All Classes and Interfaces
Class
Description
Abstract class for the Bedrock API.
Encapsulates the metrics about the model invocation.
Abstract class that serves as a base for chat memory advisors.
Abstract builder for
AbstractChatMemoryAdvisor.Abstract
StructuredOutputConverter implementation that uses a pre-configured
DefaultConversionService to convert the LLM output into the desired type
format.Abstract implementation of the
EmbeddingModel interface that provides
dimensions calculation caching.AbstractFilterExpressionConverter is an abstract class that implements the
FilterExpressionConverter interface.
The AbstractMessage class is an abstract implementation of the Message interface.
Abstract
StructuredOutputConverter implementation that uses a pre-configured
MessageConverter to convert the LLM output into the desired type format.Abstract base class for
VectorStore implementations that provides observation
capabilities.Abstract base class for tool call support.
Represents the response received when requesting an access token.
The data of the chat client request that can be modified before the execution of the
ChatClient's call method
Builder for
AdvisedRequest.The data of the chat client response that can be modified before the call returns.
Builder for
AdvisedResponse.Parent advisor interface for all advisors.
Context used to store metadata for chat client advisors.
Builder for
AdvisorObservationContext.The type of the advisor.
Interface for an
ObservationConvention for chat client advisors.AI Advisor observation documentation.
High cardinality key names.
Low cardinality key names.
Java client for the Bedrock Jurassic2 chat model.
Ai21 Jurassic2 models version.
AI21 Jurassic2 chat request parameters.
Builder for
Ai21Jurassic2ChatBedrockApi.Ai21Jurassic2ChatRequest.Penalty with float scale value.
Penalty with integer scale value.
Ai21 Jurassic2 chat response.
The completions generated by the model.
Explains why the generation process was halted for a specific completion.
The generatedToken fields.
The prompt includes the raw text, the tokens with their log probabilities, and the top-K alternative tokens
at each position, if requested.
The textRange field indicates the start and end offsets of the token in the decoded text string.
Provides detailed information about each token in both the prompt and the completions.
The topTokens field is a list of the top K alternative tokens for this position, sorted by probability,
according to the topKReturn request parameter.
Collection of attribute keys used in AI observations (spans, metrics, events).
Collection of event names used in AI observations.
Collection of metric attributes used in AI observations.
Enumeration of metric names used in AI observations.
Metadata associated with an AI operation (e.g.
Builder for
AiOperationMetadata.Types of operations performed by AI systems.
Collection of systems providing AI functionality.
Utility methods for creating native runtime hints.
Types of tokens produced and consumed in an AI operation.
AllOfGenerateResponseDetails
AllOfStreamResponseDetails
Routes a query to all the defined document retrievers.
Based on Bedrock's Anthropic
Claude Messages API.
Anthropic models version.
AnthropicChatRequest encapsulates the request parameters for the Anthropic messages model.
Builder for
Anthropic3ChatBedrockApi.AnthropicChatRequest.AnthropicChatResponse encapsulates the response parameters for the Anthropic
messages model.
AnthropicChatStreamingResponse encapsulates the streaming response parameters for
the Anthropic messages model.
Encapsulates a delta.
The streaming type of this message.
Encapsulates the metrics about the model invocation.
Message comprising the conversation.
The role of the author of this message.
Encapsulates the Amazon Bedrock invocation metrics.
The source of the media content.
The type of this message.
Options for the Anthropic 3 chat API.
Builder for
Anthropic3ChatOptions.The Anthropic API client.
Input messages.
Chat completion request object.
Metadata about the request.
Chat completion response object.
Check the Models
overview and model
comparison for additional details and options.
The content block of the message.
The source of the media content.
The ContentBlock type.
Content block delta event.
JSON content block delta.
Text content block delta.
Content block start event.
Text content block.
Tool use content block.
Content block stop event.
Error event.
Error body.
The event type of the streamed chunk.
Message delta event.
Message delta.
Message delta usage.
Message start event.
Message stop event.
Ping event.
The role of the author of this message.
Tool description.
Special event used to aggregate multiple tool use events into a single event with
list of aggregated ContentBlockToolUse.
Usage statistics.
Auto-configuration for Anthropic Chat Model.Anthropic Chat API.
Anthropic models version.
AnthropicChatRequest encapsulates the request parameters for the Anthropic chat model.
AnthropicChatResponse encapsulates the response parameters for the Anthropic chat model.
The
ChatModel implementation for the Anthropic service.The options to be used when sending a chat request to the Anthropic API.
Options for the Anthropic Chat API.
Anthropic Chat autoconfiguration properties.
Anthropic API connection properties.
RateLimit implementation for OpenAI.The AnthropicRuntimeHints class is responsible for registering runtime hints for
Anthropic API classes.
Usage implementation for AnthropicApi.Lets the generative know the content was generated as a response to the user.
Represents a response returned by the AI.
Metadata associated with an audio transcription result.
Options for audio transcription.
Represents an audio transcription prompt for an AI model.
A response containing an audio transcription result.
Metadata associated with an audio transcription response.
QianFan abstract authentication API.
Converts
Filter.Expression into Azure Search OData filter syntax.AzureOpenAI audio transcription client implementation for backed by
OpenAIClient.Options for audio transcription using Azure Open AI.
Structured response of the transcribed audio.
Segment of the transcribed text and its corresponding details.
Extracted word and it's corresponding timestamps.
Configuration properties for Azure OpenAI audio transcription.
Audio transcription metadata implementation for AzureOpenAI.
Auto-configuration for Azure OpenAI.ChatModel implementation for Microsoft Azure AI backed by
OpenAIClient.The configuration information for a chat completions request.
Azure Open AI Embedding Model implementation.
The configuration information for the embedding requests.
Usage implementation for Microsoft Azure OpenAI Service embedding.Represents the metadata for image generation using Azure OpenAI.
ImageModel implementation for Microsoft Azure AI backed by
OpenAIClient.The configuration information for a image generation request.
Configuration properties for Azure OpenAI image generation options.
Represents metadata associated with an image response from the Azure OpenAI image
model.
