All Classes and Interfaces
Class
Description
Bedrock chat model
Abstract bedrock embedding model
Bedrock Streaming chat model
Abstract class for WorkerAI models as they are all initialized the same way.
Represents a response message from an AI (language model).
AI Services is a high-level API of LangChain4j to interact with
ChatLanguageModel and StreamingChatLanguageModel.Represents an Anthropic language model with a Messages (chat) API.
See more details here.
Represents an Anthropic language model with a Messages (chat) API.
Parses PDF file into a
Document using Apache PDFBox libraryParses Microsoft Office file into a
Document using Apache POI library.Parses files into
Documents using Apache Tika library, automatically detecting the file format.Multiple models leverage the same output format, so we can use this class to parse the response.
Error class.
Implementation of
EmbeddingStore using AstraDB.Builder for
Audio.Represents a request for
ChatMessage augmentation.Represents the result of a
ChatMessage augmentation.Represents an AWS credentials object, including access key ID, secret access key, and optional session token.
Represents Azure AI Search Service as a
ContentRetriever.Azure AI Search EmbeddingStore Implementation
Represents an Azure CosmosDB Mongo vCore as an embedding store.
You can read more about vector search using Azure Cosmos DB NoSQL
here.
Represents an OpenAI language model, hosted on Azure, that has a chat completion interface, such as gpt-3.5-turbo.
A factory for building
AzureOpenAiChatModel.Builder instances.You can get the latest model names from the Azure OpenAI documentation or by executing the Azure CLI command:
az cognitiveservices account list-models --resource-group "$RESOURCE_GROUP" --name "$AI_SERVICE" -o table
Represents an OpenAI embedding model, hosted on Azure, such as text-embedding-ada-002.
A factory for building
AzureOpenAiEmbeddingModel.Builder instances.Represents an OpenAI image model, hosted on Azure, such as dall-e-3.
A factory for building
AzureOpenAiImageModel.Builder instances.Represents an OpenAI language model, hosted on Azure, such as gpt-3.5-turbo-instruct.
A factory for building
AzureOpenAiLanguageModel.Builder instances.Deprecated, for removal: This API element is subject to removal in a future version.
Represents an OpenAI language model, hosted on Azure, that has a chat completion interface, such as gpt-3.5-turbo.
A factory for building
AzureOpenAiStreamingChatModel.Builder instances.Represents an OpenAI language model, hosted on Azure, such as gpt-3.5-turbo-instruct.
A factory for building
AzureOpenAiStreamingLanguageModel.Builder instances.This class can be used to estimate the cost (in tokens) before calling OpenAI or when using streaming.
Bedrock AI21 Labs model ids
Bedrock AI21 Labs model invoke response
Bedrock Anthropic model ids
Bedrock Anthropic Text Completions API Invoke response
...
Bedrock Anthropic model ids
Bedrock Anthropic Messages API Invoke response
...
Bedrock Chat model response
Bedrock Cohere model ids
Bedrock Cohere model invoke response
Bedrock embedding response
Bedrock Llama model ids
Bedrock Llama Invoke response
Bedrock Mistral model ids
Bedrock stability AI model
This is for image generation.
Bedrock Amazon Stability AI model ids
Bedrock Anthropic Invoke response
Bedrock Amazon Titan chat model
Bedrock Amazon Titan model ids
Bedrock Titan Chat response
Bedrock Titan embedding response
Implementation of
ChatMemoryStore using Astra DB Vector Search.Implementation of
EmbeddingStore using Cassandra.Represents a chain step that takes an input and produces an output.
Represents a language model that has a chat interface.
Represents the memory (history) of a chat conversation.
Provides instances of
ChatMemory.Represents a store for the
ChatMemory state.Represents a chat message.
A deserializer for
ChatMessage objects.A codec for serializing and deserializing
ChatMessage objects to and from JSON.A factory for creating
ChatMessageJsonCodec objects.The type of content, e.g.
The error context.
A
ChatLanguageModel listener that listens for requests, responses and errors.A request to the
ChatLanguageModel or StreamingChatLanguageModel,
intended to be used with ChatModelListener.The request context.
A response from the
ChatLanguageModel or StreamingChatLanguageModel,
intended to be used with ChatModelListener.The response context.
Represents a store for embeddings using the Chroma backend.
