All Classes and Interfaces
Class
Description
Parent advisor interface for all advisors.
Defines the context for executing a chain of advisors as part of processing a chat
request.
Context used to store metadata for chat client advisors.
Builder for
AdvisorObservationContext.Interface for an
ObservationConvention for chat client advisors.AI Advisor observation documentation.
High cardinality key names.
Low cardinality key names.
Utilities to work with advisors.
Base advisor that implements common aspects of the
CallAdvisor and
StreamAdvisor, reducing the boilerplate code needed to implement an advisor.A base interface for advisor chains that can be used to chain multiple advisors
together, both for call and stream advisors.
Base interface for chat memory advisors.
Advisor for execution flows ultimately resulting in a call to an AI model
A chain of
CallAdvisor instances orchestrating the execution of a
ChatClientRequest on the next CallAdvisor in the chain.Client to perform stateless requests to an AI Model, using a fluent API.
A mutable builder for creating a
ChatClient.Specification for a prompt system.
Common attributes used in
ChatClient context.Callback interface that can be used to customize a
ChatClient.Builder.Helper that for streaming chat responses, aggregate the chat response messages into a
single AssistantMessage.
Context used to store metadata for chat client workflows.
Interface for an
ObservationConvention for chat client workflows.Documented conventions for chat client observations.
Handler for emitting the chat client prompt content to logs.
Represents a request processed by a
ChatClient that ultimately is used to build
a Prompt to be sent to an AI model.Represents a response returned by a
ChatClient.A
CallAdvisor that uses a ChatModel to generate a response.A
StreamAdvisor that uses a ChatModel to generate a streaming response.Default implementation of the
AdvisorObservationConvention.Default implementation for the
BaseAdvisorChain.The default implementation of
ChatClient as created by the
ChatClient.Builder.build() } method.DefaultChatClientBuilder is a builder class for creating a ChatClient.
Default conventions to populate observations for chat client workflows.
Implementation of
Evaluator used to evaluate the factual accuracy of Large
Language Model (LLM) responses against provided context.Returns a new list of content (e.g list of messages of list of documents) that is a
subset of the input list of contents and complies with the max token size constraint.
Memory is retrieved added as a collection of messages to the prompt
Memory is retrieved added into the prompt's system text.
Builder for PromptChatMemoryAdvisor.
Evaluates the relevancy of a response to a query based on the context provided.
Represents a
Model response that includes the
entire response along withe specified response entity type.An advisor that blocks the call to the model provider if the user input contains any of
the sensitive words.
A simple logger advisor that logs the request and response messages.
Advisor for execution flows ultimately resulting in a streaming call to an AI model.
A chain of
StreamAdvisor instances orchestrating the execution of a
ChatClientRequest on the next StreamAdvisor in the chain.