Utility enumeration for representing the response format that may be requested from the
Azure OpenAI model.
RuntimeHintsRegistrar for Azure OpenAI.Usage implementation for Microsoft Azure OpenAI Service chat.Uses Azure Cognitive Search as a backing vector store.
Auto-configuration for Azure Vector Store.Configuration properties for Azure Vector Store.
Base advisor that implements common aspects of the
CallAroundAdvisor and
StreamAroundAdvisor, reducing the boilerplate code needed to implement an
advisor.Contract for batching
Document objects so that the call to embed them could be
optimized.An implementation of
StructuredOutputConverter that transforms the LLM output
to a specific object type using JSON schema.Auto-configuration for Bedrock Jurassic2 Chat Client.Java
ChatModel for the Bedrock Jurassic2 chat generative model.Request body for the /complete endpoint of the Jurassic-2 API.
Penalty object for frequency, presence, and count penalties.
Configuration properties for Bedrock Ai21Jurassic2.
Auto-configuration for Bedrock Anthropic Chat Client.Java
ChatModel and StreamingChatModel for the Bedrock Anthropic chat
generative.Configuration properties for Bedrock Anthropic Claude 3.
Auto-configuration for Bedrock Anthropic Chat Client.Java
ChatModel and StreamingChatModel for the Bedrock Anthropic chat
generative.Configuration properties for Bedrock Anthropic.
Configuration for AWS connection.Configuration properties for Bedrock AWS connection.
Auto-configuration for Bedrock Cohere Chat Client.A
ChatModel implementation that uses the Cohere Chat API.Options for the Bedrock Cohere chat API.
Bedrock Cohere Chat autoconfiguration properties.
Auto-configuration for Bedrock Cohere Embedding Model.EmbeddingModel implementation that uses the
Bedrock Cohere Embedding API.Options for the Bedrock Cohere embedding API.
Bedrock Cohere Embedding autoconfiguration properties.
Auto-configuration for Bedrock Converse Proxy Chat Client.Configuration properties for Bedrock Converse.
Auto-configuration for Bedrock Llama Chat Client.Java
ChatModel and StreamingChatModel for the Bedrock Llama chat
generative.Options for the Bedrock Llama Chat API.
Configuration properties for Bedrock Llama.
A
ChatModel implementation that uses the Amazon Bedrock Converse API to
interact with the Supported
models.The BedrockRuntimeHints class is responsible for registering runtime hints for Bedrock
AI API classes.
Auto-configuration for Bedrock Titan Chat Client.Implementation of the
ChatModel and StreamingChatModel interfaces that
uses the Titan Chat API.Options for the Titan Chat API.
Bedrock Titan Chat autoconfiguration properties.
Auto-configuration for Bedrock Titan Embedding Model.EmbeddingModel implementation that uses the
Bedrock Titan Embedding API.Options for the Titan Embedding API.
Bedrock Titan Embedding autoconfiguration properties.
Usage implementation for Bedrock API.Usage implementation for Bedrock Converse API.BestOfSequence
Around advisor that wraps the ChatModel#call(Prompt) method.
The Call Around Advisor Chain is used to invoke the next Around Advisor in the chain.
Create a CassandraChatMemory like
CassandraChatMemory.create(CassandraChatMemoryConfig.builder().withTimeToLive(Duration.ofDays(1)).build());
For example @see org.springframework.ai.chat.memory.CassandraChatMemoryAuto-configuration for CassandraChatMemory.Configuration for the Cassandra Chat Memory store.
Given a string sessionId, return the value for each primary key column.
Configuration properties for Cassandra chat memory.
The CassandraVectorStore is for managing and querying vector data in an Apache
Cassandra db.
Indexes are automatically created with COSINE.
Auto-configuration for Cassandra Vector Store.Configuration for the Cassandra vector store.
Given a string document id, return the value for each primary key column.
Given a list of primary key column values, return the document id.
Configuration properties for Cassandra Vector Store.
The Categories class represents a set of categories used to classify content.
This class represents the scores for different categories of content.
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.
Auto-configuration for ChatClient.Builder for configuring a
ChatClient.Builder.Configuration properties for the chat client builder.
Callback interface that can be used to customize a
ChatClient.Builder.An
ObservationFilter to include the chat prompt content in the observation.Context used to store metadata for chat client workflows.
Interface for an
ObservationConvention for chat client workflows.Documented conventions for chat client observations.
Abstract Data Type (ADT) encapsulating information on the completion choices in the AI
response.
The ChatMemory interface represents a storage for chat conversation history.
An
ObservationFilter to include the chat completion content in the observation.Handler for including the chat completion content in the observation as a span event.
Marker interface, to be used to store info on the model such as the current context
length.
Handler for generating metrics from chat model observations.
Utilities to process the prompt and completion content in observations for chat models.
Context used to store metadata for chat model exchanges.
Interface for an
ObservationConvention for chat model exchanges.Documented conventions for chat model observations.
Events for chat model operations.
High-cardinality observation key names for chat model operations.
Low-cardinality observation key names for chat model operations.
An
ObservationFilter to include the chat prompt content in the observation.Handler for including the chat prompt content in the observation as a span event.
Auto-configuration for Spring AI chat model observations.
Configuration properties for chat model observations.
ModelOptions representing the common options that are portable across different
chat models.A PromptTemplate that lets you specify the role as a string should the current
implementations and their roles not suffice for your needs.
The chat completion (e.g.
Models common AI provider metadata returned in an AI response.
Single-class Chroma API implementation based on the (unofficial) Chroma REST API.
Add embeddings to the chroma data store.
Chroma embedding collection.
Request to create a new collection with the given name and metadata.
Request to delete embedding from a collection.
Single query embedding response.
Object containing the get embedding results.
Get embeddings from a collection.
Request to get the nResults nearest neighbor embeddings for provided
queryEmbeddings.
A QueryResponse object containing the query results.
Configuration properties for Chroma API client.
Connection details for a Chroma service.
