LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
LangGraph
  • Web
  • Channels
  • Pregel
  • Prebuilt
  • Remote
LangGraph SDK
  • Client
  • Auth
  • React
  • Logging
  • React Ui
  • Server
LangGraph Checkpoint
LangGraph Checkpoint MongoDB
LangGraph Checkpoint Postgres
  • Store
LangGraph Checkpoint Redis
  • Shallow
  • Store
LangGraph Checkpoint SQLite
LangGraph Checkpoint Validation
  • Cli
LangGraph API
LangGraph CLI
LangGraph CUA
  • Utils
LangGraph Supervisor
LangGraph Swarm
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

LangGraph
WebChannelsPregelPrebuiltRemote
LangGraph SDK
ClientAuthReactLoggingReact UiServer
LangGraph Checkpoint
LangGraph Checkpoint MongoDB
LangGraph Checkpoint Postgres
Store
LangGraph Checkpoint Redis
ShallowStore
LangGraph Checkpoint SQLite
LangGraph Checkpoint Validation
Cli
LangGraph API
LangGraph CLI
LangGraph CUA
Utils
LangGraph Supervisor
LangGraph Swarm
Language
Theme
JavaScript@langchain/langgraph-checkpointSearchItem
Interface●Since v0.0

SearchItem

Represents a search result item with relevance score. Extends the base Item interface with an optional similarity score.

Copy
interface SearchItem

Bases

Item

Properties

Inherited fromItem

Properties

PcreatedAt: Date
—

Timestamp of item creation.

Pkey: string
—

Unique identifier within the namespace.

Pnamespace: string[]
—

Hierarchical path for the item.

View source on GitHub
P
updatedAt
: Date
—

Timestamp of last update.

Pvalue: Record<string, any>
—

The stored data as an object. Keys are filterable.

property
createdAt: Date
property
key: string
property
namespace: string[]
property
score: number
property
updatedAt: Date
property
value: Record<string, any>

Timestamp of item creation.

Unique identifier within the namespace.

Hierarchical path defining the collection in which this document resides. Represented as an array of strings, allowing for nested categorization. For example: ["documents", "user123"]

Relevance/similarity score if from a ranked operation. Higher scores indicate better matches.

This is typically a cosine similarity score between -1 and 1, where 1 indicates identical vectors and -1 indicates opposite vectors.

Timestamp of last update.

The stored data as an object. Keys are filterable.