Class EmbeddingDistanceEvalChain

Use embedding distances to score semantic difference between a prediction and reference.

Hierarchy

StringEvaluator
- EmbeddingDistanceEvalChain

Implements

EmbeddingDistanceEvalChainInput

Index

Constructors

constructor

new EmbeddingDistanceEvalChain(
fields: EmbeddingDistanceEvalChainInput,
): EmbeddingDistanceEvalChain
Parameters
- fields: EmbeddingDistanceEvalChainInput
Returns EmbeddingDistanceEvalChain
Overrides StringEvaluator.constructor
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/embedding_distance/base.ts:103

Properties

distanceMetric

distanceMetric: EmbeddingDistanceType = "cosine"

The distance metric to use for comparing the embeddings.

`Optional`embedding

embedding?: any

The embedding objects to vectorize the outputs.

`Optional`evaluationName

evaluationName?: string = ...

The name of the evaluation.

`Optional`memory

memory?: any

outputKey

outputKey: string = "score"

requiresInput

requiresInput: boolean = false

requiresReference

requiresReference: boolean = true

`Optional`skipInputWarning

skipInputWarning?: string = ...

`Optional`skipReferenceWarning

skipReferenceWarning?: string = ...

Accessors

inputKeys

get inputKeys(): string[]
Returns string[]
Overrides StringEvaluator.inputKeys
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/embedding_distance/base.ts:122

lc_namespace

get lc_namespace(): string[]
Returns string[]
Inherited from QAEvalChain.lc_namespace
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:41

outputKeys

get outputKeys(): string[]
Returns string[]
Overrides StringEvaluator.outputKeys
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/embedding_distance/base.ts:126

Methods

_call

_call(values: ChainValues, _runManager: any): Promise<ChainValues>
Run the core logic of this chain and return the output
Parameters
- values: ChainValues
- _runManager: any
Returns Promise<ChainValues>
Overrides StringEvaluator._call
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/embedding_distance/base.ts:130

_chainType

_chainType(): | "embedding_cosine_distance"
| "embedding_euclidean_distance"
| "embedding_manhattan_distance"
| "embedding_chebyshev_distance"
Return the string type key uniquely identifying this class of chain.

Returns
    | "embedding_cosine_distance"
    | "embedding_euclidean_distance"
    | "embedding_manhattan_distance"
    | "embedding_chebyshev_distance"
Overrides StringEvaluator._chainType
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/embedding_distance/base.ts:109

_evaluateStrings

_evaluateStrings(args: StringEvaluatorArgs, config: any): Promise<ChainValues>
Evaluate Chain or LLM output, based on optional input and label.
Parameters
- args: StringEvaluatorArgs
- config: any
Returns Promise<ChainValues>
The evaluation results containing the score or value. It is recommended that the dictionary contain the following keys:
- score: the score of the evaluation, if applicable.
- value: the string value of the evaluation, if applicable.
- reasoning: the reasoning for the evaluation, if applicable.
Overrides StringEvaluator._evaluateStrings
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/embedding_distance/base.ts:113

`Protected`_formatValues

_formatValues(values: any): Promise<any>
Parameters
- values: any
Returns Promise<any>
Inherited from StringEvaluator._formatValues
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:217

apply

apply(inputs: ChainValues[], config?: any[]): Promise<ChainValues[]>
Parameters
- inputs: ChainValues[]
- Optionalconfig: any[]
Returns Promise<ChainValues[]>
Deprecated
Use .batch() instead. Will be removed in 0.2.0.

Call the chain on all inputs in the list
Inherited from StringEvaluator.apply
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:258

call

call(values: any, config?: any, tags?: string[]): Promise<ChainValues>
Parameters
- values: any
- Optionalconfig: any
- Optionaltags: string[]
  Deprecated
Returns Promise<ChainValues>
Deprecated
Use .invoke() instead. Will be removed in 0.2.0.

Run the core logic of this chain and add to output if desired.

