector_db_id}") - provider = await self.routing_table.get_provider_impl(vector_db_id) - return await provider.query_chunks(vector_db_id, query, params) + logger.debug(f"VectorIORouter.query_chunks: {vector_store_id}") + provider = await self.routing_table.get_provider_impl(vector_store_id) + return await provider.query_chunks(vector_store_id, query, params) # OpenAI Vector Stores API endpoints async def openai_create_vector_store( diff --git a/src/llama_stack/providers/inline/agents/meta_reference/agent_instance.py b/src/llama_stack/providers/inline/agents/meta_reference/agent_instance.py index 9fd3f7d0e..80ef068c7 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/agent_instance.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/agent_instance.py @@ -488,13 +488,13 @@ class ChatAgent(ShieldRunnerMixin): session_info = await self.storage.get_session_info(session_id) # if the session has a memory bank id, let the memory tool use it - if session_info and session_info.vector_db_id: + if session_info and session_info.vector_store_id: for tool_name in self.tool_name_to_args.keys(): if tool_name == MEMORY_QUERY_TOOL: - if "vector_db_ids" not in self.tool_name_to_args[tool_name]: - self.tool_name_to_args[tool_name]["vector_db_ids"] = [session_info.vector_db_id] + if "vector_store_ids" not in self.tool_name_to_args[tool_name]: + self.tool_name_to_args[tool_name]["vector_store_ids"] = [session_info.vector_store_id] else: - self.tool_name_to_args[tool_name]["vector_db_ids"].append(session_info.vector_db_id) + self.tool_name_to_args[tool_name]["vector_store_ids"].append(session_info.vector_store_id) output_attachments = [] diff --git a/src/llama_stack/providers/inline/agents/meta_reference/persistence.py b/src/llama_stack/providers/inline/agents/meta_reference/persistence.py index 3b7b4729c..26a2151e3 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/persistence.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/persistence.py @@ -22,7 +22,7 @@ log = get_logger(name=__name__, category="agents::meta_reference") class AgentSessionInfo(Session): # TODO: is this used anywhere? - vector_db_id: str | None = None + vector_store_id: str | None = None started_at: datetime owner: User | None = None identifier: str | None = None @@ -93,12 +93,12 @@ class AgentPersistence: return session_info - async def add_vector_db_to_session(self, session_id: str, vector_db_id: str): + async def add_vector_db_to_session(self, session_id: str, vector_store_id: str): session_info = await self.get_session_if_accessible(session_id) if session_info is None: raise SessionNotFoundError(session_id) - session_info.vector_db_id = vector_db_id + session_info.vector_store_id = vector_store_id await self.kvstore.set( key=f"session:{self.agent_id}:{session_id}", value=session_info.model_dump_json(), diff --git a/src/llama_stack/providers/inline/tool_runtime/rag/memory.py b/src/llama_stack/providers/inline/tool_runtime/rag/memory.py index dc3dfbbca..3ee745bf1 100644 --- a/src/llama_stack/providers/inline/tool_runtime/rag/memory.py +++ b/src/llama_stack/providers/inline/tool_runtime/rag/memory.py @@ -119,7 +119,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti async def insert( self, documents: list[RAGDocument], - vector_db_id: str, + vector_store_id: str, chunk_size_in_tokens: int = 512, ) -> None: if not documents: @@ -158,14 +158,14 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti try: await self.vector_io_api.openai_attach_file_to_vector_store( - vector_store_id=vector_db_id, + vector_store_id=vector_store_id, file_id=created_file.id, attributes=doc.metadata, chunking_strategy=chunking_strategy, ) except Exception as e: log.error( - f"Failed to attach file {created_file.id} to vector store {vector_db_id} for document {doc.document_id}: {e}" + f"Failed to attach file {created_file.id} to vector store {vector_store_id} for document {doc.document_id}: {e}" ) continue @@ -176,10 +176,10 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti async def query( self, content: InterleavedContent, - vector_db_ids: list[str], + vector_store_ids: list[str], query_config: RAGQueryConfig | None = None, ) -> RAGQueryResult: - if not vector_db_ids: + if not vector_store_ids: raise ValueError( "No vector DBs were provided to the knowledge search tool. Please provide at least one vector DB ID." ) @@ -192,7 +192,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti ) tasks = [ self.vector_io_api.query_chunks( - vector_db_id=vector_db_id, + vector_store_id=vector_store_id, query=query, params={ "mode": query_config.mode, @@ -201,18 +201,18 