ai.z.openapi.api.knowledge.document

Interface DocumentApi

public interface DocumentApi

Document Management API for intelligent knowledge base content Provides comprehensive document operations within knowledge bases for RAG (Retrieval-Augmented Generation) Supports document upload, automatic processing, vectorization, modification, deletion, and retrieval Enables efficient knowledge management for AI systems with advanced indexing and search capabilities Features automatic content extraction, chunking, embedding generation, and semantic organization

Method Summary

Modifier and Type	Method and Description
io.reactivex.Single<DocumentObject>	createDocument(okhttp3.MultipartBody document) Create and upload a new document to knowledge base with automatic processing Uploads document content for intelligent processing, content extraction, and vectorization Supports multiple file formats (PDF, DOC, TXT, MD) with automatic format detection Features automatic text chunking, embedding generation, and semantic indexing for optimal retrieval
io.reactivex.Single<retrofit2.Response<Void>>	deleteDocument(String documentId) Delete a document from knowledge base with complete cleanup Permanently removes the document, its indexed content, generated embeddings, and all associated metadata Ensures complete removal from vector database and search indices for data consistency Irreversible operation that affects knowledge base search and retrieval capabilities
io.reactivex.Single<retrofit2.Response<Void>>	modifyDocument(String documentId, DocumentEditParams documentEditParams) Modify an existing document with intelligent reprocessing Updates document metadata, content, or processing settings with automatic re-indexing Supports content updates, metadata changes, and processing parameter adjustments Triggers automatic re-vectorization and re-indexing when content is modified
io.reactivex.Single<DocumentPage>	queryDocumentList(String knowledgeId, String purpose, Integer page, Integer limit, String order) Query and list documents with advanced filtering and pagination Retrieves documents from knowledge base with comprehensive filter options and sorting Supports filtering by knowledge base, purpose, processing status, and content type Provides efficient pagination for large document collections with optimized performance
io.reactivex.Single<DocumentData>	retrieveDocument(String documentId) Retrieve comprehensive information about a specific document Gets detailed document data including content, processing status, embedding information, and usage statistics Provides insights into document processing results, chunk distribution, and retrieval performance Essential for monitoring document quality and troubleshooting knowledge base issues

Method Detail

createDocument

@POST(value="files")
io.reactivex.Single<DocumentObject> createDocument(@Body
                                                                        okhttp3.MultipartBody document)

Create and upload a new document to knowledge base with automatic processing Uploads document content for intelligent processing, content extraction, and vectorization Supports multiple file formats (PDF, DOC, TXT, MD) with automatic format detection Features automatic text chunking, embedding generation, and semantic indexing for optimal retrieval

Parameters:

document - Multipart document data including file content, metadata, and processing preferences

Returns:

Document object with unique ID, processing status, extraction results, and indexing information

modifyDocument

@PUT(value="document/{document_id}")
io.reactivex.Single<retrofit2.Response<Void>> modifyDocument(@Path(value="document_id")
                                                                                                  String documentId,
                                                                                                  @Body
                                                                                                  DocumentEditParams documentEditParams)

Modify an existing document with intelligent reprocessing Updates document metadata, content, or processing settings with automatic re-indexing Supports content updates, metadata changes, and processing parameter adjustments Triggers automatic re-vectorization and re-indexing when content is modified

Parameters:

documentId - Unique identifier of the document to modify

documentEditParams - Updated document parameters including content, metadata, and processing settings

Returns:

HTTP response indicating modification success, processing status, and any validation errors

deleteDocument

@DELETE(value="document/{document_id}")
io.reactivex.Single<retrofit2.Response<Void>> deleteDocument(@Path(value="document_id")
                                                                                                     String documentId)

Delete a document from knowledge base with complete cleanup Permanently removes the document, its indexed content, generated embeddings, and all associated metadata Ensures complete removal from vector database and search indices for data consistency Irreversible operation that affects knowledge base search and retrieval capabilities

Parameters:

documentId - Unique identifier of the document to delete

Returns:

HTTP response indicating deletion success, cleanup status, and any dependency warnings

queryDocumentList

@GET(value="files")
io.reactivex.Single<DocumentPage> queryDocumentList(@Query(value="knowledge_id")
                                                                        String knowledgeId,
                                                                        @Query(value="purpose")
                                                                        String purpose,
                                                                        @Query(value="page")
                                                                        Integer page,
                                                                        @Query(value="limit")
                                                                        Integer limit,
                                                                        @Query(value="order")
                                                                        String order)

Query and list documents with advanced filtering and pagination Retrieves documents from knowledge base with comprehensive filter options and sorting Supports filtering by knowledge base, purpose, processing status, and content type Provides efficient pagination for large document collections with optimized performance

Parameters:

knowledgeId - Filter documents by specific knowledge base ID (optional)

purpose - Filter documents by their intended purpose or category (optional)

page - Page number for pagination (starts from 1)

limit - Maximum number of documents to return per page (recommended: 10-50)

order - Sort order for the document list (e.g., 'created_at', 'updated_at', 'name')

Returns:

Paginated list of documents with metadata, processing status, and summary information

retrieveDocument

@GET(value="document/{document_id}")
io.reactivex.Single<DocumentData> retrieveDocument(@Path(value="document_id")
                                                                                        String documentId)

Retrieve comprehensive information about a specific document Gets detailed document data including content, processing status, embedding information, and usage statistics Provides insights into document processing results, chunk distribution, and retrieval performance Essential for monitoring document quality and troubleshooting knowledge base issues

Parameters:

documentId - Unique identifier of the document to retrieve

Returns:

Complete document data with content, metadata, processing details, embedding statistics, and access history