Converts
Filter.Expression into Chroma metadata filter expression format.ChromaVectorStore is a concrete implementation of the VectorStore
interface.Auto-configuration for Chroma Vector Store.Configuration properties for Chroma Vector Store.
Java client for the Bedrock Cohere chat model.
Cohere models version.
CohereChatRequest encapsulates the request parameters for the Cohere command model.
Builder for the CohereChatRequest.
Prevents the model from generating unwanted tokens or incentivize the model to include desired tokens.
(optional) Specify how and if the token likelihoods are returned with the response.
Specifies how the API handles inputs longer than the maximum token length.
CohereChatResponse encapsulates the response parameters for the Cohere command model.
Generated result along with the likelihoods for tokens requested.
The reason the response finished being generated.
Token likelihood.
Cohere Embedding API.
Cohere Embedding model ids.
The Cohere Embed model request.
Cohere Embedding API input types.
Specifies how the API handles inputs longer than the maximum token length.
Cohere Embedding response.
Converts Spring AI
Filter.Expression into Coherence Filter.
Integration of Coherence Coherence 24.09+ as a Vector Store.
Configuration properties for the common chat memory.
Common properties for vector stores.
CompatGenerateRequest
Combines documents retrieved based on multiple queries and from multiple data sources
by concatenating them into a single collection of documents.
Data structure that contains content and metadata.
Converts the Document text and metadata into an AI, prompt-friendly text
representation.
ContentFormatTransformer processes a list of documents by applying a content formatter
to each document.
Augments the user query with contextual data from the content of the provided
documents.
Amazon Bedrock Converse API utils.
Special event used to aggregate multiple tool use events into a single event with
list of aggregated ContentBlockToolUse.
Cosmos DB implementation.
Auto-configuration for CosmosDB Vector Store.Configuration properties for a CosmosDB vector store.
Configuration properties for CosmosDB Vector Store.
Default implementation of the
AdvisorObservationConvention.Implementation of the
CallAroundAdvisorChain and
StreamAroundAdvisorChain.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.
Default conventions to populate observations for chat model operations.
Default implementation of
ContentFormatter.Default conventions to populate observations for embedding model operations.
Default implementation of the
FunctionCallback.Builder.Default conventions to populate observations for image model operations.
Default implementation of the
Usage interface.Default conventions to populate observations for vector store operations.
Details
A document is a container for the content and metadata of a document.
A component for compressing the content of each document to reduce noise and redundancy
in the retrieved information, addressing challenges such as "lost-in-the-middle" and
context length restrictions from the model.
EmbeddingModel is a generic interface for embedding models.
Represents a request to embed a list of documents.
A component for combining documents retrieved based on multiple queries and from
multiple data sources into a single collection of documents.
A component for ordering and ranking documents based on their relevance to a query to
bring the most relevant documents to the top of the list, addressing challenges such as
"lost-in-the-middle".
Component responsible for retrieving
Documents from an underlying data source,
such as a search engine, a vector store, a database, or a knowledge graph.A component for removing irrelevant or redundant documents from a list of retrieved
documents, addressing challenges such as "lost-in-the-middle" and context length
restrictions from the model.
Write a list of
Document instances.ElasticsearchAiSearchFilterExpressionConverter is a class that converts
Filter.Expression objects into Elasticsearch query string representation.
The ElasticsearchVectorStore class implements the VectorStore interface and provides
functionality for managing and querying documents in Elasticsearch.
Auto-configuration for Elasticsearch Vector Store.Provided Elasticsearch vector option configuration.
Configuration properties for Elasticsearch Vector Store.
Represents a single embedding vector.
EmbeddingModel is a generic interface for embedding models.
Description of an embedding model.
Handler for generating metrics from embedding model observations.
Context used to store metadata for embedding model exchanges.
Interface for an
ObservationConvention for embedding model exchanges.Documented conventions for embedding model observations.
High-cardinality observation key names for embedding model operations.
Low-cardinality observation key names for embedding model operations.
Auto-configuration for Spring AI embedding model observations.
Options for embedding models.
Builder for
EmbeddingOptions.Request to embed a list of input instructions.
Embedding response object.
Common AI provider metadata returned in an embedding response.
Metadata associated with the embedding result.
Utility methods for embedding related operations.
A RateLimit implementation that returns zero for all property getters
A EmpytUsage implementation that returns zero for all property getters
An
ObservationHandler that logs errors using a Tracer.ErrorResponse
Represents an evaluation request, which includes the user's text, a list of content
data, and a chat response.
A utility to reformat extracted text content before encapsulating it in a
Document.The
Builder class is a nested static class of
ExtractedTextFormatter designed to facilitate the creation and
customization of instances of ExtractedTextFormatter.Implementation of
Evaluator used to evaluate the factual accuracy of Large
Language Model (LLM) responses against provided context.Writes the content of a list of
Documents into a file.Portable runtime generative for metadata filter expressions.
Triple that represents and filter boolean expression as
left type right.Filter expression operations.
Represents expression grouping (e.g.
String identifier representing an expression key.
Mark interface representing the supported expression types:
Filter.Key,
Filter.Value, Filter.Expression and Filter.Group.Represents expression value constant or constant array.
DSL builder for
Filter.Expression instances.Converters a generic, portable
Filter.Expression into a
VectorStore specific expression language
format.Parse a textual, vector-store agnostic, filter expression language into
Filter.Expression.Helper class providing various boolean transformation.
This class provides an empty implementation of
FiltersListener, which can be
extended to create a listener which only needs to handle a subset of the available
methods.This class provides an empty implementation of
FiltersVisitor, which can be
extended to create a visitor which only needs to handle a subset of the available
methods.This interface defines a complete listener for a parse tree produced by
FiltersParser.This interface defines a complete generic visitor for a parse tree produced by
FiltersParser.Gets or Sets FinishReason
This class extends PDFTextStripper to provide custom text extraction and formatting
capabilities for PDF pages.
Implementations of this interface provides instructions for how the output of a
language generative should be formatted.
Represents a model function call handler.
Builder for creating a
FunctionCallback instance.Function invoking builder interface.Method invoking builder interface.
