Example usage:

// Initialize embeddings and chat model
const embeddings = new OpenAIEmbeddings();
const chatModel = new ChatOpenAI();

// Create retriever with hybrid search
const retriever = new AzionRetriever(embeddings, chatModel, {
searchType: 'hybrid',
similarityK: 3,
ftsK: 2,
dbName: 'my_docs',
metadataItems: ['category', 'author'],
vectorTable: 'documents',
ftsTable: 'documents_fts',
filters: [
{ operator: '=', column: 'status', value: 'published' }
]
});

// Retrieve relevant documents
const docs = await retriever.invoke(
"What are coral reefs in Australia?"
);

// Create retriever with similarity search only
const simRetriever = new AzionRetriever(embeddings, chatModel, {
searchType: 'similarity',
similarityK: 5,
dbName: 'my_docs',
vectorTable: 'documents'
});

// Customize entity extraction prompt
const customRetriever = new AzionRetriever(embeddings, chatModel, {
searchType: 'hybrid',
similarityK: 3,
ftsK: 2,
dbName: 'my_docs',
promptEntityExtractor: "Extract key entities from: {{query}}"
});

Hierarchy

  • BaseRetriever
    • AzionRetriever

Constructors

Properties

callbacks?: Callbacks

Optional callbacks to handle various events in the retrieval process.

dbName: string

Name of the database to search

embeddings: EmbeddingsInterface

Interface for generating embeddings from text

entityExtractor?: BaseChatModel<BaseChatModelCallOptions, AIMessageChunk>

Optional ChatModel used to extract entities from queries

expandedMetadata: boolean

Whether the metadata is contained in a single column or multiple columns

filters: AzionFilter[]

Array of filters to apply to search results

ftsK: number

Number of results to return from full text search. Minimum is 1.

ftsTable: string

Name of table containing documents for full text search

metadata?: Record<string, unknown>

Metadata to provide additional context or information about the retrieval operation.

metadataItems?: string[]

Optional metadata columns to include in results

name?: string
promptEntityExtractor: string

Prompt template for entity extraction

searchType?: "similarity" | "hybrid"

Type of search to perform - either hybrid (combining vector + FTS) or similarity only

similarityK: number

Number of results to return from similarity search. Minimum is 1.

tags?: string[]

Tags to label or categorize the retrieval operation.

vectorTable: string

Name of table containing vector embeddings for similarity search

verbose?: boolean

If set to true, enables verbose logging for the retrieval process.

Methods

  • Convert a runnable to a tool. Return a new instance of RunnableToolLike which contains the runnable, name, description and schema.

    Type Parameters

    • T extends string = string

    Parameters

    • fields: {
          description?: string;
          name?: string;
          schema: ZodType<T, ZodTypeDef, T>;
      }
      • Optionaldescription?: string

        The description of the tool. Falls back to the description on the Zod schema if not provided, or undefined if neither are provided.

      • Optionalname?: string

        The name of the tool. If not provided, it will default to the name of the runnable.

      • schema: ZodType<T, ZodTypeDef, T>

        The Zod schema for the input of the tool. Infers the Zod type from the input type of the runnable.

    Returns RunnableToolLike<ZodType<ToolCall | T, ZodTypeDef, ToolCall | T>, DocumentInterface<Record<string, any>>[]>

    An instance of RunnableToolLike which is a runnable that can be used as a tool.

  • Assigns new fields to the dict output of this runnable. Returns a new runnable.

    Parameters

    • mapping: RunnableMapLike<Record<string, unknown>, Record<string, unknown>>

    Returns Runnable<any, any, RunnableConfig<Record<string, any>>>

  • Default implementation of batch, which calls invoke N times. Subclasses should override this method if they can batch more efficiently.

    Parameters

    • inputs: string[]

      Array of inputs to each batch call.

    • Optionaloptions: Partial<RunnableConfig<Record<string, any>>> | Partial<RunnableConfig<Record<string, any>>>[]

      Either a single call options object to apply to each batch call or an array for each call.