Wraps _call and handles memory.
Inherited from StringEvaluator.call
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:243

checkEvaluationArgs

checkEvaluationArgs(reference?: string, input?: string): void
Check if the evaluation arguments are valid.
Parameters
- Optionalreference: string
  The reference label.
- Optionalinput: string
  The input string.
Returns void
Throws
If the evaluator requires an input string but none is provided, or if the evaluator requires a reference label but none is provided.
Inherited from StringEvaluator.checkEvaluationArgs
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/base.ts:97

evaluateStrings

evaluateStrings(args: StringEvaluatorArgs, config?: any): Promise<ChainValues>
Evaluate Chain or LLM output, based on optional input and label.
Parameters
- args: StringEvaluatorArgs
- Optionalconfig: any
Returns Promise<ChainValues>
The evaluation results containing the score or value. It is recommended that the dictionary contain the following keys:
- score: the score of the evaluation, if applicable.
- value: the string value of the evaluation, if applicable.
- reasoning: the reasoning for the evaluation, if applicable.
Inherited from StringEvaluator.evaluateStrings
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/evaluation/base.ts:238

invoke

invoke(input: ChainValues, options?: any): Promise<ChainValues>
Invoke the chain with the provided input and returns the output.
Parameters
- input: ChainValues
  Input values for the chain run.
- Optionaloptions: any
Returns Promise<ChainValues>
Promise that resolves with the output of the chain run.
Inherited from StringEvaluator.invoke
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:86

prepOutputs

prepOutputs(
    inputs: Record<string, unknown>,
    outputs: Record<string, unknown>,
    returnOnlyOutputs?: boolean,
): Promise<Record<string, unknown>>
Parameters
- inputs: Record<string, unknown>
- outputs: Record<string, unknown>
- returnOnlyOutputs: boolean = false
Returns Promise<Record<string, unknown>>
Inherited from StringEvaluator.prepOutputs
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:149

run

run(input: any, config?: any): Promise<string>
Parameters
- input: any
- Optionalconfig: any
Returns Promise<string>
Deprecated
Use .invoke() instead. Will be removed in 0.2.0.
Inherited from StringEvaluator.run
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:190

serialize

serialize(): SerializedBaseChain
Return a json-like object representing this chain.

Returns SerializedBaseChain
Inherited from StringEvaluator.serialize
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:181

`Static`deserialize

deserialize(
data: SerializedBaseChain,
values?: LoadValues,
): Promise<BaseChain<ChainValues, ChainValues>>
Load a chain from a json-like object describing it.
Parameters
- data: SerializedBaseChain
- values: LoadValues = {}
Returns Promise<BaseChain<ChainValues, ChainValues>>
Inherited from StringEvaluator.deserialize
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:270

Class EmbeddingDistanceEvalChain

Hierarchy

Implements

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Parameters

Returns EmbeddingDistanceEvalChain

Properties

distanceMetric

Optionalembedding

OptionalevaluationName

Optionalmemory

outputKey

requiresInput

requiresReference

OptionalskipInputWarning

OptionalskipReferenceWarning

Accessors

inputKeys

Returns string[]

lc_namespace

Returns string[]

outputKeys

Returns string[]

Methods

_call

Parameters

Returns Promise<ChainValues>

_chainType

Returns | "embedding_cosine_distance" | "embedding_euclidean_distance" | "embedding_manhattan_distance" | "embedding_chebyshev_distance"

_evaluateStrings

Parameters

Returns Promise<ChainValues>

Protected_formatValues

Parameters

Returns Promise<any>

apply

Parameters

Returns Promise<ChainValues[]>

Deprecated

call

Parameters

Deprecated

Returns Promise<ChainValues>

Deprecated

checkEvaluationArgs

Parameters

Returns void

Throws

evaluateStrings

Parameters

Returns Promise<ChainValues>

invoke

Parameters

Returns Promise<ChainValues>

prepOutputs

Parameters

Returns Promise<Record<string, unknown>>

run

Parameters

Returns Promise<string>

Deprecated

serialize

Returns SerializedBaseChain

Staticdeserialize

Parameters

Returns Promise<BaseChain<ChainValues, ChainValues>>

Settings

On This Page

`Optional`embedding

`Optional`evaluationName

`Optional`memory

`Optional`skipInputWarning

`Optional`skipReferenceWarning

Returns
| "embedding_cosine_distance"
| "embedding_euclidean_distance"
| "embedding_manhattan_distance"
| "embedding_chebyshev_distance"

`Protected`_formatValues

`Static`deserialize