A Spring
ApplicationContextAware implementation that provides a way to retrieve
a Function from the Spring context and wrap it into a FunctionCallback.Deprecated.
Deprecated.
in favor of
DefaultFunctionCallbackBuilderHelper class that reuses the
AbstractToolCallSupport to implement the function
call handling logic on the client side.Helper used to provide only the function definition, without the actual function
call implementation.
FunctionCallingOptions is a set of options that can be used to configure the function
calling behavior of the ChatModel.
Builder for
FunctionCallingOptions.Note that the underlying function is responsible for converting the output into format
that can be consumed by the Model.
Connection details for a GemFire service.
A VectorStore implementation backed by GemFire.
Auto-configuration for GemFire Vector Store.Configuration properties for GemFire Vector Store.
GenerateParameters
GenerateRequest
GenerateResponse
Represents a response returned by the AI.
The Generation class represents a response from a moderation process.
The SAP HANA Cloud vector engine offers multiple use cases in AI scenarios.
Auto-configuration for Hana Cloud Vector Store.The
HanaCloudVectorStoreConfig class represents the configuration for the
HanaCloudVectorStore.Configuration properties for Hana Cloud Vector Store.
The
HanaVectorEntity is an abstract class that represents a mapped superclass
for entities that have a vector representation stored in a HANA vector repository.The
HanaVectorRepository interface provides methods for interacting with a HANA
vector repository, which allows storing and querying vector embeddings.An implementation of
ChatModel that interfaces with HuggingFace Inference
Endpoints for text generation.Configuration properties for Hugging Face chat model.
Interface for generating unique document IDs.
Context used to store metadata for image model exchanges.
Interface for an
ObservationConvention for image model exchanges.Documented conventions for image model observations.
Events for image model operations.
High-cardinality observation key names for image model operations.
Low-cardinality observation key names for image model operations.
An
ObservationFilter to include the image prompt content in the observation.Auto-configuration for Spring AI image model observations.
Configuration properties for image model observations.
ImageOptions represent the common options, portable across different image generation
models.
The image completion (e.g.
Represents metadata associated with an image response.
Info
The InMemoryChatMemory class is an implementation of the ChatMemory interface that
represents an in-memory storage for chat conversation history.
Utility methods for Jackson.
A SHA-256 based ID generator that returns the hash as a UUID.
A class that reads JSON documents and converts them into a list of
Document
objects.Estimates the number of tokens in a given text or message using the JTokkit encoding
library.
Keyword extractor that uses generative to extract 'excerpt_keywords' metadata field.
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.
StructuredOutputConverter implementation that uses a
DefaultConversionService to convert the LLM output into a
List instance.Java client for the Bedrock Llama chat model.
Llama models version.
LlamaChatRequest encapsulates the request parameters for the Meta Llama chat model.
LlamaChatResponse encapsulates the response parameters for the Meta Llama chat model.
The reason the response finished being generated.
StructuredOutputConverter implementation that uses a pre-configured
MappingJackson2MessageConverter to convert the LLM output into a
java.util.Map<String, Object> instance.Reads the given Markdown resource and groups headers, paragraphs, or text divided by
horizontal lines (depending on the
MarkdownDocumentReaderConfig.horizontalRuleCreateDocument configuration) into
Documents.Common configuration for the
MarkdownDocumentReader.The Media class represents the data and metadata of a media attachment in a message.
Utility class for merging ChatCompletions instances and their associated objects.
The Message interface represents a message that can be sent or received in a chat
application.
Helper that for streaming chat responses, aggregate the chat response messages into a
single AssistantMessage.
Memory is retrieved added as a collection of messages to the prompt
Converts a list of messages to a prompt for bedrock models.
Enumeration representing types of
Messages in a chat application.A
FunctionCallback that invokes methods on objects via reflection, supporting:
Static and non-static methods
Any number of parameters (including none)
Any parameter/return types (primitives, objects, collections)
Special handling for ToolContext parameters
Automatically infers the input parameters JSON schema from method's argument types.Converts
Filter.Expression into Milvus metadata filter expression format.Connection details for a Milvus service client.
Parameters for Milvus client connection.
Milvus based implementation of the
VectorStore.Configuration for the Milvus vector store.
Auto-configuration for Milvus Vector Store.Configuration properties for Milvus Vector Store.
Gemini supports the following MIME types:
image/gif
image/png
image/jpeg
video/mov
video/mpeg
video/mp4
video/mpg
video/avi
video/wmv
video/mpegps
video/flv
https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini
Single class implementation of the MiniMax Chat Completion API and
MiniMax Embedding API.
Represents a chat completion response returned by model, based on the provided input.
Chat completion choice.
Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
Chat completion choice.
The reason the model stopped generating tokens.
Message comprising the conversation.
The function definition.
An array of content parts with a defined type.
The image content of the message.
The role of the author of this message.
The relevant tool call.
Creates a model response for the given chat conversation.
An object specifying the format that the model must output.
Helper factory that creates a tool_choice of type 'none', 'auto' or selected function by name.
MiniMax Chat Completion Models:
MiniMax Model.
List of multiple embedding responses.
MiniMax Embeddings Models:
Embeddings.
Creates an embedding vector representing the input text.
MiniMax Embeddings Types
Represents a tool the model may call.
Function definition.
Create a tool of type 'function' and the given function definition.
Log probability information for the choice.
Message content tokens with log probability information.
The most likely tokens and their log probability, at this token position.
Usage statistics for the completion request.
Common value constants for MiniMax api.
Auto-configuration for MiniMax Chat and Embedding Models.MiniMaxChatOptions represents the options for performing chat completion using the
MiniMax API.
Configuration properties for MiniMax chat model.
MiniMax Embedding Model implementation.
This class represents the options for MiniMax embedding.
Configuration properties for MiniMax embedding model.
The MiniMaxRuntimeHints class is responsible for registering runtime hints for MiniMax
API classes.
Helper class to support Streaming function calling.
Usage implementation for MiniMax.Single-class, Java Client library for Mistral AI platform.
