Module●Since v0.3

utils/testing

Functions

function

asAsyncIterable→ AsyncIterable<T>

function

openAIReasoningTextChunks→ OpenAICompletionsStreamChunk[]

function

openAITextOnlyChunks→ OpenAICompletionsStreamChunk[]

function

openAITextOnlyChunksWithUsage→ OpenAICompletionsStreamChunk[]

function

openAIToolCallChunks→ OpenAICompletionsStreamChunk[]

function

sseResponseFromOpenAIChunks→ Response

Classes

class

FakeChatMessageHistory

Base class for all chat message histories. All chat message histories should extend this class.

class

FakeChatModel

Base class for chat models. It extends the BaseLanguageModel class and provides methods for generating chat based on input messages.

class

FakeEmbeddings

A class that provides fake embeddings by overriding the embedDocuments and embedQuery methods to return fixed values.

class

FakeListChatMessageHistory

Base class for all list chat message histories. All list chat message histories should extend this class.

class

FakeListChatModel

A fake Chat Model that returns a predefined list of responses. It can be used for testing purposes.

class

FakeLLM

LLM class that provides a simpler interface to subclass than BaseLLM.

Requires only implementing a simpler _call method instead of _generate.

class

FakeRetriever

Abstract base class for a document retrieval system, designed to process string queries and return the most relevant documents from a source.

BaseRetriever provides common properties and methods for derived retrievers, such as callbacks, tagging, and verbose logging. Custom retrieval systems should extend this class and implement _getRelevantDocuments to define the specific retrieval logic.

class

FakeRunnable

A Runnable is a generic unit of work that can be invoked, batched, streamed, and/or transformed.

class

FakeSplitIntoListParser

Parser for comma-separated values. It splits the input text by commas and trims the resulting values.

class

FakeStreamingChatModel

Base class for chat models. It extends the BaseLanguageModel class and provides methods for generating chat based on input messages.

class

FakeStreamingLLM

LLM class that provides a simpler interface to subclass than BaseLLM.

Requires only implementing a simpler _call method instead of _generate.

class

FakeTool

Base class for Tools that accept input of any shape defined by a Zod schema.

class

FakeTracer

Abstract base class for creating callback handlers in the LangChain framework. It provides a set of optional methods that can be overridden in derived classes to handle various events during the execution of a LangChain application.

class

FakeVectorStore

Class that extends VectorStore to store vectors in memory. Provides methods for adding documents, performing similarity searches, and creating instances from texts, documents, or an existing index.

A class that provides synthetic embeddings by overriding the embedDocuments and embedQuery methods to generate embeddings based on the input documents. The embeddings are generated by converting each document into chunks, calculating a numerical value for each chunk, and returning an array of these values as the embedding.