Represent the result of classification.
Interface for executing code.
An implementation of an
EmbeddingModel that uses
Cohere Embed API.A
ChatMemoryStore backed by an Oracle Coherence named map.A builder to create
CoherenceChatMemoryStore instances.An
EmbeddingStore backed by an Oracle Coherence NamedMap.A builder to create
CoherenceEmbeddingStore instances.An implementation of a
ScoringModel that uses
Cohere Rerank API.A
QueryTransformer that leverages a ChatLanguageModel to condense a given Query
along with a chat memory (previous conversation history) into a concise Query.Abstract base interface for message content.
Represents content relevant to a user
Query with the potential to enhance and ground the LLM's response.Injects given
Contents into a given UserMessage.The type of content, e.g.
A chain for conversing with a specified
ChatLanguageModel while maintaining a memory of the conversation.A chain for conversing with a specified
ChatLanguageModel
based on the information retrieved by a specified ContentRetriever.Utility class for calculating cosine similarity between two vectors.
Represents a Couchbase index as an embedding store.
Options which configure the creation of database schema objects, such as tables and indexes.
Utility class to guess the mime-type of a file from its path or URI.
Maps
Filter objects to Azure AI Search filter strings.Default implementation of
ContentAggregator intended to be suitable for the majority of use cases.Default implementation of
ContentInjector intended to be suitable for the majority of use cases.Metadata configuration implementation
Default implementation of
QueryRouter intended to be suitable for the majority of use cases.Default implementation of
QueryTransformer intended to be suitable for the majority of use cases.The default implementation of
RetrievalAugmentor intended to be suitable for the majority of use cases.Default implementation of
StructuredPromptFactory.Annotation to attach a description to a class field.
A dimension aware embedding model
A
ChatLanguageModel which throws a ModelDisabledException for all of its methodsAn
EmbeddingModel which throws a ModelDisabledException for all of its methodsAn
ImageModel which throws a ModelDisabledException for all of its methodsA
LanguageModel which throws a ModelDisabledException for all of its methodsA
ModerationModel which throws a ModelDisabledException for all of its methodsA
StreamingChatLanguageModel which throws a ModelDisabledException for all of its methodsA
StreamingLanguageModel which throws a ModelDisabledException for all of its methodsRepresents an unstructured piece of text that usually corresponds to a content of a single file.
Splits the provided
Document into characters and attempts to fit as many characters as possible
into a single TextSegment, adhering to the limit set by maxSegmentSize.Splits the provided
Document into lines and attempts to fit as many lines as possible
into a single TextSegment, adhering to the limit set by maxSegmentSize.Splits the provided
Document into paragraphs and attempts to fit as many paragraphs as possible
into a single TextSegment, adhering to the limit set by maxSegmentSize.Splits the provided
Document into parts using the provided regex and attempts to fit as many parts
as possible into a single TextSegment, adhering to the limit set by maxSegmentSize.Splits the provided
Document into sentences and attempts to fit as many sentences as possible
into a single TextSegment, adhering to the limit set by maxSegmentSize.Splits the provided
Document into words and attempts to fit as many words as possible
into a single TextSegment, adhering to the limit set by maxSegmentSize.Utility class for loading documents.
Defines the interface for parsing an
InputStream into a Document.A factory for creating
DocumentParser instances through SPI.Defines the interface for a Document source.
Defines the interface for splitting a document into text segments.
A factory for creating
DocumentSplitter instances through SPI.Defines the interface for transforming a
Document.Represents an Elasticsearch index as an embedding store
using the approximate kNN query implementation.
Represents an Elasticsearch index as an embedding store.
Represents an Elasticsearch index as an embedding store.
Represents a dense vector embedding of a text.
Represents a matched embedding along with its relevance score (derivative of cosine distance), ID, and original embedded content.
Represents a model that can convert a given text into an embedding (vector representation of the text).
A factory for creating
EmbeddingModel instances through SPI.A
TextClassifier that uses an EmbeddingModel and predefined examples to perform classification.Represents a request to search in an
EmbeddingStore.Represents a result of a search in an
EmbeddingStore.Represents a store for embeddings, also known as a vector database.
A
ContentRetriever that retrieves from an EmbeddingStore.The
EmbeddingStoreIngestor represents an ingestion pipeline and is responsible
for ingesting Documents into an EmbeddingStore.EmbeddingStoreIngestor builder.
