All Classes and Interfaces
Class
Description
Abstract
OutputParser implementation that uses a pre-configured
DefaultConversionService to convert the LLM output into the desired type
format.Abstract
OutputParser implementation that uses a pre-configured
MessageConverter to convert the LLM output into the desired type format.AllOfGenerateResponseDetails
AllOfStreamResponseDetails
Lets the model know the content was generated as a response to the user.
Implementation of
AiClient backed by an OpenAiServiceAn implementation of
OutputParser that transforms the LLM output to a specific
object type using JSON schema.BestOfSequence
A PromptTemplate that lets you specify the role as a string should the current
implementations and their roles not suffice for your needs.
CompatGenerateRequest
Converts the Document text and metadata into a AI, prompt-friendly text representation.
Details
ErrorResponse
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.Writes the content of a list of
Documents into a file.Portable runtime model 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.Parse a textual, vector-store agnostic, filter expression language into
Filter.Expression.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 model should be formatted.
GenerateParameters
GenerateRequest
GenerateResponse
An implementation of
AiClient that interfaces with HuggingFace Inference
Endpoints for text generation.Info
Keyword extractor that uses model to extract 'excerpt_keywords' metadata field.
OutputParser implementation that uses a DefaultConversionService to
convert the LLM output into a List instance.OutputParser implementation that uses a pre-configured
MappingJackson2MessageConverter to convert the LLM output into a
java.util.Map<String, Object> instance.Converts
Filter.Expression into Milvus metadata filter expression format.Parameters for Milvus client connection.
Configuration for the Milvus vector store.
An enum to configure the distance function used in the Neo4j vector index.
Configuration for the Neo4j vector store.
A client implementation for interacting with Ollama Service.
Ollama generate a completion api response model
Implementation of
AiClient backed by an OpenAiService.Converts the (raw) LLM output into a structured responses of type.
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.
Common configuration builder for the
PagePdfDocumentReader and the
ParagraphPdfDocumentReader.Re-implement the PDFLayoutTextStripperByArea on top of the PDFLayoutTextStripper
instead the original PDFTextStripper.
Converts
Filter.Expression into PgVector metadata filter expression format.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.
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.
PostgresML EmbeddingClient
PrefillToken
Converts
Filter.Expression into test string format.Service that helps caching remote
Resources on the local file system.Similarity search request builder.
Adds simple serialization/deserialization to the data stored in the InMemoryVectorStore
StreamDetails
StreamResponse
Title extractor with adjacent sharing that uses model to extract 'section_summary',
'prev_section_summary', 'next_section_summary' metadata fields.
A message of the type 'system' passed as input.
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.
Token
https://www.sbert.net/index.html https://www.sbert.net/docs/pretrained_models.html
Configurations for the
HuggingFaceTokenizer used to convert sentences into
tokens.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.