Document Vector Database

RE: Document Vector Database

laurensw9497 — Tue, 20 May 2025 11:34:16 GMT

Hi Author,

We have been using this plugin for a while now using latest version whenever available.

However, this plugin keeps popping up in health check reports. Can you please sustainably keep this plugin in a healthy state such that it does not flaw the health check results? Thank you.

Issues

- HIGH RISK: Plug-ins using removed, private or deprecated Appian APIs

[embed:dc8ab71f-3b98-42d9-b0f6-e21e02a0f8e2:2d5d9a76-b13d-4de6-8653-ef4cc3c05dc0:type=text&text=Document%20Vector%20Database%20%28DocumentVectorDatabase%29%20references%20private%20and%20deprecated%20Appian%20APIs%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatMessage.%3Cinit%3E%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatMessage.%3Cinit%3E%28java.lang.String%2C%20java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatMessage.getContent%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatMessage.getRole%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatMessage.setContent%28java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatMessage.setRole%28java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatResponse.getResponseText%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.ChatResponse.getUsageMap%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAIException.%3Cinit%3E%28java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAIException.getErrorCode%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAIException.getErrorMessage%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAIException.getMessage%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAIException.getStatusCode%28%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.%3Cinit%3E%28java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createCompletion%28com.appian.connectedsystems.templateframework.sdk.ExecutionContext%2C%20java.lang.String%2C%20java.util.List%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createCompletion%28com.appian.connectedsystems.templateframework.sdk.ExecutionContext%2C%20java.lang.String%2C%20java.util.List%2C%20java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createCompletion%28java.lang.String%2C%20java.util.List%2C%20java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createCompletionWithUsage%28com.appian.connectedsystems.templateframework.sdk.ExecutionContext%2C%20java.lang.String%2C%20java.util.List%2C%20java.lang.String%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createEmbeddings%28com.appian.connectedsystems.templateframework.sdk.ExecutionContext%2C%20java.lang.String%2C%20java.util.List%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createEmbeddings%28java.lang.String%2C%20java.util.List%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createEmbeddingsAsListOfStringWithBackOff%28com.appian.connectedsystems.templateframework.sdk.ExecutionContext%2C%20java.lang.String%2C%20java.util.List%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createEmbeddingsAsListOfStringWithBackOff%28java.lang.String%2C%20java.util.List%29%0D%0A%5Bprivate%5D%20com.appiancorp.openai.utils.OpenAiService.createEmbeddingsWithBackOff%28com.appian.connectedsystems.templateframework.sdk.ExecutionContext%2C%20java.lang.String%2C%20java.util.List%29%0D%0A%5Bdeprecated%5D%20com.appiancorp.suiteapi.common.ServiceLocator.getContentService%28com.appiancorp.services.ServiceContext%29%0D%0A%5Bdeprecated%5D%20com.appiancorp.suiteapi.common.ServiceLocator.getProcessDesignService%28com.appiancorp.services.ServiceContext%29%0D%0A%5Bdeprecated%5D%20com.appiancorp.suiteapi.common.ServiceLocator.getUserProfileService%28com.appiancorp.services.ServiceContext%29]

- MEDIUM RISK: # of objects with no admin group

- MEDIUM RISK: Knowledge Centers missing explicit reader and author groups

[embed:dc8ab71f-3b98-42d9-b0f6-e21e02a0f8e2:81ff54e8-552c-4742-b582-e1b803619553:type=text&text=KC_H2_DATABASE_DOCUMENT_COMMUNITY_KNOWLEDGE_CENTER%0AKnowledge%20Center%20ID%3A%20%28_a-0000ec32-c60a-8000-9bfe-011c48011c48_631283%29]

RE: Document Vector Database

Appian AppMarket — Tue, 15 Apr 2025 22:00:01 GMT

v3.2.6 Release Notes

Resolved issues related to incorrect embedding dimensions to ensure consistent vector representations.
Improved error handling for Azure requests with clearer messages.

RE: Document Vector Database

Appian AppMarket — Fri, 04 Apr 2025 22:00:01 GMT

v3.2.5 Release Notes

Security Patch Updated.

RE: Document Vector Database

Appian AppMarket — Tue, 28 Jan 2025 23:00:01 GMT

v3.2.4 Release Notes

Security Patch Updated.

RE: Document Vector Database

Amit Lathkar — Mon, 09 Dec 2024 17:58:51 GMT

When will this be supported on HA environments?

RE: Document Vector Database

Omkar — Tue, 06 Aug 2024 18:08:13 GMT

What will be the Database Name (Table values)? which will be used in the creation of the Database file in Appian while creating a connected system.

RE: Document Vector Database

Appian AppMarket — Thu, 01 Aug 2024 22:00:00 GMT

v3.2.3 Release Notes

Security Patch Updated.
Implemented Retry mechanism when the database is locked in HA environments.
Included token usage information in the client APIs and servlets.
Added the user information to the OpenAI and Azure OpenAI request for monitoring purpose.

IMPORTANT NOTE: If you are using this plugin in production, open a support case and ask to increase Heap Max for app server by 1GB. This will increase query performance and allow the plugin to handle a larger number of concurrent users.

RE: Document Vector Database

Appian AppMarket — Thu, 20 Jun 2024 22:00:00 GMT

v3.2.2 Release Notes

Added 128 k tokens option for Max Tokens input for Azure authentication in the Connected System configuration.
Minor Bug fixes

RE: Document Vector Database

Appian AppMarket — Wed, 12 Jun 2024 22:00:00 GMT

v3.2.1 Release Notes

Minor Bug Fixes.
Security patch updated.

RE: Document Vector Database

Appian AppMarket — Wed, 29 May 2024 22:00:01 GMT

v3.2.0 Release Notes

Introduced a new input in the connected system configuration to enable/disable Response streaming in the AI Knowledge Assistant component.
Added new Client APIs for uploading documents and performing chat completions. If the Disable Streaming Response is true, the AI Knowledge Assistant component will use the Client APIs for uploading documents and chat completions.
Security patch updated.

RE: Document Vector Database

Appian AppMarket — Wed, 24 Apr 2024 22:00:00 GMT

v3.1.2 Release Notes

Security patch updated.

RE: Document Vector Database

Appian AppMarket — Wed, 06 Mar 2024 23:00:00 GMT

v3.1.1 Release Notes

Bug fixes.
Security patch updated.

RE: Document Vector Database

Appian AppMarket — Tue, 20 Feb 2024 23:00:00 GMT

v3.1.0 Release Notes

Introduced a new integration - Grouping Integration enabling the grouping of text entries into specified categories.
Enhanced usability by restricting editing of the embedding model and Database constant name in the Connected System configuration only during the initial creation phase of the Connected System.

RE: Document Vector Database

Appian AppMarket — Tue, 06 Feb 2024 23:00:00 GMT

v3.0.1 Release Notes

Bug fixes
Made all the fields in Connected System as import customizable.

RE: Document Vector Database

Appian AppMarket — Mon, 22 Jan 2024 23:00:00 GMT

v3.0.0 Release Notes

Scalability Enhancements
We have significantly enhanced the vector database’s scalability to allow multiple users to interact with the chatbot concurrently. Please note that query speeds may vary depending on the length of the documents, the amount of documents queried, the number of concurrent users, and hardware configurations.
Query Performance
There has been a substantial increase in query performance. Documents that are queried are now temporarily cached in-memory, resulting in a slight latency during the initial query but followed by nearly instantaneous responses for subsequent questions. This update markedly improves the speed and efficiency of our query processing.