Represents a chat completion response returned by model, based on the provided
input.
Chat completion choice.
Represents a streamed chunk of a chat completion response returned by model, based
on the provided input.
Chat completion choice.
The reason the model stopped generating tokens.
Message comprising the conversation.
The function definition.
The role of the author of this message.
The relevant tool call.
Creates a model request for chat conversation.
An object specifying the format that the model must output.
Specifies a tool the model should use.
List of well-known Mistral chat models.
Represents an embedding vector returned by embedding endpoint.
List of multiple embedding responses.
List of well-known Mistral embedding models.
Creates an embedding vector representing the input text.
Represents a tool the model may call.
Function definition.
Create a tool of type 'function' and the given function definition.
Log probability information for the choice.
Message content tokens with log probability information.
The most likely tokens and their log probability, at this token position.
Usage statistics.
Auto-configuration for Mistral AI.Represents a Mistral AI Chat Model.
Options for the Mistral AI Chat API.
Configuration properties for Mistral AI chat.
Common properties for Mistral AI.
Provides the Mistral AI Embedding Model.
Options for the Mistral AI Embedding API.
Configuration properties for MistralAI embedding model.
Parent properties for Mistral AI.
The MistralAiRuntimeHints class is responsible for registering runtime hints for
Mistral AI API classes.
Helper class to support Streaming function calling.
Usage implementation for Mistral AI.The Model interface provides a generic API for invoking AI models.
Describes an AI model's basic characteristics.
Options for managing models in Ollama.
Context used when sending a request to a machine learning model and waiting for a
response from the model provider.
Interface representing the customizable options for AI model interactions.
Utility class for manipulating
ModelOptions objects.Interface representing a request to an AI model.
Interface representing the response received from an AI model.
This interface provides methods to access the main output of the AI model and the
metadata associated with this result.
Generate metrics about the model usage in the context of an AI operation.
The Moderation class represents the result of a moderation process.
An interface that represents metadata associated with the results of a moderation
generation process.
Represents a single message intended for moderation, encapsulating the text content.
The ModerationModel interface defines a generic AI model for moderation.
Represents the options for moderation.
A builder class for creating instances of ModerationOptions.
Represents a prompt for moderation containing a single message and the options for the
moderation model.
Represents a response from a moderation process, encapsulating the moderation metadata
and the generated content.
Defines the metadata associated with a moderation response, extending a base response
interface.
Represents the result of a moderation process, indicating whether content was flagged,
the categories of moderation, and detailed scores for each category.
Converts
Filter.Expression into MongoDB Atlas metadata filter expression
format.A
VectorStore implementation that uses MongoDB Atlas for storing andAuto-configuration for MongoDB Atlas Vector Store.Configuration properties for MongoDB Atlas Vector Store.
Single-class, Java Client library for Moonshot platform.
Represents a chat completion response returned by model, based on the provided
input.
Chat completion choice.
Represents a streamed chunk of a chat completion response returned by model, based
on the provided input.
Chat completion choice.
The reason the model stopped generating tokens.
Message comprising the conversation.
The function definition.
The role of the author of this message.
The relevant tool call.
Creates a model response for the given chat conversation.
Helper factory that creates a tool_choice of type 'none', 'auto' or selected
function by name.
Moonshot Chat Completion Models:
MOONSHOT_V1_8K - moonshot-v1-8k
MOONSHOT_V1_32K - moonshot-v1-32k
MOONSHOT_V1_128K - moonshot-v1-128k
Represents a tool the model may call.
Function definition.
Create a tool of type 'function' and the given function definition.
Usage statistics.
Auto-configuration for Moonshot Chat Model.MoonshotChatModel is a
ChatModel implementation that uses the MoonshotOptions for Moonshot chat completions.
Configuration properties for Moonshot chat client.
Parent properties for Moonshot.
Constants for Moonshot API.
Parent properties for Moonshot.
The MoonshotRuntimeHints class is responsible for registering runtime hints for
Moonshot API classes.
Helper class to support Streaming function calling.
Represents the usage of a Moonshot model.
Uses a large language model to expand a query into multiple semantically diverse
variations to capture different perspectives, useful for retrieving additional
contextual information and increasing the chances of finding relevant results.
Converts
Filter.Expression into Neo4j condition expression format.A vector store implementation that stores and retrieves vectors in a Neo4j database.
An enum to configure the distance function used in the Neo4j vector index.
Configuration for the Neo4j vector store.
Auto-configuration for Neo4j Vector Store.Configuration properties for Neo4j Vector Store.
Root of the hierarchy of Model access exceptions that are considered non-transient -
where a retry of the same operation would fail unless the cause of the Exception is
corrected.
ChatModel implementation that uses the OCI GenAI Chat API.Configuration properties for OCI Cohere chat model.
The configuration information for OCI chat requests
Configuration properties for OCI connection.
EmbeddingModel implementation that uses the
OCI GenAI Embedding API.Configuration properties for OCI embedding model.
The configuration information for OCI embedding requests
Auto-configuration for Oracle Cloud Infrastructure Generative
AI.Java Client for the Ollama API.
Chat request object.
Represents a tool the model may call.
Function definition.
Create a tool of type 'function' and the given function definition.
Ollama chat response object.
Generate embeddings from a model.
The response object returned from the /embedding endpoint.
Chat message object.
The role of the message in the conversation.
The relevant tool call.
The function definition.
Auto-configuration for Ollama Chat Client.ChatModel implementation for Ollama.Ollama Chat autoconfiguration properties.
Usage implementation for OllamaConnection details for an Ollama service.
Ollama connection autoconfiguration properties.
EmbeddingModel implementation for Ollama.Ollama Embedding autoconfiguration properties.
Usage implementation for Ollama embeddings.Ollama initialization configuration properties.
Helper class for common Ollama models.
Manage the lifecycle of models in Ollama.
Helper class for creating strongly-typed Ollama options.
The OllamaRuntimeHints class is responsible for registering runtime hints for Ollama AI
API classes.
Single class implementation of the
OpenAI Chat Completion
API and OpenAI
Embedding API.
