Crate entelix_memory 

entelix-memory

Tier-3 cross-thread persistent knowledge. Defines Store<V>, Namespace (mandatory tenant_id — invariant 11 / F2 mitigation), the Embedder / Retriever / VectorStore traits, and the five LangChain-style patterns: BufferMemory, SummaryMemory, EntityMemory, SemanticMemory<E, V>, EpisodicMemory<V>. Concrete Embedder / VectorStore / Retriever impls ship in companion crates .

Structs

BufferMemory

Bounded conversation buffer.

ConsolidatingBufferMemory

Layered memory: a BufferMemory for recent turns, a SummaryMemory for the running summary, and a Summarizer that bridges the two when the buffer’s policy fires.

ConsolidationContext

Inputs that a ConsolidationPolicy consults when deciding whether to consolidate. Carries the buffer plus optional signals (last-consolidated-at, current/available context tokens) so non-trivial policies — for example, “summarise once we use 80 % of the model’s context window” or “throttle consolidation to at most once per hour” — can express their decision without embedding their own clock or token counter.

CostCalculatorAdapter

Adapter that bridges any CostCalculator (ChatModel pricing source) into the EmbeddingCostCalculator surface.

Document

One retrieved document with optional similarity score.

EdgeId

Stable, opaque edge identifier minted by the backend.

Embedding

One embedded text’s vector plus optional usage metadata.

EmbeddingRetriever

Adapter that combines an Embedder and a VectorStore (scoped to one Namespace) into a Retriever.

EmbeddingUsage

Token-accounting metadata an Embedder reports alongside the computed vector. Mirrors the ChatModel Usage shape so cost meters can charge embedding calls with the same machinery they use for completions.

EntityMemory

Map of entity_name → EntityRecord keyed by namespace.

EntityRecord

One entity’s recorded fact plus provenance metadata.

Episode

One time-stamped episode of operator-shaped payload.

EpisodeId

Stable identifier for one episode. Backed by UUID v7 so two ids minted in order compare in the same order — the audit trail and external correlation paths stay consistent without a separate sequence column.

EpisodicMemory

Time-ordered append-only episode store keyed by Namespace.

GraphHop

One traversal hop produced by GraphMemory::traverse or GraphMemory::find_path.

IdentityReranker

No-op Reranker: returns the first top_k candidates in the order the underlying VectorStore produced them, copying the retrieval score into RerankedDocument::rerank_score so downstream consumers see a uniform shape.

InMemoryGraphMemory

In-process GraphMemory backed by BTreeMap adjacency lists, sharded per namespace.

InMemoryStore

In-process Store<V> backed by a HashMap keyed by (rendered_namespace, key). Cheap to clone — internal state is Arc<Mutex<...>>-shared.

InMemoryVectorStore

In-process VectorStore backed by a per-namespace Vec<Slot>.

MeteredEmbedder

Embedder decorator that emits OTel-compatible telemetry per call (and optional cost via EmbeddingCostCalculator).

MmrReranker

Maximal Marginal Relevance reranker.

Namespace

Hierarchical key prefix for memory operations.

NamespacePrefix

Hierarchical prefix used by crate::Store::list_namespaces.

NeverConsolidate

Never trigger. Useful as a default when consolidation is wired but the operator wants to disable it temporarily without rebuilding the agent graph.

NodeId

Stable, opaque node identifier minted by the backend.

OnMessageCount

Trigger consolidation once the buffer reaches max_messages.

OnTokenBudget

Trigger consolidation when the buffer’s total text length (summed UTF-8 byte length of every ContentPart::Text) exceeds max_bytes. Approximates a token-budget gate without needing a tokenizer in the SDK.

PolicyExtras

Optional signals fed into BufferMemory::should_consolidate_with. Operators that don’t track tokens or last-consolidated time can pass Self::default and the policy will see the buffer plus whatever the buffer itself tracks via BufferMemory::mark_consolidated.

PutOptions

Per-write knobs the operator may attach when calling Store::put_with_options. Default::default() corresponds to the simple Store::put path: no TTL, no extra metadata.

RerankedDocument

One reranked document paired with the score the Reranker assigned.

RetrievalQuery

Declarative description of one retrieval call.

SemanticMemory

Embedder + VectorStore + Namespace bundle.

SummaryMemory

Single-string summary keyed by Namespace.

Enums

Direction

Direction of edge traversal — outgoing edges leave a node, incoming edges arrive at it. Both returns the union.

VectorFilter

Predicate against Document::metadata used by VectorStore::search_filtered. Backends translate this into their native filter language (pgvector WHERE, qdrant Filter, lancedb where); backends that cannot honour a given variant fall back to filterless search and emit a LossyEncode-style warning at the operator layer.

Traits

ConsolidationPolicy

Decides whether the current buffered conversation should be consolidated.

Embedder

Text → vector encoder.

EmbeddingCostCalculator

Compute a monetary cost for one embedder call.

GraphMemory

Generic graph-of-knowledge memory. Trait so backends (Neo4j, ArangoDB, Postgres-with-recursive-CTE) can plug in without touching the consumer code; reference in-process impl is InMemoryGraphMemory.

Reranker

Re-rank a candidate document set against the originating query.

Retriever

Returns documents ranked by relevance to a RetrievalQuery.

SemanticMemoryBackend

Object-safe consumer trait — tier 3 of the semantic-memory layering documented at the module level. Consumers (tools, orchestration code, recipes) take Arc<dyn SemanticMemoryBackend> to operate on a namespace-scoped embed-and-search surface without parameterising over the concrete embedder / vector-store types.

Store

Persistent (or in-memory) key/value store, scoped by Namespace.

Summarizer

Reduces a buffer of conversation messages to a summary string.

VectorStore

Vector index keyed by Namespace. Backed by qdrant, lancedb, pgvector, etc. in companion crates.

Functions

first_non_finite_vector_value

Return the first non-finite vector element, if any.

validate_vector_shape

Validate vector dimension and finite values for vector-store calls.

Type Aliases

DocumentId

Stable identifier for an indexed document. Backends mint these at insertion time; passing the same id to VectorStore::update or VectorStore::delete is the canonical way to mutate or remove a previously-indexed document.