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti "ranker": query_config.ranker, }, ) - for vector_db_id in vector_db_ids + for vector_store_id in vector_store_ids ] results: list[QueryChunksResponse] = await asyncio.gather(*tasks) chunks = [] scores = [] - for vector_db_id, result in zip(vector_db_ids, results, strict=False): + for vector_store_id, result in zip(vector_store_ids, results, strict=False): for chunk, score in zip(result.chunks, result.scores, strict=False): if not hasattr(chunk, "metadata") or chunk.metadata is None: chunk.metadata = {} - chunk.metadata["vector_db_id"] = vector_db_id + chunk.metadata["vector_store_id"] = vector_store_id chunks.append(chunk) scores.append(score) @@ -250,7 +250,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti metadata_keys_to_exclude_from_context = [ "token_count", "metadata_token_count", - "vector_db_id", + "vector_store_id", ] metadata_for_context = {} for k in chunk_metadata_keys_to_include_from_context: @@ -275,7 +275,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti "document_ids": [c.document_id for c in chunks[: len(picked)]], "chunks": [c.content for c in chunks[: len(picked)]], "scores": scores[: len(picked)], - "vector_db_ids": [c.metadata["vector_db_id"] for c in chunks[: len(picked)]], + "vector_store_ids": [c.metadata["vector_store_id"] for c in chunks[: len(picked)]], }, ) @@ -309,7 +309,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti ) async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: - vector_db_ids = kwargs.get("vector_db_ids", []) + vector_store_ids = kwargs.get("vector_store_ids", []) query_config = kwargs.get("query_config") if query_config: query_config = TypeAdapter(RAGQueryConfig).validate_python(query_config) @@ -319,7 +319,7 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, RAGToolRunti query = kwargs["query"] result = await self.query( content=query, - vector_db_ids=vector_db_ids, + vector_store_ids=vector_store_ids, query_config=query_config, ) diff --git a/src/llama_stack/providers/inline/vector_io/faiss/faiss.py b/src/llama_stack/providers/inline/vector_io/faiss/faiss.py index 5e33d4ca3..9d8e282b0 100644 --- a/src/llama_stack/providers/inline/vector_io/faiss/faiss.py +++ b/src/llama_stack/providers/inline/vector_io/faiss/faiss.py @@ -248,19 +248,19 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoco del self.cache[vector_store_id] await self.kvstore.delete(f"{VECTOR_DBS_PREFIX}{vector_store_id}") - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = self.cache.get(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = self.cache.get(vector_store_id) if index is None: - raise ValueError(f"Vector DB {vector_db_id} not found. found: {self.cache.keys()}") + raise ValueError(f"Vector DB {vector_store_id} not found. found: {self.cache.keys()}") await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None + self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = self.cache.get(vector_db_id) + index = self.cache.get(vector_store_id) if index is None: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) return await index.query_chunks(query, params) diff --git a/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py b/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py index 37294f173..accf5cead 100644 --- a/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py +++ b/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py @@ -447,20 +447,20 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresPro await self.cache[vector_store_id].index.delete() del self.cache[vector_store_id] - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = await self._get_and_cache_vector_store_index(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) # The VectorStoreWithIndex helper is expected to compute embeddings via the inference_api # and then call our index's add_chunks. await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: Any, params: dict[str, Any] | None = None + self, vector_store_id: str, query: Any, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = await self._get_and_cache_vector_store_index(vector_db_id) + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) return await index.query_chunks(query, params) async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None: diff --git a/src/llama_stack/providers/registry/vector_io.py b/src/llama_stack/providers/registry/vector_io.py index ff3b8486f..55b302751 100644 --- a/src/llama_stack/providers/registry/vector_io.py +++ b/src/llama_stack/providers/registry/vector_io.py @@ -163,14 +163,14 @@ The SQLite-vec provider supports three search modes: Example with