Represents a chat completion response returned by model, based on the provided
input.
Chat completion choice.
Represents a streamed chunk of a chat completion response returned by model, based
on the provided input.
Chat completion choice.
The reason the model stopped generating tokens.
Message comprising the conversation.
The function definition.
An array of content parts with a defined type.
Shortcut constructor for an image content.
The role of the author of this message.
The relevant tool call.
Creates a model response for the given chat conversation.
Options for streaming response.
Helper factory that creates a tool_choice of type 'none', 'auto' or selected function by name.
Represents an embedding vector returned by embedding endpoint.
List of multiple embedding responses.
OpenAI Embeddings Models:
Embeddings.
Creates an embedding vector representing the input text.
Represents a tool the model may call.
Function definition.
Create a tool of type 'function' and the given function definition.
Log probability information for the choice.
Message content tokens with log probability information.
The most likely tokens and their log probability, at this token position.
Usage statistics for the completion request.
Breakdown of tokens used in a completion
Breakdown of tokens used in the prompt
Thrown on 4xx client errors, such as 401 - Incorrect API key provided, 401 - You must
be a member of an organization to use the API, 429 - Rate limit reached for requests,
429 - You exceeded your current quota , please check your plan and billing details.
Common value constants for OpenAI api.
Enumeration of OpenAI API response headers.Turn audio into text or text into audio.
Request to generates audio from the input text.
The format to audio in.
Builder for the SpeechRequest.
The voice to use for synthesis.
The Transcription
Object represents a verbose json transcription response returned by model,
based on the provided input.
Segment of the transcribed text and its corresponding details.
Extracted word and it corresponding timestamps.
Request to transcribe an audio file to text.
The format of the transcript and translation outputs, in one of these options:
json, text, srt, verbose_json, or vtt.
Request to translate an audio file to English.
TTS is an AI model that converts text to natural sounding spoken text.
Whisper is a
general-purpose speech recognition model.
OpenAI audio speech client implementation for backed by
OpenAiAudioApi.Options for OpenAI text to audio - speech synthesis.
Configuration properties for OpenAI audio speech.
Audio speech metadata implementation for OpenAI.
OpenAI audio transcription client implementation for backed by
OpenAiAudioApi.OpenAI Audio Transcription Options.
Audio transcription metadata implementation for OpenAI.
Auto-configuration for OpenAI.Options for the OpenAI Chat API.
Open AI Embedding Model implementation.
OpenAI Embedding Options.
OpenAI Image API.
OpenAI Image API model.
OpenAiImageModel is a class that implements the ImageModel interface.
OpenAI Image API options.
OpenAI Image autoconfiguration properties.
OpenAI Moderation API.
OpenAiModerationModel is a class that implements the ModerationModel interface.
OpenAI Moderation API options.
OpenAI Moderation autoconfiguration properties.
RateLimit implementation for OpenAI.Utility used to extract known HTTP response headers for the OpenAI API.
The OpenAiRuntimeHints class is responsible for registering runtime hints for OpenAI
API classes.
Helper class to support Streaming function calling.
Usage implementation for OpenAI.A FilterExpressionConverter implementation for OpenSearch AI search filter expressions.
An ObservationVectorStore implementation that stores vectors in OpenSearch.
Integration of Oracle database 23ai as a Vector Store.
Auto-configuration for Oracle Vector Store.Configuration properties for Oracle Vector Store.
Groups the parsed PDF pages into
Documents.The ParagraphManager class is responsible for managing the paragraphs and hierarchy of
a PDF document.
Represents a document paragraph metadata and hierarchy.
Uses the PDF catalog (e.g.
Utility methods for
String parsing.Common configuration builder for the
PagePdfDocumentReader and the
ParagraphPdfDocumentReader.Re-implement the PDFLayoutTextStripperByArea on top of the PDFLayoutTextStripper
instead the original PDFTextStripper.
The PdfReaderRuntimeHints class is responsible for registering runtime hints for PDFBox
resources.
Converts
Filter.Expression into PgVector metadata filter expression format.Validates the schema of a PostgreSQL table used as a PGVectorStore.
Uses the "vector_store" table to store the Spring AI vector data.
Defaults to CosineDistance.
By default, pgvector performs exact nearest neighbor search, which provides perfect
recall.
Auto-configuration for PostgreSQL Vector Store.Configuration properties for PostgreSQL Vector Store.
Converts
Filter.Expression into Pinecone metadata filter expression format.A VectorStore implementation backed by Pinecone, a cloud-based vector database.
Configuration class for the PineconeVectorStore.
Auto-configuration for Pinecone Vector Store.Configuration properties for Pinecone Vector Store.
Auto-configuration class for PostgresMlEmbeddingModel.
PostgresML EmbeddingModel
PostgresML Embedding Options.
Configuration properties for Postgres ML.
PrefillToken
Converts
Filter.Expression into test string format.The Prompt class represents a prompt used in AI model requests.
Assertion utility class that assists in validating arguments for prompt-related
operations.
Memory is retrieved added into the prompt's system text.
Abstract Data Type (ADT) modeling metadata gathered by the AI during request
processing.
Abstract Data Type (ADT) modeling filter metadata for all prompts sent during an AI
request.
Strategy for pulling Ollama models.
Connection details for a Qdrant service client.
Qdrant vectorStore implementation.
Auto-configuration for Qdrant Vector Store.Configuration properties for Qdrant Vector Store.
Represents an access token for the QianFan API.
Single class implementation of the QianFan Chat Completion API and Embedding API.
Represents a chat completion response returned by model, based on the provided input.
Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
Message comprising the conversation.
The role of the author of this message.
Creates a model response for the given chat conversation.
An object specifying the format that the model must output.
QianFan Chat Completion Models:
QianFan Model.
Represents an embedding vector returned by embedding endpoint.
List of multiple embedding responses.
QianFan Embeddings Models:
Embeddings.
Creates an embedding vector representing the input text.
Usage statistics for the completion request.
QianFanAuthenticator is a class that authenticates and requests access token for the
QianFan API.