Deprecated, for removal: This API element is subject to removal in a future version.
use
EmbeddingStoreContentRetriever instead.
Represents a database table where embeddings, text, and metadata are stored.
A builder that configures and builds an
EmbeddingTable.Utility methods for creating common exceptions.
Indicates that a class/constructor/method is experimental and might change in the future.
This class represents a filter that can be applied during search in an
EmbeddingStore.Parses a filter expression string into a
Filter object.The reason why a model call finished.
Represents a language model, hosted on GitHub Models, that has a chat completion interface, such as gpt-4o.
A factory for building
GitHubModelsChatModel.Builder instances.Represents an embedding model, hosted on GitHub Models, such as text-embedding-3-small.
A factory for building
GitHubModelsEmbeddingModel.Builder instances.Represents a language model, hosted on GitHub Models, that has a chat completion interface, such as gpt-4o.
A factory for building
GitHubModelsStreamingChatModel.Builder instances.Google Cloud Storage Document Loader to load documents from Google Cloud Storage buckets.
An implementation of a
WebSearchEngine that uses
Google Custom Search API for performing web searches.CodeExecutionEngine that uses GraalVM Polyglot/Truffle to execute provided JavaScript code.A tool that executes provided JavaScript code using GraalVM Polyglot/Truffle.
CodeExecutionEngine that uses GraalVM Polyglot/Truffle to execute provided Python code.A tool that executes provided Python code using GraalVM Polyglot/Truffle.
A codec for serializing and deserializing
ChatMessage objects to and from JSON.Possible harm categories for the generation of responses that have been blocked by the model.
Base class for hierarchical document splitters.
Extracts plain text from a given HTML document.
A factory for building
HuggingFaceChatModel.Builder instances.A factory for building
HuggingFaceEmbeddingModel.HuggingFaceEmbeddingModelBuilder instances.A factory for building
HuggingFaceLanguageModel.Builder instances.Represents an image as a URL or as a Base64-encoded string.
Builder for
Image.Represents an image with a DetailLevel.
The detail level of an
Image.Text to Image generator model.
Infinispan Embedding Store
Holds configuration for the store
Represents the result of a
EmbeddingStoreIngestor ingestion process.Implementation of
ChatMemoryStore that stores state of ChatMemory (chat messages) in-memory.An
EmbeddingStore that stores embeddings in memory.Annotation to mark methods where JaCoCo coverage should be ignored.
An implementation of an
EmbeddingModel that uses
Jina Embeddings API.An implementation of a
ScoringModel that uses
Jina Reranker API.A factory for building
JlamaChatModel.JlamaChatModelBuilder instances.A factory for building
JlamaEmbeddingModel.JlamaEmbeddingModelBuilder instances.A factory for building
JlamaLanguageModel.JlamaLanguageModelBuilder instances.A factory for building
JlamaStreamingChatModel.JlamaStreamingChatModelBuilder instances.A factory for building
JlamaStreamingLanguageModel.JlamaStreamingLanguageModelBuilder instances.Deprecated.
Do not use
Json from third-party modules.The abstract JSON codec interface.
A factory for creating
Json.JsonCodec instances through SPI.Can reference
JsonObjectSchema when recursion is required.A base interface for a JSON schema element.
Deprecated, for removal: This API element is subject to removal in a future version.
please use the new
JsonSchemaElement API instead to define the schema for tool parametersA tool that executes JS code using the Judge0 service, hosted by Rapid API.
Utility class with lambda-based streaming response handlers.
Langchain item that is serialized for the langchain integration use case
Marshaller to read and write embeddings to Infinispan
Langchain Metadata item that is serialized for the langchain integration use case
Marshaller to read and write metadata to Infinispan
LangchainSchemaCreator for Infinispan
Represents a language model that has a simple text interface (as opposed to a chat interface).
A
QueryRouter that utilizes a ChatLanguageModel to make a routing decision.Strategy applied if the call to the LLM fails of if LLM does not return a valid response.
See LocalAI documentation for more details.
A factory for building
LocalAiChatModel.LocalAiChatModelBuilder instances.See LocalAI documentation for more details.
A factory for building
LocalAiEmbeddingModel.LocalAiEmbeddingModelBuilder instances.See LocalAI documentation for more details.