    • OptionalbatchOptions: RunnableBatchOptions & {
          returnExceptions?: false;
      }

    Returns Promise<DocumentInterface<Record<string, any>>[][]>

    An array of RunOutputs, or mixed RunOutputs and errors if batchOptions.returnExceptions is set

  • Parameters

    • inputs: string[]
    • Optionaloptions: Partial<RunnableConfig<Record<string, any>>> | Partial<RunnableConfig<Record<string, any>>>[]
    • OptionalbatchOptions: RunnableBatchOptions & {
          returnExceptions: true;
      }

    Returns Promise<(Error | DocumentInterface<Record<string, any>>[])[]>

  • Parameters

    • inputs: string[]
    • Optionaloptions: Partial<RunnableConfig<Record<string, any>>> | Partial<RunnableConfig<Record<string, any>>>[]
    • OptionalbatchOptions: RunnableBatchOptions

    Returns Promise<(Error | DocumentInterface<Record<string, any>>[])[]>

  • Bind arguments to a Runnable, returning a new Runnable.

    Parameters

    • kwargs: Partial<RunnableConfig<Record<string, any>>>

    Returns Runnable<string, DocumentInterface<Record<string, any>>[], RunnableConfig<Record<string, any>>>

    A new RunnableBinding that, when invoked, will apply the bound args.

  • Extracts entities from a user query using the entityExtractor model.

    Parameters

    • query: string

      The user query

    Returns Promise<string>

    A promise that resolves with the extracted entities when the extraction is complete.

  • Generates SQL queries for full-text search and similarity search.

    Parameters

    • embeddedQuery: number[]

      The embedded query vector.

    • queryEntities: string

      The entities extracted from the query for full-text search.

    • metadata: string

      Additional metadata columns to be included in the results.

    Returns {
        ftsQuery: string;
        similarityQuery: string;
    }

    An object containing the FTS query and similarity query strings.

    • ftsQuery: string
    • similarityQuery: string
  • Parameters

    • Optional_: RunnableConfig<Record<string, any>>

    Returns Graph

  • Parameters

    • Optionalsuffix: string

    Returns string

  • Parameters

    • query: string

      The query string to retrieve relevant documents for.

    • Optionalconfig: Callbacks | BaseCallbackConfig

      Optional configuration object for the retrieval process.

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    A promise that resolves to an array of Document objects.

    Use .invoke() instead. Will be removed in 0.3.0.

    Main method used to retrieve relevant documents. It takes a query string and an optional configuration object, and returns a promise that resolves to an array of Document objects. This method handles the retrieval process, including starting and ending callbacks, and error handling.

  • Performs a hybrid search on the vector store, using cosine similarity and FTS search, and returns the top 'similarityK' + 'ftsK' similar documents.

    Parameters

    • query: string

      The user query

    Returns Promise<[Document<Record<string, any>>][]>

    A promise that resolves with the hybrid search results when the search is complete.

  • Executes a retrieval operation.

    Parameters

    • input: string

      The query string used to search for relevant documents.

    • Optionaloptions: RunnableConfig<Record<string, any>>

      (optional) Configuration options for the retrieval run, which may include callbacks, tags, and metadata.

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    A promise that resolves to an array of DocumentInterface instances representing the most relevant documents to the query.

  • Return a new Runnable that maps a list of inputs to a list of outputs, by calling invoke() with each input.

    Returns Runnable<string[], DocumentInterface<Record<string, any>>[][], RunnableConfig<Record<string, any>>>

  • Maps search results to Document objects.

    Parameters

    • searches: SearchEmbeddingsResponse[]

      An array of SearchEmbeddingsResponse objects.

    Returns [Document<Record<string, any>>][]

    An array of tuples, each containing a single Document object.

  • Pick keys from the dict output of this runnable. Returns a new runnable.

    Parameters

    • keys: string | string[]

    Returns Runnable<any, any, RunnableConfig<Record<string, any>>>

  • Create a new runnable sequence that runs each individual runnable in series, piping the output of one runnable into another runnable or runnable-like.

    Type Parameters

    • NewRunOutput

    Parameters

    • coerceable: RunnableLike<DocumentInterface<Record<string, any>>[], NewRunOutput, RunnableConfig<Record<string, any>>>

      A runnable, function, or object whose values are functions or runnables.

