API standards and multilingual preset SDKs
The OpenAPI of this product (DianJin/2024-06-28) uses the ROA signature style. We have encapsulated SDKs for common programming languages for developers. Developers can download the SDK to directly call this product's OpenAPI without worrying about technical details. If the existing SDK does not meet your needs, you can use the signature mechanism for self-signing integration. Since the details of self-signing are very complex, it may take around 5 business days. Therefore, we recommend joining our DingTalk service group (147535001692) and conducting signature integration under expert guidance.
Before using the API, you need to prepare your identity account and access key (AccessKey) to effectively access the API through client tools (such as SDK and CLI). For details, see Obtain an AccessKey.
Custom signature scenarios
If your business scenario has special requirements and you need to integrate the API through self-signing, we recommend consulting our technical support team first (DingTalk service group: 147535001692) to obtain professional guidance and ensure efficient integration.
Account and security preparation
Alibaba Cloud accounts have full administrative permissions over all resources. Once an AccessKey is compromised, all associated resources will be at risk of unauthorized access. To ensure security, it is recommended to create a RAM user with only API access permissions and configure its AccessKey, while configuring RAM policies based on the principle of least privilege (PoLP). Use the Alibaba Cloud account only in specific scenarios where Alibaba Cloud account permissions are explicitly required.
Platform capabilities - document library
API | Title | Description |
|---|---|---|
| UpdateDocumentChunk | Update document block content | Update the text content of a document chunk in a document. |
| GetAppConfig | Obtain Configuration Information | Retrieve app configuration. |
| CreateLibrary | Create a document library | Creates a document library. A document library isolates document and index data. If your use case requires frequent natural language search by category, create multiple libraries to isolate different data types. You can customize vector and text indexes by format. |
| GetLibraryList | Retrieve document library list | Retrieve the document library list. The list includes document names, descriptions, and unique identifiers. |
| GetLibrary | Obtain document library details | Retrieves the detailed configuration of a document library, including its name, description, and index settings. |
| UploadDocument | File | Upload a document to a document library. The system parses the document, splits it into chunks, and builds an index. |
| GetDocumentUrl | Obtain the document download link | Retrieve a download URL for a document. The URL expires after 1 hour. |
| PreviewDocument | Preview document | Preview documents. Retrieve document download links, types, and titles. Use this operation to preview documents. |
| GetFilterDocumentList | Query document list by metadata filters | This operation retrieves a list of documents. You can filter documents by metadata or use paging. |
| GetDocumentList | Retrieve Document List | Retrieves a list of documents from a document library. This operation supports paged queries and filtering by document status. |
| DeleteDocument | Delete Document | Deletes a document. After deletion, you cannot view the original document or recall it. |
| UpdateDocument | Update Document | Updates the title, metadata, and other information of a document. |
| CreatePredefinedDocument | Create a predefined document | Creates document chunks based on your business scenarios. |
| GetDocumentChunkList | Retrieve document chunk list | Retrieve a list of document chunks. You can filter them by query conditions. |
| RecallDocument | document recall | You can retrieve document chunks from a document library using text. You can specify the number of chunks to retrieve, filter them by metadata conditions, and choose whether to complete the document chunks. |
| GetParseResult | Obtain document parsing result | Retrieve document parsing results. You can query the document's parsing status and obtain the parsing results. |
| ReIndex | Reindex | Reindexing reprocesses the specified document by parsing it, splitting it into chunks, and building a new index. |
| UpdateLibrary | Update Document Library | Updates a document library. You can update the library name, description, and index configuration. |