A factory for building
LocalAiLanguageModel.LocalAiLanguageModelBuilder instances.See LocalAI documentation for more details.
A factory for building
LocalAiStreamingChatModel.LocalAiStreamingChatModelBuilder instances.See LocalAI documentation for more details.
A factory for building
LocalAiStreamingLanguageModel.LocalAiStreamingLanguageModelBuilder instances.The value of a method parameter annotated with @MemoryId will be used to find the memory belonging to that user/conversation.
Sanitizes the messages to conform to the format expected by the Anthropic API.
This chat memory operates as a sliding window of
MessageWindowChatMemory.maxMessages messages.Represents metadata of a
Document or a TextSegment.Represents metadata that may be useful or necessary for retrieval or augmentation purposes.
MetadataColumDefinition used to define column definition from sql String
Metadata configuration.
Metadata storage mode
COLUMN_PER_KEY: for static metadata, when you know in advance the list of metadata
COMBINED_JSON: For dynamic metadata, when you don't know the list of metadata that will be used.
Represents an Milvus index as an embedding store.
Represents a Mistral AI Chat Model with a chat completion interface, such as open-mistral-7b and open-mixtral-8x7b
This model allows generating chat completion of a sync way based on a list of chat messages.
A factory for building
MistralAiChatModel.MistralAiChatModelBuilder instances.Represents the available chat completion models for Mistral AI.
Represents a Mistral AI embedding model, such as mistral-embed.
A factory for building
MistralAiEmbeddingModel.MistralAiEmbeddingModelBuilder instances.The MistralAiEmbeddingModelName enum represents the available embedding models in the Mistral AI module.
Represents a collection of Mistral AI models.
A factory for building
MistralAiModels.MistralAiModelsBuilder instances.Represents the value of the 'type' field in the response_format parameter of the MistralAi Chat completions request.
Represents a Mistral AI Chat Model with a chat completion interface, such as mistral-tiny and mistral-small.
A factory for building
MistralAiStreamingChatModel.MistralAiStreamingChatModelBuilder instances.An exception thrown by a model that could be disabled by a user.
When a method in the AI Service is annotated with @Moderate, each invocation of this method will call not only the LLM,
but also the moderation model (which must be provided during the construction of the AI Service) in parallel.
Represents moderation status.
Thrown when content moderation fails, i.e., when content is flagged by the moderation model.
Represents a model that can moderate text.
Represents a MongoDB indexed collection as an embedding store.
A
ContentRetriever that retrieves from an Neo4jGraph.Represents a Vector index as an embedding store.
Creates an instance of Neo4jEmbeddingStore defining a
Driver
starting from uri, user and passwordAn integration with Nomic Atlas's Text Embeddings API.
A factory for building
OllamaChatModel.OllamaChatModelBuilder instances.A factory for building
OllamaEmbeddingModel.OllamaEmbeddingModelBuilder instances.A factory for building
OllamaLanguageModel.OllamaLanguageModelBuilder instances.A factory for building
OllamaStreamingChatModel.OllamaStreamingChatModelBuilder instances.A factory for building
OllamaStreamingLanguageModel.OllamaStreamingLanguageModelBuilder instances.Represents an OpenAI language model with a chat completion interface, such as gpt-3.5-turbo and gpt-4.
A factory for building
OpenAiChatModel.OpenAiChatModelBuilder instances.Represents an OpenAI embedding model, such as text-embedding-ada-002.
A factory for building
OpenAiEmbeddingModel.OpenAiEmbeddingModelBuilder instances.Represents an OpenAI DALL·E models to generate artistic images.
A factory for building
OpenAiImageModel.OpenAiImageModelBuilder instances.Represents an OpenAI language model with a completion interface, such as gpt-3.5-turbo-instruct.
Builder class for constructing instances of
OpenAiLanguageModel.A factory for building
OpenAiLanguageModel.OpenAiLanguageModelBuilder instances.Deprecated, for removal: This API element is subject to removal in a future version.
use one of the following enums instead:
OpenAiChatModelName, OpenAiEmbeddingModelName
OpenAiImageModelName, OpenAiLanguageModelName, OpenAiModerationModelNameRepresents an OpenAI moderation model, such as text-moderation-latest.
