Skip to main content

Module vectors

Module vectors 

Source
Expand description

Vector-store abstractions: describe a collection’s fields, then read and write records through a provider-agnostic trait pair.

Ports the portable core of upstream’s agent_framework._vectors (#8014): VectorStoreField and VectorStoreCollectionDefinition describe a collection’s shape, VectorCollection is one collection’s data plane, and VectorStore is the connection that hands out collections. A provider crate implements the two traits; nothing here talks to a service.

§Divergence: records are serde_json::Value, not a registered model type

Roughly half of upstream’s module is a model layer: a @vector_store_model decorator that registers a Python class, walks its annotations, and generates encoders/decoders between instances of that class and the flat mappings a store wants. Rust needs none of it — a record type derives Serialize/Deserialize and serde already performs that conversion, with the field names checked at compile time rather than at registration time.

So a record here is a serde_json::Value object keyed by field name, exactly as the workflow engine passes payloads, and a caller with a typed struct converts at the boundary with serde_json::to_value / from_value. That keeps both traits object-safe, so a Box<dyn VectorCollection> can be swapped between providers — which a generic-over-record-type trait could not be.

The one piece of upstream’s model layer that is not redundant is the split between a field’s logical name and its storage name, since that is a property of the store rather than of the Rust type. VectorStoreCollectionDefinition::to_storage and VectorStoreCollectionDefinition::from_storage perform that renaming.

Modules§

filters
Portable vector-store filter expressions.
provider
A collection exposed to an agent as tools — see VectorCollectionContextProvider. A caller-owned vector collection, exposed to an agent as tools.

Structs§

DistanceFunction
How similarity between two vectors is measured. Open value wrapper, as IndexKind.
Filter
One field test.
FilterGroup
Several filters combined by a boolean operator.
InMemoryVectorStore
An in-memory VectorStore, for tests and for running a pipeline before a real store is provisioned.
IndexKind
How a vector index is built. Open value wrapper — the constants cover upstream’s list, and any other string a provider understands is accepted.
VectorCollectionContextProvider
Exposes a vector collection to an agent as tools. See the module docs.
VectorCollectionContextProviderBuilder
Builds a VectorCollectionContextProvider.
VectorSearchOptions
Paging and shaping options for a search.
VectorSearchResult
One search hit: the record, and the provider’s score for it.
VectorStoreCollectionDefinition
The shape of one vector-store collection: its fields, and the accessors a provider needs to build requests from them.
VectorStoreField
One field in a vector-store collection.

Enums§

FieldType
What role a field plays in a collection.
FilterExpression
A filter tree: either one field test or a group of them.
FilterGroupOperator
How a FilterGroup’s children combine.
FilterOperator
How one field is tested.
VectorToolKind
Which generated tool an approval mode applies to.

Constants§

DEFAULT_MAX_TOOL_BATCH_SIZE
The default cap on how many records or keys one tool call may carry.
DEFAULT_SEARCH_TOP
The default number of hits the search tool returns.
MAX_FILTER_DEPTH
Maximum nesting depth of a filter expression.
MAX_FILTER_NODES
Maximum number of nodes (leaves plus groups) in a filter expression.

Traits§

VectorCollection
One collection’s data plane: create/drop, read/write, and search.
VectorStore
A connection to a vector store: lists collections and hands them out.