    Returns Runnable<string, Exclude<NewRunOutput, Error>, RunnableConfig<Record<string, any>>>

    A new runnable sequence.

  • Generates an error document based on the provided error information

    Parameters

    • error: undefined | {
          message: string;
          operation: string;
      }

      The error object containing details about the issue

    Returns Error

    A promise that resolves to an array containing a single Document representing the error

  • Performs a similarity search on the vector store and returns the top 'similarityK' similar documents.

    Parameters

    • query: string

      The query string.

    Returns Promise<[Document<Record<string, any>>][]>

    A promise that resolves with the similarity search results when the search is complete.

  • Stream output in chunks.

    Parameters

    • input: string
    • Optionaloptions: Partial<RunnableConfig<Record<string, any>>>

    Returns Promise<IterableReadableStream<DocumentInterface<Record<string, any>>[]>>

    A readable stream that is also an iterable.

  • Generate a stream of events emitted by the internal steps of the runnable.

    Use to create an iterator over StreamEvents that provide real-time information about the progress of the runnable, including StreamEvents from intermediate results.

    A StreamEvent is a dictionary with the following schema:

    • event: string - Event names are of the format: on_[runnable_type]_(start|stream|end).
    • name: string - The name of the runnable that generated the event.
    • run_id: string - Randomly generated ID associated with the given execution of the runnable that emitted the event. A child runnable that gets invoked as part of the execution of a parent runnable is assigned its own unique ID.
    • tags: string[] - The tags of the runnable that generated the event.
    • metadata: Record<string, any> - The metadata of the runnable that generated the event.
    • data: Record<string, any>

    Below is a table that illustrates some events that might be emitted by various chains. Metadata fields have been omitted from the table for brevity. Chain definitions have been included after the table.

    ATTENTION This reference table is for the V2 version of the schema.

    +----------------------+-----------------------------+------------------------------------------+
    | event                | input                       | output/chunk                             |
    +======================+=============================+==========================================+
    | on_chat_model_start  | {"messages": BaseMessage[]} |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chat_model_stream |                             | AIMessageChunk("hello")                  |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chat_model_end    | {"messages": BaseMessage[]} | AIMessageChunk("hello world")            |
    +----------------------+-----------------------------+------------------------------------------+
    | on_llm_start         | {'input': 'hello'}          |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_llm_stream        |                             | 'Hello'                                  |
    +----------------------+-----------------------------+------------------------------------------+
    | on_llm_end           | 'Hello human!'              |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chain_start       |                             |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chain_stream      |                             | "hello world!"                           |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chain_end         | [Document(...)]             | "hello world!, goodbye world!"           |
    +----------------------+-----------------------------+------------------------------------------+
    | on_tool_start        | {"x": 1, "y": "2"}          |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_tool_end          |                             | {"x": 1, "y": "2"}                       |
    +----------------------+-----------------------------+------------------------------------------+
    | on_retriever_start   | {"query": "hello"}          |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_retriever_end     | {"query": "hello"}          | [Document(...), ..]                      |
    +----------------------+-----------------------------+------------------------------------------+
    | on_prompt_start      | {"question": "hello"}       |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_prompt_end        | {"question": "hello"}       | ChatPromptValue(messages: BaseMessage[]) |
    +----------------------+-----------------------------+------------------------------------------+
    

    The "on_chain_*" events are the default for Runnables that don't fit one of the above categories.

    In addition to the standard events above, users can also dispatch custom events.

    Custom events will be only be surfaced with in the v2 version of the API!

    A custom event has following format:

    +-----------+------+------------------------------------------------------------+
    | Attribute | Type | Description                                                |
    +===========+======+============================================================+
    | name      | str  | A user defined name for the event.                         |
    +-----------+------+------------------------------------------------------------+
    | data      | Any  | The data associated with the event. This can be anything.  |
    +-----------+------+------------------------------------------------------------+
    