A factory for building
OpenAiModerationModel.OpenAiModerationModelBuilder instances.Represents an OpenAI language model with a chat completion interface, such as gpt-3.5-turbo and gpt-4.
A factory for building
OpenAiStreamingChatModel.OpenAiStreamingChatModelBuilder instances.Represents an OpenAI language model with a completion interface, such as gpt-3.5-turbo-instruct.
A factory for building
OpenAiStreamingLanguageModel.OpenAiStreamingLanguageModelBuilder instances.This class needs to be thread safe because it is called when a streaming result comes back
and there is no guarantee that this thread will be the same as the one that initiated the request,
in fact it almost certainly won't be.
This class can be used to estimate the cost (in tokens) before calling OpenAI or when using streaming.
Represents an OpenSearch index as an
embedding store.
An
EmbeddingStore which uses AI Vector Search capabilities of Oracle Database.Builder which configures and creates instances of
OracleEmbeddingStore.Represents an OVHcloud embedding model.
Parameter of a Tool
Builder for
PdfFile.PGVector EmbeddingStore Implementation
Represents a Pinecone index as an embedding store.
Represents a prompt (an input text sent to the LLM).
Represents a template of a prompt that can be reused multiple times.
A factory for creating prompt templates.
Interface for input for the factory.
Interface for a prompt template.
Represents a Qdrant collection as an
embedding store.
Represents a query from the user intended for retrieving relevant
Contents.Routes the given
Query to one or multiple ContentRetrievers.Implementation of Reciprocal Rank Fusion.
Represents a Redis index as an embedding store.
Utility class for converting between cosine similarity and relevance score.
A
ContentAggregator that performs re-ranking using a ScoringModel, such as Cohere.Represents the response from various types of models, including language, chat, embedding, and moderation models.
Represents the result of an AI Service invocation.
Augments the provided
ChatMessage with retrieved Contents.Deprecated, for removal: This API element is subject to removal in a future version.
Please use
ContentRetriever instead.Utility class for retrying actions.
This class encapsulates a retry policy.
This class encapsulates a retry policy builder.
Safety thresholds, for the harm categories for the generation of responses that have been blocked by the model.
Helper class to create a
com.google.cloud.vertexai.api.Schema
from a JSON schema string, or from a class by reflection on its public fields.Represents a classification label with score.
Represents a model capable of scoring a text against a query.
An implementation of a
WebSearchEngine that uses
Search API for performing web searches.Utility class for loading web documents using Selenium.
Utility wrapper around
ServiceLoader.load().
WARNING! Although fun and exciting, this class is dangerous to use! Do not ever use this in production!
The database user must have very limited READ-ONLY permissions!
Although the generated SQL is somewhat validated (to ensure that the SQL is a SELECT statement) using JSqlParser,
this class does not guarantee that the SQL will be harmless.
Parses an SQL "WHERE" clause into a
Filter object using
JSqlParser.Represents a language model that has a chat interface and can stream a response one token at a time.
Represents a language model that has a simple text interface (as opposed to a chat interface)
and can stream a response one token at a time.
Represents a handler for streaming responses from a language model.
Represents a structured prompt.
Utility class for
StructuredPrompt.Represents a factory for structured prompts.
Utility class for structured prompts.
Represents a system message, typically defined by a developer.
Specifies either a complete system message (prompt) or a system message template to be used each time an AI service is invoked.
Represents Tavily Search API as a
WebSearchEngine.Classifies a given text based on a set of labels.
Represents a text content.
Builder for
TextFile.Represents a semantically meaningful segment (chunk/piece/fragment) of a larger entity such as a document or chat conversation.
Defines the interface for transforming a
TextSegment.Represents an interface for estimating the count of tokens in various text types such as a text, message, prompt, text segment, etc.
Represents an interface for estimating the count of tokens in various texts, text segments, etc.
Represents an interface for estimating the count of tokens in various text types such as a text, prompt, text segment, etc.
Represents an interface for estimating the count of tokens in various text types such as a text, prompt, text segment, etc.
Represents a token stream from language model to which you can subscribe and receive updates
when a new token is available, when language model finishes streaming, or when an error occurs during streaming.
Represents the token usage of a response.
