Uses of Class
dev.langchain4j.test.mock.MockStreamingChatModel

Packages that use MockStreamingChatModel

Package	Description
dev.langchain4j.test.mock	Model mocks for tests: they need no network, answer the way a test tells them to, and record the requests they receive.

Uses of MockStreamingChatModel in dev.langchain4j.test.mock

Methods in dev.langchain4j.test.mock that return MockStreamingChatModel

Modifier and Type	Method	Description
MockStreamingChatModel	MockStreamingChatModel.andFails(RuntimeException exception)	Makes the response of the last step fail after its thinking and text were streamed, the way a broken connection does: the handler gets the partial responses and then the error, but no tool calls and no complete response.
static MockStreamingChatModel	MockStreamingChatModel.thatCallsTool(String toolName, String jsonArguments)	A model that answers the first request with a call of the given tool.
static MockStreamingChatModel	MockStreamingChatModel.thatCallsTool(String toolName, Map<String,?> arguments)	A model that answers the first request with a call of the given tool.
static MockStreamingChatModel	MockStreamingChatModel.thatFails(RuntimeException exception)	A model whose first request fails with the given exception, before anything is streamed: the handler gets it in onError.
static MockStreamingChatModel	MockStreamingChatModel.thatResponds(AiMessage... aiMessages)	A model that streams the given messages in order, one per request, in word-like tokens.
static MockStreamingChatModel	MockStreamingChatModel.thatResponds(ChatResponse chatResponse)	A model that answers the first request by streaming the message of the given response, in word-like tokens, and completing with exactly that response, including its metadata, for example its token usage, model name or finish reason.
static MockStreamingChatModel	MockStreamingChatModel.thatResponds(String text)	A model that answers the first request by streaming the given text, in word-like tokens.
static MockStreamingChatModel	MockStreamingChatModel.thatResponds(Function<ChatRequest, AiMessage> answers)	A model that computes the answer to the first request from the request and streams it, in word-like tokens.
static MockStreamingChatModel	MockStreamingChatModel.thatResponds(List<AiMessage> aiMessages)	A model that streams the given messages in order, one per request, in word-like tokens.
static MockStreamingChatModel	MockStreamingChatModel.thatStreams(String... tokens)	A model that answers the first request by streaming exactly the given tokens, which together make up one answer: thatStreams("Hel", "lo") streams "Hel" and then "lo", and completes with "Hello".
static MockStreamingChatModel	MockStreamingChatModel.thatStreams(List<String> tokens)	A model that answers the first request by streaming exactly the given tokens, see MockStreamingChatModel.thatStreams(String...).
MockStreamingChatModel	MockStreamingChatModel.thenCallsTool(String toolName, String jsonArguments)	Adds a step: the next request is answered with a call of the given tool.
MockStreamingChatModel	MockStreamingChatModel.thenCallsTool(String toolName, Map<String,?> arguments)	Adds a step: the next request is answered with a call of the given tool.
MockStreamingChatModel	MockStreamingChatModel.thenFails(RuntimeException exception)	Adds a step: the next request fails with the given exception before anything is streamed.
MockStreamingChatModel	MockStreamingChatModel.thenRepeats()	Answers every further request with the last step of the script.
MockStreamingChatModel	MockStreamingChatModel.thenResponds(AiMessage aiMessage)	Adds a step: the next request is answered by streaming the given message, in word-like tokens.
MockStreamingChatModel	MockStreamingChatModel.thenResponds(ChatResponse chatResponse)	Adds a step: the next request is answered by streaming the message of the given response, in word-like tokens, and completing with exactly that response, including its metadata, for example its token usage.
MockStreamingChatModel	MockStreamingChatModel.thenResponds(String text)	Adds a step: the next request is answered by streaming the given text, in word-like tokens.
MockStreamingChatModel	MockStreamingChatModel.thenStreams(String... tokens)	Adds a step: the next request is answered by streaming exactly the given tokens, which together make up one answer.
MockStreamingChatModel	MockStreamingChatModel.thenStreams(List<String> tokens)	Adds a step: the next request is answered by streaming exactly the given tokens, see MockStreamingChatModel.thenStreams(String...).
MockStreamingChatModel	MockStreamingChatModel.withListeners(ChatModelListener... listeners)	Notifies the given listeners of each call, like a real model does.
MockStreamingChatModel	MockStreamingChatModel.withListeners(List<ChatModelListener> listeners)	Notifies the given listeners of each call, like a real model does.
MockStreamingChatModel	MockStreamingChatModel.withSupportedCapabilities(Capability... capabilities)	Reports the given capabilities from MockStreamingChatModel.supportedCapabilities(), like a model that supports them.
MockStreamingChatModel	MockStreamingChatModel.withSupportedCapabilities(Set<Capability> capabilities)	Reports the given capabilities from MockStreamingChatModel.supportedCapabilities(), see MockStreamingChatModel.withSupportedCapabilities(Capability...).
MockStreamingChatModel	MockStreamingChatModel.withTokenUsage(@Nullable TokenUsage tokenUsage)	Reports the given token usage in the response to every request, except for a step that gives the whole response: that one reports exactly its own token usage.