Class MultiRetrievalQAChain

A class that represents a multi-retrieval question answering chain in the LangChain framework. It extends the MultiRouteChain class and provides additional functionality specific to multi-retrieval QA chains.

Example

const multiRetrievalQAChain = MultiRetrievalQAChain.fromLLMAndRetrievers(
  new ChatOpenAI({ model: "gpt-4o-mini" }),
  {
    retrieverNames: ["aqua teen", "mst3k", "animaniacs"],
    retrieverDescriptions: [
      "Good for answering questions about Aqua Teen Hunger Force theme song",
      "Good for answering questions about Mystery Science Theater 3000 theme song",
      "Good for answering questions about Animaniacs theme song",
    ],
    retrievers: [
      new MemoryVectorStore().asRetriever(3),
      new MemoryVectorStore().asRetriever(3),
      new MemoryVectorStore().asRetriever(3),
    ],
    retrievalQAChainOpts: {
      returnSourceDocuments: true,
    },
  },
);

const result = await multiRetrievalQAChain.call({
  input:
    "In the Aqua Teen Hunger Force theme song, who calls himself the mike rula?",
});

console.log(result.sourceDocuments, result.text);

Hierarchy (View Summary)

MultiRouteChain
- MultiRetrievalQAChain

Index

Constructors

constructor

new MultiRetrievalQAChain(fields: MultiRouteChainInput): MultiRetrievalQAChain
Parameters
- fields: MultiRouteChainInput
Returns MultiRetrievalQAChain
Inherited from MultiRouteChain.constructor
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_route.ts:76

Properties

defaultChain

defaultChain: BaseChain

destinationChains

destinationChains: { [name: string]: BaseChain<ChainValues, ChainValues> }

`Optional`memory

memory?: any

routerChain

routerChain: RouterChain

silentErrors

silentErrors: boolean = false

Accessors

inputKeys

get inputKeys(): string[]
Returns string[]
Inherited from MultiRouteChain.inputKeys
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_route.ts:84

lc_namespace

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

outputKeys

get outputKeys(): string[]
Returns string[]
Overrides MultiRouteChain.outputKeys
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_retrieval_qa.ts:67

Methods

_call

_call(values: ChainValues, runManager?: any): Promise<ChainValues>
Run the core logic of this chain and return the output
Parameters
- values: ChainValues
- OptionalrunManager: any
Returns Promise<ChainValues>
Inherited from MultiRouteChain._call
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_route.ts:92

_chainType

_chainType(): string
Return the string type key uniquely identifying this class of chain.

Returns string
Overrides MultiRouteChain._chainType
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_retrieval_qa.ts:224

`Protected`_formatValues

_formatValues(values: any): Promise<any>
Parameters
- values: any
Returns Promise<any>
Inherited from MultiRouteChain._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 MultiRouteChain.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 MultiRouteChain.call
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:243

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 MultiRouteChain.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 MultiRouteChain.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 MultiRouteChain.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 MultiRouteChain.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 MultiRouteChain.deserialize
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/base.ts:270

`Static`fromLLMAndRetrievers

fromLLMAndRetrievers(
    llm: BaseLanguageModelInterface,
    __namedParameters: {
        defaults?: MultiRetrievalDefaults;
        multiRetrievalChainOpts?: Omit<MultiRouteChainInput, "defaultChain">;
        retrievalQAChainOpts?: Partial<
            Omit<RetrievalQAChainInput, "retriever" | "combineDocumentsChain">,
        > & { prompt?: any };
        retrieverDescriptions: string[];
        retrieverNames: string[];
        retrieverPrompts?: PromptTemplate[];
        retrievers: BaseRetrieverInterface[];
    },
): MultiRetrievalQAChain
A static method that creates an instance of MultiRetrievalQAChain from a BaseLanguageModel and a set of retrievers. It takes in optional parameters for the retriever names, descriptions, prompts, defaults, and additional options. It is an alternative method to fromRetrievers and provides more flexibility in configuring the underlying chains.
Parameters
- llm: BaseLanguageModelInterface
  A BaseLanguageModel instance.
- __namedParameters: {
      defaults?: MultiRetrievalDefaults;
      multiRetrievalChainOpts?: Omit<MultiRouteChainInput, "defaultChain">;
      retrievalQAChainOpts?: Partial<
          Omit<RetrievalQAChainInput, "retriever" | "combineDocumentsChain">,
      > & { prompt?: any };
      retrieverDescriptions: string[];
      retrieverNames: string[];
      retrieverPrompts?: PromptTemplate[];
      retrievers: BaseRetrieverInterface[];
  }
Returns MultiRetrievalQAChain
A new instance of MultiRetrievalQAChain.
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_retrieval_qa.ts:109

`Static`fromRetrievers

fromRetrievers(
    llm: BaseLanguageModelInterface,
    retrieverNames: string[],
    retrieverDescriptions: string[],
    retrievers: BaseRetrieverInterface[],
    retrieverPrompts?: PromptTemplate[],
    defaults?: MultiRetrievalDefaults,
    options?: Omit<MultiRouteChainInput, "defaultChain">,
): MultiRetrievalQAChain
Parameters
- llm: BaseLanguageModelInterface
- retrieverNames: string[]
- retrieverDescriptions: string[]
- retrievers: BaseRetrieverInterface[]
- OptionalretrieverPrompts: PromptTemplate[]
- Optionaldefaults: MultiRetrievalDefaults
- Optionaloptions: Omit<MultiRouteChainInput, "defaultChain">
Returns MultiRetrievalQAChain
Deprecated
Use fromRetrieversAndPrompts instead
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_retrieval_qa.ts:74

`Static`lc_name

lc_name(): string
Returns string
Inherited from MultiRouteChain.lc_name
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain/src/chains/router/multi_route.ts:64

Class MultiRetrievalQAChain

Example

Hierarchy (View Summary)

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Parameters

Returns MultiRetrievalQAChain

Properties

defaultChain

destinationChains

Optionalmemory

routerChain

silentErrors

Accessors

inputKeys

Returns string[]

lc_namespace

Returns string[]

outputKeys

Returns string[]

Methods

_call

Parameters

Returns Promise<ChainValues>

_chainType

Returns string

Protected_formatValues

Parameters

Returns Promise<any>

apply

Parameters

Returns Promise<ChainValues[]>

Deprecated

call

Parameters

Deprecated

Returns Promise<ChainValues>

Deprecated

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>>

StaticfromLLMAndRetrievers

Parameters

Returns MultiRetrievalQAChain

StaticfromRetrievers

Parameters

Returns MultiRetrievalQAChain

Deprecated

Staticlc_name

Returns string

Settings

On This Page

`Optional`memory

`Protected`_formatValues

`Static`deserialize

`Static`fromLLMAndRetrievers

`Static`fromRetrievers

`Static`lc_name