    Here's an example:

    import { RunnableLambda } from "@langchain/core/runnables";
    import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch";
    // Use this import for web environments that don't support "async_hooks"
    // and manually pass config to child runs.
    // import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch/web";

    const slowThing = RunnableLambda.from(async (someInput: string) => {
    // Placeholder for some slow operation
    await new Promise((resolve) => setTimeout(resolve, 100));
    await dispatchCustomEvent("progress_event", {
    message: "Finished step 1 of 2",
    });
    await new Promise((resolve) => setTimeout(resolve, 100));
    return "Done";
    });

    const eventStream = await slowThing.streamEvents("hello world", {
    version: "v2",
    });

    for await (const event of eventStream) {
    if (event.event === "on_custom_event") {
    console.log(event);
    }
    }

    Parameters

    • input: string
    • options: Partial<RunnableConfig<Record<string, any>>> & {
          version: "v1" | "v2";
      }
    • OptionalstreamOptions: Omit<EventStreamCallbackHandlerInput, "autoClose">

    Returns IterableReadableStream<StreamEvent>

  • Parameters

    • input: string
    • options: Partial<RunnableConfig<Record<string, any>>> & {
          encoding: "text/event-stream";
          version: "v1" | "v2";
      }
    • OptionalstreamOptions: Omit<EventStreamCallbackHandlerInput, "autoClose">

    Returns IterableReadableStream<Uint8Array>

  • Stream all output from a runnable, as reported to the callback system. This includes all inner runs of LLMs, Retrievers, Tools, etc. Output is streamed as Log objects, which include a list of jsonpatch ops that describe how the state of the run has changed in each step, and the final state of the run. The jsonpatch ops can be applied in order to construct state.

    Parameters

    • input: string
    • Optionaloptions: Partial<RunnableConfig<Record<string, any>>>
    • OptionalstreamOptions: Omit<LogStreamCallbackHandlerInput, "autoClose">

    Returns AsyncGenerator<RunLogPatch, any, unknown>

  • Returns Serialized

  • Default implementation of transform, which buffers input and then calls stream. Subclasses should override this method if they can start producing output while input is still being generated.

    Parameters

    • generator: AsyncGenerator<string, any, unknown>
    • options: Partial<RunnableConfig<Record<string, any>>>

    Returns AsyncGenerator<DocumentInterface<Record<string, any>>[], any, unknown>

  • Bind config to a Runnable, returning a new Runnable.

    Parameters

    • config: RunnableConfig<Record<string, any>>

      New configuration parameters to attach to the new runnable.

    Returns Runnable<string, DocumentInterface<Record<string, any>>[], RunnableConfig<Record<string, any>>>

    A new RunnableBinding with a config matching what's passed.

  • Create a new runnable from the current one that will try invoking other passed fallback runnables if the initial invocation fails.

    Parameters

    • fields: {
          fallbacks: Runnable<string, DocumentInterface<Record<string, any>>[], RunnableConfig<Record<string, any>>>[];
      } | Runnable<string, DocumentInterface<Record<string, any>>[], RunnableConfig<Record<string, any>>>[]

    Returns RunnableWithFallbacks<string, DocumentInterface<Record<string, any>>[]>

    A new RunnableWithFallbacks.

  • Bind lifecycle listeners to a Runnable, returning a new Runnable. The Run object contains information about the run, including its id, type, input, output, error, startTime, endTime, and any tags or metadata added to the run.

    Parameters

    • params: {
          onEnd?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
          onError?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
          onStart?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
      }

      The object containing the callback functions.

      • OptionalonEnd?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called after the runnable finishes running, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

      • OptionalonError?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called if the runnable throws an error, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

      • OptionalonStart?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called before the runnable starts running, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

    Returns Runnable<string, DocumentInterface<Record<string, any>>[], RunnableConfig<Record<string, any>>>

  • Add retry logic to an existing runnable.

    Parameters

    • Optionalfields: {
          onFailedAttempt?: RunnableRetryFailedAttemptHandler;
          stopAfterAttempt?: number;
      }
      • OptionalonFailedAttempt?: RunnableRetryFailedAttemptHandler
      • OptionalstopAfterAttempt?: number

    Returns RunnableRetry<string, DocumentInterface<Record<string, any>>[], RunnableConfig<Record<string, any>>>

    A new RunnableRetry that, when invoked, will retry according to the parameters.

  • Parameters

    • thing: any

    Returns thing is Runnable<any, any, RunnableConfig<Record<string, any>>>