hybrid search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7}, ) # Using RRF ranker response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={ "mode": "hybrid", @@ -182,7 +182,7 @@ response = await vector_io.query_chunks( # Using weighted ranker response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={ "mode": "hybrid", @@ -196,7 +196,7 @@ response = await vector_io.query_chunks( Example with explicit vector search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7}, ) @@ -205,7 +205,7 @@ response = await vector_io.query_chunks( Example with keyword search: ```python response = await vector_io.query_chunks( - vector_db_id="my_db", + vector_store_id="my_db", query="your query here", params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7}, ) diff --git a/src/llama_stack/providers/remote/vector_io/chroma/chroma.py b/src/llama_stack/providers/remote/vector_io/chroma/chroma.py index 2663ad43e..a4fd15f77 100644 --- a/src/llama_stack/providers/remote/vector_io/chroma/chroma.py +++ b/src/llama_stack/providers/remote/vector_io/chroma/chroma.py @@ -169,20 +169,20 @@ class ChromaVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc await self.cache[vector_store_id].index.delete() del self.cache[vector_store_id] - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = await self._get_and_cache_vector_store_index(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = await self._get_and_cache_vector_store_index(vector_store_id) if index is None: - raise ValueError(f"Vector DB {vector_db_id} not found in Chroma") + raise ValueError(f"Vector DB {vector_store_id} not found in Chroma") await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None + self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = await self._get_and_cache_vector_store_index(vector_db_id) + index = await self._get_and_cache_vector_store_index(vector_store_id) if index is None: - raise ValueError(f"Vector DB {vector_db_id} not found in Chroma") + raise ValueError(f"Vector DB {vector_store_id} not found in Chroma") return await index.query_chunks(query, params) diff --git a/src/llama_stack/providers/remote/vector_io/milvus/milvus.py b/src/llama_stack/providers/remote/vector_io/milvus/milvus.py index cccf13816..ace9ab1c4 100644 --- a/src/llama_stack/providers/remote/vector_io/milvus/milvus.py +++ b/src/llama_stack/providers/remote/vector_io/milvus/milvus.py @@ -348,19 +348,19 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc await self.cache[vector_store_id].index.delete() del self.cache[vector_store_id] - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = await self._get_and_cache_vector_store_index(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None + self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = await self._get_and_cache_vector_store_index(vector_db_id) + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) return await index.query_chunks(query, params) async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None: diff --git a/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py b/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py index f28bd3cd9..29cfd673f 100644 --- a/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py +++ b/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py @@ -399,14 +399,14 @@ class PGVectorVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProt assert self.kvstore is not None await self.kvstore.delete(key=f"{VECTOR_DBS_PREFIX}{vector_store_id}") - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = await self._get_and_cache_vector_store_index(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = await self._get_and_cache_vector_store_index(vector_store_id) await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None + self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = await self._get_and_cache_vector_store_index(vector_db_id) + index = await self._get_and_cache_vector_store_index(vector_store_id) return await index.query_chunks(query, params) async def _get_and_cache_vector_store_index(self, vector_store_id: str) -> VectorStoreWithIndex: diff --git a/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py b/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py index 93d0894a6..266e9bf58 100644 --- a/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py +++ b/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py @@ -222,19 +222,19 @@ class QdrantVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorStoresProtoc self.cache[vector_store_id] = index return index - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = await self._get_and_cache_vector_store_index(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None + self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = await self._get_and_cache_vector_store_index(vector_db_id) + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) return await index.query_chunks(query, params) diff --git a/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py b/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py index 66922aa3f..7813f6e5c 100644 --- a/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py +++ b/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py @@ -366,19 +366,19 @@ class WeaviateVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, NeedsRequestProv self.cache[vector_store_id] = index return index - async def insert_chunks(self, vector_db_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: - index = await self._get_and_cache_vector_store_index(vector_db_id) + async def insert_chunks(self, vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None) -> None: + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) await index.insert_chunks(chunks) async def query_chunks( - self, vector_db_id: str, query: InterleavedContent, params: dict[str, Any] | None = None + self, vector_store_id: str, query: InterleavedContent, params: dict[str, Any] | None = None ) -> QueryChunksResponse: - index = await self._get_and_cache_vector_store_index(vector_db_id) + index = await self._get_and_cache_vector_store_index(vector_store_id) if not index: - raise VectorStoreNotFoundError(vector_db_id) + raise VectorStoreNotFoundError(vector_store_id) return await index.query_chunks(query, params) diff --git a/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py b/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py index 8f9fb9fb4..41d4cb2d7 100644 --- a/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py +++ b/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py @@ -333,7 +333,7 @@ class OpenAIVectorStoreMixin(ABC): @abstractmethod async def insert_chunks( self, - vector_db_id: str, + vector_store_id: str, chunks: list[Chunk], ttl_seconds: int | None = None, ) -> None: @@ -342,7 +342,7 @@ class OpenAIVectorStoreMixin(ABC): @abstractmethod async def query_chunks( - self, vector_db_id: str, query: Any, params: dict[str, Any] | None = None + self, vector_store_id: str, query: Any, params: dict[str, Any] | None = None ) -> QueryChunksResponse: """Query chunks from a vector database (provider-specific implementation).""" pass @@ -609,7 +609,7 @@ class OpenAIVectorStoreMixin(ABC): # TODO: Add support for ranking_options.ranker response = await self.query_chunks( - vector_db_id=vector_store_id, + vector_store_id=vector_store_id, query=search_query, params=params, ) @@ -803,7 +803,7 @@ class OpenAIVectorStoreMixin(ABC): ) else: await self.insert_chunks( - vector_db_id=vector_store_id, + vector_store_id=vector_store_id, chunks=chunks, ) vector_store_file_object.status = "completed" diff --git a/tests/integration/vector_io/test_openai_vector_stores.py b/tests/integration/vector_io/test_openai_vector_stores.py index 626faf42d..f2131c614 100644 --- a/tests/integration/vector_io/test_openai_vector_stores.py +++ b/tests/integration/vector_io/test_openai_vector_stores.py @@ -367,7 +367,7 @@ def test_openai_vector_store_with_chunks( # Insert chunks using the native LlamaStack API (since OpenAI API doesn't have direct chunk insertion) llama_client.vector_io.insert( - vector_db_id=vector_store.id, + vector_store_id=vector_store.id, chunks=sample_chunks, ) @@ -434,7 +434,7 @@ def test_openai_vector_store_search_relevance( # Insert chunks using native API llama_client.vector_io.insert( - vector_db_id=vector_store.id, + vector_store_id=vector_store.id, chunks=sample_chunks, ) @@ -484,7 +484,7 @@ def test_openai_vector_store_search_with_ranking_options( # Insert chunks llama_client.vector_io.insert( - vector_db_id=vector_store.id, + vector_store_id=vector_store.id, chunks=sample_chunks, ) @@ -544,7 +544,7 @@ def test_openai_vector_store_search_with_high_score_filter( # Insert chunks llama_client.vector_io.insert( - vector_db_id=vector_store.id, + vector_store_id=vector_store.id, chunks=sample_chunks, ) @@ -610,7 +610,7 @@ def test_openai_vector_store_search_with_max_num_results( # Insert chunks llama_client.vector_io.insert( - vector_db_id=vector_store.id, + vector_store_id=vector_store.id, chunks=sample_chunks, ) @@ -1175,7 +1175,7 @@ def test_openai_vector_store_search_modes( ) client_with_models.vector_io.insert( - vector_db_id=vector_store.id, + vector_store_id=vector_store.id, chunks=sample_chunks, ) query = "Python