| DeleteLibrary | Delete document library | Delete a document library. ⚠️ This operation deletes the library and all its associated documents. |
| RunLibraryChatGeneration | Generate Document Library Session | Generates a chat response from a document library. You can ask questions in natural language, and the system retrieves relevant information to provide a summarized answer. |
| GetHistoryListByBizType | Retrieve conversation history by business type | Retrieve conversation history records by business type. |
| InvokePlugin | Invoke Plugin | Call a plugin and retrieve its response. |
Platform capabilities - applications
API | Title | Description |
|---|---|---|
| EndToEndRealTimeDialog | Real-time speech dialogue | This API uses the WebSocket protocol to perform real-time conversational transcription, intent recognition, and speech synthesis. It supports various audio formats for both input and output to ensure real-time performance and high compatibility. |
| RunDialogAnalysis | Generate Conversation Analysis Result | Retrieves session analysis results through a streaming API. |
| RunAgent | Run agent | Run an agent. This API supports both streaming and non-streaming responses. |
| CreateDialog | Create an outbound call session | Creates an outbound call session. |
| RealTimeDialog | Real-time Session | Starts a real-time session. After you create a session by calling the CreateDialog API, use this API to conduct the real-time interaction. |
| RealtimeDialogAssist | Real-Time Session Assistance | Provides real-time dialog assistance after a session is created using CreateDialog. Note: This operation returns multiple intents, tags, and SOP flows. Unlike real-time sessions, it does not support streaming responses. |
| GetDialogDetail | Retrieve session details | Retrieve session details. |
| GetDialogLog | Retrieve conversation logs | Retrieves records of real-time conversations and the results of intent analysis. |
| GetDialogAnalysisResult | Retrieve Conversation Analysis Result | Retrieve session analysis results. You can retrieve results in batches by specifying a list of session IDs or a time range. |
| CreateDialogAnalysisTask | Create Conversation Analysis Job | Creates a session analysis task. After the task is created, use the session ID with GetDialogAnalysisResult to retrieve the results. |
| RebuildTask | Rebuild Job | Rebuilds an existing task. You cannot rebuild tasks that are queued or currently executing. |
| EvictTask | Cancel Job | Terminate the job. |
| GetTaskStatus | Obtain Job Status | Gets the status of a task. |
| CreateDocsSummaryTask | Create a multi-document summarization job | Creates a multi-document summary task. |
| CreateAnnualDocSummaryTask | Create a document summarization job by year | Create a task to summarize documents by year. |
| CreatePdfTranslateTask | Create a PDF Document Translation Job | Create a PDF document translation task. Submit the task to start asynchronous translation. |
| CreateFinReportSummaryTask | Create a Financial Report Summary Job | Creates a financial report summary. |
| GetSummaryTaskResult | Retrieve Financial Report Summary Job Result | Retrieves the result of a financial report summary task. |
| GetTaskResult | Retrieve Result | Retrieves the result of an asynchronous task. |
| CreateQualityCheckTask | Create a quality inspection job | Creates a quality check task. |
| GetQualityCheckTaskResult | Obtain quality inspection Result | Retrieve quality check results. |
| RecognizeIntention | Intent recognition | Detects intents. This operation supports global and hierarchical intent detection, attitude detection, and enterprise detection. |
| GenDocQaResult | Parse Q&A pairs from a document | Parses question and answer (Q&A) pairs from a document. You can use the UpdateQaLibrary API to update the Q&A pairs. |
| UpdateQaLibrary | Update Q&A Pair Library | Updates a Q&A library. After the update, use the GenDocQaResult API to parse the Q&A pairs. |
| SubmitChatQuestion | submit question List | Submit a list of questions and retrieve results by calling the `GetChatQuestionResp` API. |
| GetChatQuestionResp | Retrieve Q&A results | Retrieves the Q&A results generated by the SubmitChatQuestion API. |
| RunChatResultGeneration | Generate conversation result | Generates chat responses. You can select a model for the conversation and choose streaming or non-streaming output. |
Others
API | Title | Description |
|---|---|---|
| DashscopeAsyncTaskFinishEvent | Dashscope asynchronous job completion callback event | A callback event that indicates the completion of a Dashscope asynchronous task. |