This chat memory operates as a sliding window of
TokenWindowChatMemory.maxTokens tokens.Java methods annotated with
@Tool are considered tools/functions that language model can execute/call.Tool calling mode, to instruct Gemini whether it can request calls to any functions,
to just a subset of the available functions, or to none at all.
Represents the execution of a tool, including the request and the result.
Represents an LLM-generated request to execute a tool.
ToolExecutionRequest builder static inner class.Represents the result of a tool execution in response to a
ToolExecutionRequest.A low-level executor/handler of a
ToolExecutionRequest.If a
Tool method parameter is annotated with this annotation,
memory id (parameter annotated with @MemoryId in AI Service) will be injected automatically.Deprecated, for removal: This API element is subject to removal in a future version.
please use the new
JsonObjectSchema API instead to define the schema for tool parameters.ToolParameters builder static inner class.A tool provider.
Describes a tool that language model can execute.
ToolSpecification builder static inner class.Utility methods for
ToolSpecifications.Represents a message from a user, typically an end user of the application.
Specifies either a complete user message or a user message template to be used each time an AI service is invoked.
The value of a method parameter annotated with @UserName will be injected into the field 'name' of a UserMessage.
Utility methods.
When a parameter of a method in an AI Service is annotated with
@V,
it becomes a prompt template variable.Utility class for validating method arguments.
Represents a Google Vertex AI language model with a chat completion interface, such as chat-bison.
A factory for building
VertexAiChatModel.Builder instances.Represents a Google Vertex AI embedding model, such as textembedding-gecko.
A factory for building
VertexAiChatModel.Builder instances.Represents a Google Vertex AI Gemini language model with a chat completion interface, such as gemini-pro.
A factory for building
VertexAiGeminiChatModel.VertexAiGeminiChatModelBuilder instances.Represents a Google Vertex AI Gemini language model with a stream chat completion interface, such as gemini-pro.
A factory for building
VertexAiGeminiStreamingChatModel.VertexAiGeminiStreamingChatModelBuilder instances.Image model for the Google Cloud Vertex AI Imagen image generation models.
Supported aspect ratios: 1:1, 9:16, 16:9, 4:3, and 3:4.
Image style can be specified for
imagen@002.Supported mime types: only PNG and JPEG image formats can be generated.
Specify whether persons are allowed to be generated.
A factory for building
VertexAiImageModel.Builder instances.Represents a Google Vertex AI language model with a text interface, such as text-bison.
A factory for building
VertexAiLanguageModel.Builder instances.Implementation of a
ScoringModel for the Google Cloud Vertex AI
Ranking API.Represents the Vespa - search engine and vector database.
Builder for
Video.An implementation of an
EmbeddingModel that uses
Voyage AI Embedding API.An implementation of a
ScoringModel that uses
Voyage AI Rerank API.Represents the Weaviate vector database.
Represents a web search engine that can be used to perform searches on the Web in response to a user query.
Represents general information about the web search performed.
Represents an organic search results are the web pages that are returned by the search engine in response to a search query.
Represents a search request that can be made by the user to perform searches in any implementation of
WebSearchEngine.Represents the response of a web search performed.
Public interface to interact with the WorkerAI API.
Represents a request for AI chat completion.
Represents a message in the AI chat.
Defines the roles a message can have in the chat conversation.
Wrapper for the chat completion response.
WorkerAI Chat model.
Internal Builder.
A factory for building
WorkersAiChatModel.Builder instances.Enum for Workers AI Chat Model Name.
Low level client to interact with the WorkerAI API.
An interceptor for HTTP requests to add an authorization token to the header.
WorkerAI Embedding model.
Internal Builder.
A factory for building
WorkersAiEmbeddingModel.Builder instances.Enum for Workers AI Embedding Model Name.
Request to compute embeddings
Response to compute embeddings
Beam to hold results
Request to generate an image.
Response to generate an image.
Body of the image generating process
WorkerAI Image model.
Internal Builder.
A factory for building
WorkersAiImageModel.Builder instances.Enum for Workers AI Omage Model Name.
WorkerAI Language model.
Internal Builder.
A factory for building
WorkersAiLanguageModel.Builder instances.Request to complete a text.
Wrapper for the text completion response.
Wrapper for the text completion response.
AzureOpenAiChatModelName,AzureOpenAiEmbeddingModelName,AzureOpenAiImageModelNameandAzureOpenAiLanguageModelName, instead.