Auto-configuration for QianFan Chat, Embedding, and Image
Models.QianFanChatOptions represents the options for performing chat completion using the
QianFan API.
Configuration properties for QianFan chat model.
The ApiUtils class provides utility methods for working with API requests and
responses.
QianFan Embedding Client implementation.
This class represents the options for QianFan embedding.
Configuration properties for QianFan embedding model.
QianFan Image API.
QianFan Image API model.
QianFanImageModel is a class that implements the ImageModel interface.
QianFan Image API options.
QianFan Image autoconfiguration properties.
The QianFanRuntimeHints class is responsible for registering runtime hints for QianFan
API classes.
Usage implementation for QianFan.Represents a query in the context of a Retrieval Augmented Generation (RAG) flow.
A component for augmenting an input query with additional data, useful to provide a
large language model with the necessary context to answer the user query.
A component for expanding the input query into a list of queries, addressing challenges
such as poorly formed queries by providing alternative query formulations, or by
breaking down complex problems into simpler sub-queries,
A component for routing a query to one or more document retrievers.
A component for transforming the input query to make it more effective for retrieval
tasks, addressing challenges such as poorly formed queries, ambiguous terms, complex
vocabulary, or unsupported languages.
Context for the question is retrieved from a Vector Store and added to the prompt's
user text.
A random ID generator that returns a UUID.
Abstract Data Type (ADT) encapsulating metadata from an AI provider's API rate limits
granted to the API key in use and the API key's current balance.
Converts
Filter.Expression into Redis search filter expression format.The RedisVectorStore is for managing and querying vector data in a Redis database.
Configuration for the Redis vector store.
Auto-configuration for Redis Vector Store.Configuration properties for Redis Vector Store.
Deprecated.
since 1.0.0 M3 please use
CallAroundAdvisor or
StreamAroundAdvisor instead.Service that helps caching remote
Resources on the local file system.Miscellaneous Resource utility methods.
Represents a
Model response that includes the
entire response along withe specified response entity type.An object specifying the format that the model must output.
JSON schema object that describes the format of the JSON object.
Interface representing metadata associated with an AI model's response.
Interface representing metadata associated with the results of an AI model.
Advisor that implements common Retrieval Augmented Generation (RAG) flows using the
building blocks defined in the
org.springframework.ai.rag package and following
the Modular RAG Architecture.RetryUtils is a utility class for configuring and handling retry operations.
A
CallAroundAdvisor and StreamAroundAdvisor that filters out the
response if the user input contains any of the sensitive words.Utility class for working with Cassandra schema.
Similarity search request builder.
OCI serving mode.
Helper class to load the OCI Gen AI
ServingModehttps://www.elastic.co/guide/en/elasticsearch/reference/master/dense-vector.html
max_inner_product is currently not supported because the distance value is not
normalized and would not comply with the requirement of being between 0 and 1
A simple logger advisor that logs the request and response messages.
SimpleVectorStore is a simple implementation of the VectorStore interface.
The Speech class represents the result of speech synthesis from an AI model.
The
SpeechMessage class represents a single text message to be converted to
speech by the OpenAI TTS API.The
SpeechModel interface provides a way to interact with the OpenAI
Text-to-Speech (TTS) API.The
SpeechPrompt class represents a request to the OpenAI Text-to-Speech (TTS)
API.Creates a new instance of SpeechResponse with the given speech result.
Types of Spring AI constructs which can be observed.
Auto-configuration for AI Retry.Properties for AI Retry.
Exponential Backoff properties.
Converts a
Filter into a JSON Path expression.Represents the StabilityAI API.
Auto-configuration for StabilityAI Image Model.Represents metadata associated with the image generation process in the StabilityAI
framework.
StabilityAiImageModel is a class that implements the ImageModel interface.
StabilityAiImageOptions is an interface that extends ImageOptions.
Configuration properties for Stability AI image model.
Around advisor that runs around stream based requests.
The StreamAroundAdvisorChain is used to delegate the call to the next
StreamAroundAdvisor in the chain.
StreamDetails
Helper class to support streaming function calling.
The StreamingModel interface provides a generic API for invoking an AI models with
streaming response.
The
StreamingSpeechModel interface provides a way to interact with the OpenAI
Text-to-Speech (TTS) API using a streaming approach, allowing you to receive the
generated audio in a real-time fashion.StreamResponse
Converts the (raw) LLM output into a structured responses of type.
Enum representing different styles for images.
Title extractor with adjacent sharing that uses generative to extract
'section_summary', 'prev_section_summary', 'next_section_summary' metadata fields.
A message of the type 'system' passed as input.
A
DocumentReader that reads text from a Resource.A document reader that leverages Apache Tika to extract text from a variety of document
formats, such as PDF, DOC/DOCX, PPT/PPTX, and HTML.
Java client for the Bedrock Titan chat model.
Titan models version.
TitanChatRequest encapsulates the request parameters for the Titan chat model.
Titan request text generation configuration.
TitanChatResponse encapsulates the response parameters for the Titan chat model.
The reason the response finished being generated.
Titan response result.
Titan chat model streaming response.
Java client for the Bedrock Titan Embedding model.
Titan Embedding model ids.
Titan Embedding request parameters.
TitanEmbeddingRequest builder.
Titan Embedding response.
Token
Token count based strategy implementation for
BatchingStrategy.Estimates the number of tokens in a given text or message.
A
TextSplitter that splits text into chunks of a target size in tokens.Represents the context for tool execution in a function calling scenario.
The ToolResponseMessage class represents a message with a function content in a chat
application.
Utilities to prepare and process traces for observability.
An implementation of the AbstractEmbeddingModel that uses ONNX-based Transformer models
for text embeddings.
Auto-configuration for Transformers Embedding Model.Configuration properties for the Transformer Embedding model.
Configurations for the
HuggingFaceTokenizer used to convert sentences into
tokens.Root of the hierarchy of Model access exceptions that are considered transient - where
a previously failed operation might be able to succeed when the operation is retried
without any intervention by application-level functionality.
