Uses of Class
com.hw.langchain.schema.AgentAction
-
Uses of AgentAction in com.hw.langchain.agents.agent
Modifier and TypeMethodDescriptionAgent.constructScratchpad
(List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps) Construct the scratchpad that lets the agent continue its thought process.Agent.getFullInputs
(List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps, Map<String, Object> kwargs) Create the full inputs for the LLMChain from intermediate steps.AgentExecutor.getToolReturn
(org.apache.commons.lang3.tuple.Pair<AgentAction, String> nextStepOutput) Check if the tool is a returning tool.Agent.plan
(List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps, Map<String, Object> kwargs) abstract AgentResult
BaseSingleActionAgent.plan
(List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps, Map<String, Object> kwargs) Given input, decided what to do.AgentExecutor.processOutput
(AgentFinish output, List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps) Agent.returnStoppedResponse
(String earlyStoppingMethod, List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps, Map<String, ?> kwargs) BaseSingleActionAgent.returnStoppedResponse
(String earlyStoppingMethod, List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps, Map<String, ?> kwargs) Return response when agent has been stopped due to max iterations.AgentExecutor.takeNextStep
(Map<String, BaseTool> nameToToolMap, Map<String, Object> inputs, List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps) Take a single step in the thought-action-observation loop. -
Uses of AgentAction in com.hw.langchain.agents.chat.base
Modifier and TypeMethodDescriptionChatAgent.constructScratchpad
(List<org.apache.commons.lang3.tuple.Pair<AgentAction, String>> intermediateSteps)