Class AgentEmbeddingService

Utility service for agent embedding operations. Uses agent data already loaded by AIEngine - no separate initialization needed. All methods are static - no instance state required.

Example

// Generate embeddings during AIEngine initialization
const entries = await AgentEmbeddingService.GenerateAgentEmbeddings(
  agents,
  (text) => aiEngine.EmbedTextLocal(text)
);

// Find similar agents
const matches = await AgentEmbeddingService.FindSimilarAgents(
  vectorService,
  "Handle customer support",
  (text) => aiEngine.EmbedTextLocal(text),
  5,
  0.7
);

Index

Constructors

constructor

Methods

Constructors

constructor

new AgentEmbeddingService(): AgentEmbeddingService
Returns AgentEmbeddingService

Methods

`Static`FindRelatedAgents

FindRelatedAgents(
    vectorService: SimpleVectorService<AgentEmbeddingMetadata>,
    agentId: string,
    topK?: number,
    minSimilarity?: number,
): AgentMatchResult[]
Find agents similar to a specific agent.
Parameters
- vectorService: SimpleVectorService<AgentEmbeddingMetadata>
  Vector service containing agent embeddings
- agentId: string
  The ID of the agent to find similar agents to
- topK: number = 5
  Maximum number of results to return (default: 5)
- minSimilarity: number = 0.5
  Minimum similarity score 0-1 (default: 0.5)
Returns AgentMatchResult[]
Array of matching agents (excludes the source agent)

Throws
Error if agent not found in embeddings
- Defined in AI/Engine/src/services/AgentEmbeddingService.ts:160

`Static`FindSimilarAgents

FindSimilarAgents(
    vectorService: SimpleVectorService<AgentEmbeddingMetadata>,
    taskDescription: string,
    embedFunction: (
        text: string,
    ) => Promise<{ model: MJAIModelEntityExtended; result: EmbedTextResult }>,
    topK?: number,
    minSimilarity?: number,
): Promise<AgentMatchResult[]>
Find agents similar to a given task description.
Parameters
- vectorService: SimpleVectorService<AgentEmbeddingMetadata>
  Vector service containing agent embeddings
- taskDescription: string
  The task description to match against agent capabilities
- embedFunction: (
  text: string,
  ) => Promise<{ model: MJAIModelEntityExtended; result: EmbedTextResult }>
  Function to generate embeddings (from AIEngine)
- topK: number = 5
  Maximum number of results to return (default: 5)
- minSimilarity: number = 0.5
  Minimum similarity score 0-1 (default: 0.5)
Returns Promise<AgentMatchResult[]>
Array of matching agents sorted by similarity score (highest first)

Throws
Error if embedding generation fails
- Defined in AI/Engine/src/services/AgentEmbeddingService.ts:94

`Static`GenerateAgentEmbeddings

GenerateAgentEmbeddings(
    agents: MJAIAgentEntityExtended[],
    embedFunction: (
        text: string,
    ) => Promise<{ model: MJAIModelEntityExtended; result: EmbedTextResult }>,
): Promise<VectorEntry<AgentEmbeddingMetadata>[]>
Generate embeddings for agents using provided embedding function. Called by AIEngine during AdditionalLoading.
Parameters
- agents: MJAIAgentEntityExtended[]
  Array of agents (already loaded by AIEngine)
- embedFunction: (
  text: string,
  ) => Promise<{ model: MJAIModelEntityExtended; result: EmbedTextResult }>
  Function to generate embeddings (from AIEngine)
Returns Promise<VectorEntry<AgentEmbeddingMetadata>[]>
Vector entries ready for loading into vector service
- Defined in AI/Engine/src/services/AgentEmbeddingService.ts:39

`Static`GetSimilarity

GetSimilarity(
    vectorService: SimpleVectorService<AgentEmbeddingMetadata>,
    agentId1: string,
    agentId2: string,
): number
Get the similarity score between two specific agents.
Parameters
- vectorService: SimpleVectorService<AgentEmbeddingMetadata>
  Vector service containing agent embeddings
- agentId1: string
  First agent ID
- agentId2: string
  Second agent ID
Returns number
Similarity score (0-1)

Throws
Error if either agent is not found
- Defined in AI/Engine/src/services/AgentEmbeddingService.ts:206

Class AgentEmbeddingService

Example

Index

Constructors

Methods

Constructors

constructor

Returns AgentEmbeddingService

Methods

`Static`FindRelatedAgents

Parameters

Returns AgentMatchResult[]

Throws

`Static`FindSimilarAgents

Parameters

Returns Promise<AgentMatchResult[]>

Throws

`Static`GenerateAgentEmbeddings

Parameters

Returns Promise<VectorEntry<AgentEmbeddingMetadata>[]>

`Static`GetSimilarity

Parameters

Returns number

Throws

Settings

On This Page

Class AgentEmbeddingService

Example

Index

Constructors

Methods

Constructors

constructor

Returns AgentEmbeddingService

Methods

StaticFindRelatedAgents

Parameters

Returns AgentMatchResult[]

Throws

StaticFindSimilarAgents

Parameters

Returns Promise<AgentMatchResult[]>

Throws

StaticGenerateAgentEmbeddings

Parameters

Returns Promise<VectorEntry<AgentEmbeddingMetadata>[]>

StaticGetSimilarity

Parameters

Returns number

Throws

Settings

On This Page

`Static`FindRelatedAgents

`Static`FindSimilarAgents

`Static`GenerateAgentEmbeddings

`Static`GetSimilarity