Uses a large language model to translate a query to a target language that is supported
by the embedding model used to generate the document embeddings.
A utility class that provides methods for resolving types and classes related to
functions.
Connection details for a Typesense service client.
DockerComposeConnectionDetailsFactory for TypesenseConnectionDetails.Converts
Filter.Expression into Typesense metadata filter expression format.Configuration properties for Typesense service client.
A ObservationVectorStore implementation that uses Typesense as the underlying storage.
Auto-configuration for Typesense Vector Store.Configuration properties for Typesense Vector Store.
Utility class for detecting and normalizing URLs.
Abstract Data Type (ADT) encapsulating metadata on the usage of an AI provider's API
per AI request.
A message of the type 'user' passed as input Messages with the user role are from the
end-user or developer.
The
VectorStore interface defines the operations for managing and querying
documents in a vector database.Memory is retrieved from a VectorStore added into the prompt's system text.
Retrieves documents from a vector store that are semantically similar to the input
query.
Builder for
VectorStoreDocumentRetriever.Collection of attribute keys used in vector store observations (spans, metrics,
events).
Auto-configuration for Spring AI vector store observations.
Utilities to process the query content in observations for vector store operations.
Context used to store metadata for vector store operations.
A
ObservationConvention for VectorStoreObservationContext.Documented conventions for vector store observations.
High-cardinality observation key names for vector store operations.
Low-cardinality observation key names for vector store operations.
Collection of event names used in vector store observations.
Configuration properties for vector store observations.
Collection of systems providing vector store functionality.
An
ObservationFilter to include the Vector Store search response content in the
observation.Handler for including the query response content in the observation as a span event.
Types of similarity metrics used in vector store operations.
Auto-configuration for Vertex AI Gemini Chat.
VertexAiEmbeddingConnectionDetails represents the details of a connection to the Vertex
AI embedding service.
Configuration properties for Vertex AI Embedding.
Utility class for constructing parameter objects for Vertex AI embedding requests.
Auto-configuration for Vertex AI Gemini Chat.
Vertex AI Gemini Chat Model implementation.
Options for the Vertex AI Gemini Chat API.
Configuration properties for Vertex AI Gemini Chat.
Configuration properties for Vertex AI Gemini Chat.
Constants for Vertex AI Gemini.
The VertexAiGeminiRuntimeHints class is responsible for registering runtime hints for
Vertex AI Gemini API classes.
Implementation of the Vertex AI Multimodal Embedding Model.
VertexAI Embedding Models: - Text
embeddings - Multimodal
embeddings
Class representing the options for Vertex AI Multimodal Embedding.
Configuration properties for Vertex AI Gemini Chat.
A class representing a Vertex AI Text Embedding Model.
VertexAI Embedding Models: - Text
embeddings - Multimodal
embeddings
Options for the Vertex AI Text Embedding service.
Configuration properties for Vertex AI Gemini Chat.
Represents the usage of a Vertex AI model.
Java Client for the watsonx.ai API.
WatsonX.ai autoconfiguration class.
ChatModel implementation for watsonx.ai.Helper class for creating watsonx.ai options.
Chat properties for Watsonx.AI Chat.
Java class for Watsonx.ai Chat Request object.
Java class for Watsonx.ai Chat Response object.
Java class for Watsonx.ai Chat Results object.
WatsonX.ai connection autoconfiguration properties.
EmbeddingModel implementation for Watsonx.ai.The configuration information for the embedding requests.
Watsonx.ai Embedding autoconfiguration properties.
Java class for Watsonx.ai Embedding Request object.
Java class for Watsonx.ai Embedding Response object.
Java class for Watsonx.ai Embedding Results object.
The WatsonxAiRuntimeHints class is responsible for registering runtime hints for
Watsonx AI API classes.
Converts
Filter.Expression into Weaviate metadata filter expression format.A VectorStore implementation backed by Weaviate vector database.
Configuration class for the WeaviateVectorStore.
https://weaviate.io/developers/weaviate/concepts/replication-architecture/consistency#tunable-consistency-strategies
Auto-configuration for Weaviate Vector Store.Configuration properties for Weaviate Vector Store.
Single class implementation of the ZhiPuAI Chat Completion API and
ZhiPuAI Embedding API.
Represents a chat completion response returned by model, based on the provided input.
Chat completion choice.
Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
Chat completion choice.
The reason the model stopped generating tokens.
Message comprising the conversation.
The function definition.
An array of content parts with a defined type.
The image content of the message.
The role of the author of this message.
The relevant tool call.
Creates a model response for the given chat conversation.
An object specifying the format that the model must output.
Helper factory that creates a tool_choice of type 'none', 'auto' or selected function by name.
ZhiPuAI Chat Completion Models:
ZhiPuAI Model.
Represents an embedding vector returned by embedding endpoint.
List of multiple embedding responses.
ZhiPuAI Embeddings Models:
Embeddings.
Creates an embedding vector representing the input text.
Represents a tool the model may call.
Function definition.
Create a tool of type 'function' and the given function definition.
Log probability information for the choice.
Message content tokens with log probability information.
The most likely tokens and their log probability, at this token position.
Usage statistics for the completion request.
Auto-configuration for ZhiPuAI.ZhiPuAiChatOptions represents the options for the ZhiPuAiChat model.
Configuration properties for ZhiPuAI chat model.
ZhiPuAI Embedding Model implementation.
The ZhiPuAiEmbeddingOptions class represents the options for ZhiPuAI embedding.
Configuration properties for ZhiPuAI embedding model.
ZhiPuAI Image API.
ZhiPuAI Image API model.
ZhiPuAiImageModel is a class that implements the ImageModel interface.
ZhiPuAiImageOptions represents the options for image generation using ZhiPuAI image
model.
Configuration properties for ZhiPuAI chat model.
The ZhiPuAiRuntimeHints class is responsible for registering runtime hints for ZhiPu AI
API classes.
Helper class to support Streaming function calling.
Usage implementation for ZhiPuAI.Common value constants for ZhiPu api.
FunctionCallbackWrapper.Builder