programming language" diff --git a/tests/integration/vector_io/test_vector_io.py b/tests/integration/vector_io/test_vector_io.py index 1f67ddb24..a312456b9 100644 --- a/tests/integration/vector_io/test_vector_io.py +++ b/tests/integration/vector_io/test_vector_io.py @@ -123,12 +123,12 @@ def test_insert_chunks( actual_vector_store_id = create_response.id client_with_empty_registry.vector_io.insert( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, chunks=sample_chunks, ) response = client_with_empty_registry.vector_io.query( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, query="What is the capital of France?", ) assert response is not None @@ -137,7 +137,7 @@ def test_insert_chunks( query, expected_doc_id = test_case response = client_with_empty_registry.vector_io.query( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, query=query, ) assert response is not None @@ -174,13 +174,13 @@ def test_insert_chunks_with_precomputed_embeddings( ] client_with_empty_registry.vector_io.insert( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, chunks=chunks_with_embeddings, ) provider = [p.provider_id for p in client_with_empty_registry.providers.list() if p.api == "vector_io"][0] response = client_with_empty_registry.vector_io.query( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, query="precomputed embedding test", params=vector_io_provider_params_dict.get(provider, None), ) @@ -224,13 +224,13 @@ def test_query_returns_valid_object_when_identical_to_embedding_in_vdb( ] client_with_empty_registry.vector_io.insert( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, chunks=chunks_with_embeddings, ) provider = [p.provider_id for p in client_with_empty_registry.providers.list() if p.api == "vector_io"][0] response = client_with_empty_registry.vector_io.query( - vector_db_id=actual_vector_store_id, + vector_store_id=actual_vector_store_id, query="duplicate", params=vector_io_provider_params_dict.get(provider, None), ) diff --git a/tests/unit/rag/test_rag_query.py b/tests/unit/rag/test_rag_query.py index c012bc4f0..45b194332 100644 --- a/tests/unit/rag/test_rag_query.py +++ b/tests/unit/rag/test_rag_query.py @@ -23,14 +23,14 @@ class TestRagQuery: config=MagicMock(), vector_io_api=MagicMock(), inference_api=MagicMock(), files_api=MagicMock() ) with pytest.raises(ValueError): - await rag_tool.query(content=MagicMock(), vector_db_ids=[]) + await rag_tool.query(content=MagicMock(), vector_store_ids=[]) async def test_query_chunk_metadata_handling(self): rag_tool = MemoryToolRuntimeImpl( config=MagicMock(), vector_io_api=MagicMock(), inference_api=MagicMock(), files_api=MagicMock() ) content = "test query content" - vector_db_ids = ["db1"] + vector_store_ids = ["db1"] chunk_metadata = ChunkMetadata( document_id="doc1", @@ -55,7 +55,7 @@ class TestRagQuery: query_response = QueryChunksResponse(chunks=[chunk], scores=[1.0]) rag_tool.vector_io_api.query_chunks = AsyncMock(return_value=query_response) - result = await rag_tool.query(content=content, vector_db_ids=vector_db_ids) + result = await rag_tool.query(content=content, vector_store_ids=vector_store_ids) assert result is not None expected_metadata_string = ( @@ -90,7 +90,7 @@ class TestRagQuery: files_api=MagicMock(), ) - vector_db_ids = ["db1", "db2"] + vector_store_ids = ["db1", "db2"] # Fake chunks from each DB chunk_metadata1 = ChunkMetadata( @@ -101,7 +101,7 @@ class TestRagQuery: ) chunk1 = Chunk( content="chunk from db1", - metadata={"vector_db_id": "db1", "document_id": "doc1"}, + metadata={"vector_store_id": "db1", "document_id": "doc1"}, stored_chunk_id="c1", chunk_metadata=chunk_metadata1, ) @@ -114,7 +114,7 @@ class TestRagQuery: ) chunk2 = Chunk( content="chunk from db2", - metadata={"vector_db_id": "db2", "document_id": "doc2"}, + metadata={"vector_store_id": "db2", "document_id": "doc2"}, stored_chunk_id="c2", chunk_metadata=chunk_metadata2, ) @@ -126,13 +126,13 @@ class TestRagQuery: ] ) - result = await rag_tool.query(content="test", vector_db_ids=vector_db_ids) + result = await rag_tool.query(content="test", vector_store_ids=vector_store_ids) returned_chunks = result.metadata["chunks"] returned_scores = result.metadata["scores"] returned_doc_ids = result.metadata["document_ids"] - returned_vector_db_ids = result.metadata["vector_db_ids"] + returned_vector_store_ids = result.metadata["vector_store_ids"] assert returned_chunks == ["chunk from db1", "chunk from db2"] assert returned_scores == (0.9, 0.8) assert returned_doc_ids == ["doc1", "doc2"] - assert returned_vector_db_ids == ["db1", "db2"] + assert returned_vector_store_ids == ["db1", "db2"]