Package dev.langchain4j.test.service
package dev.langchain4j.test.service
-
ClassDescriptionCaptures what AI Services do while a lambda runs: what they produce, which tools they execute, which sources they retrieve, which model calls they make, how many tokens they use and how they end.A lambda to capture that returns nothing.What happened during one AI Service invocation: what it produced, the tools it executed, the sources it retrieved, the calls to models made during it (its own calls to its chat model and the tokens they used, and the calls of the components it runs), how it ended, and the AI Service invocations that its work started (for example its tools, guardrails or content retrievers).Assertions on what an AI Service did: which tools were executed, with which arguments and in which order, which sources were retrieved, how many times the chat model and the other models were called, why the response finished and whether the invocation succeeded.A call to a chat model made during an AI Service invocation (see
ModelCall).A call to a decision model made during an AI Service invocation (seeModelCall).A call to a embedding model made during an AI Service invocation (seeModelCall).A call to a model made during an AI Service invocation: by the AI Service itself to its chat model (seeChatModelCall.isOwn()), or by the components it runs, for example a query transformer or a judge calling a chat model, an embedding model used for retrieval, or a scoring model that re-ranks the retrieved contents.A call to a moderation model made during an AI Service invocation (seeModelCall).A call to a scoring model made during an AI Service invocation (seeModelCall).