Knowledge Base Management

How to Create Org Spaces and Knowledge Bases?

In the Knowledge module, users can create "Org Spaces" and "Knowledge Bases" to support multi-level knowledge management. Before starting to create, it is recommended to understand the following core concepts for more efficient use of related features.

• No spaces can be created in My Space, only Knowledge Bases can be created. There is a built-in default knowledge base.

• Different Spaces can be created under Org Spaces, and only under these created spaces can Knowledge Bases be created.

The table below compares the creation of spaces and knowledge bases between "My Space" and "Org Space":

How to Create a New Org Space?

After fully understanding the above concepts, you can start creating an Org Space to begin an efficient knowledge management journey.

💡 Tip: Creating an Org space requires the relevant space creation permission. Please ensure you have this permission before creating.

Steps to create an Org space:

• First, navigate to "Management -> Knowledge Management -> Org Space", click the “⚙️” next to the Org space;

• Click "Add New" on the popped-up Org space page;

• Enter the Org space's ID, name, icon, description, order, etc., and click "Save" to successfully create the Org space. (The example in the image is creating "Test Org Space New")

How to Create a New Knowledge Base?

💡 Tip: Creating a knowledge base in personal space does not require related permissions.

Creating a Knowledge Base in My Space

Steps to create a knowledge base in My Space:

• First, navigate to the My Space overview page, click "Add Knowledge Base";

• Fill in the knowledge base name and description, click "Save", and the knowledge base will be successfully created in the personal space. (The example in the image is creating "Test Knowledge Base")

Creating a Knowledge Base in Org Space

💡 Tip: Creating a knowledge base in an Org space requires relevant permissions. Please ensure you have creation permission before creating.

Steps to create a knowledge base in an Org Space:

• First, navigate to "Management -> Knowledge -> Org Space", enter the Org space where the new knowledge base will be created;

• Click "Add" on the right side of the knowledge base;

• In the popped-up create knowledge base page, enter the knowledge base's name, confidentiality level, description, etc., and click "Save" to create successfully.

  • Confidentiality level: The default levels are three types, including public and Highly confidential.

  • Storage quota: 0-1GB.

  • File size limit: Supports files within 100MB.

  • Supported file formats: Including ppt, .pptx, doc, docx, xls, .xlsx, .csv, .md, txt, .png, .jpeg, .jpg, .pdf, .mp3, .flac, .mp4, .xmind, .json, .xml, etc. (Please refer to the dropdown list options for specific formats).

💡 Tip:If you customize the upload file size and format, the system will prompt you if the uploaded file does not meet the restrictions.

How to Configure Knowledge Base Space Settings?

💡 Tip: Knowledge base space settings require Org space management permissions. Please ensure you have this permission before modifying knowledge base settings.

Knowledge base space settings can be accessed from multiple entry points:

• On the knowledge base overview page of the Org space, click “✏️” on the knowledge base card to open;

• After entering the knowledge base, click the ⚙️ button at the top left of the page to open;

• Navigate to "Management -> Knowledge Management -> Org Space", select the knowledge base to edit, click the right side “···”, and choose "Manage" to open.

General Settings

General settings of the knowledge base are the information filled in when creating the knowledge base, including knowledge base name, type, confidentiality level, description, storage quota, file size limit, and supported file formats.

File Settings

Indexing Method:

• Basic Analysis: Suitable for general text recognition, choose basic parsing when files do not contain tables or images.

• OCR Intelligent Parsing: Calls integrated models to process documents, suitable for documents containing many tables; OCR intelligent parsing allows choosing between intelligent model parsing mode or Azure AI Document Intelligence.

  • Intelligent Model Parsing Mode: Uses built-in system models for semantic recognition and structured extraction, suitable for documents with tables or complex layouts.

  • Azure AI Document Intelligence Mode:

    • Basic: Provides more accurate text extraction, suitable for complex documents. Extracts printed and handwritten text.

    • Layout: Has text recognition, table reconstruction, and image recognition capabilities. High-precision parsing to preserve document layout structure.

Chunk Setting:

• Default Segmentation: The system segments text according to the default method.

• Fine Segmentation Mode: Text is first segmented by a maximum of 1024 characters, then each segment is further subdivided by 200 characters, with each small segment having an independent index.

• Custom Mode: Users can customize the maximum number of characters per segment, for example, setting it to 500 means each 500 characters are segmented into one piece.

Retrieval Settings:

• File Preview: Controls whether files (documents, images, videos, audio) in the knowledge base support online preview.

• File Indexing: Sets whether various resources (documents, images, videos, audio) in the knowledge base are included in the global search index. If disabled, the corresponding resources cannot be retrieved by keywords.

File Summary Generation: Automatically generates content summaries for documents in the knowledge base to facilitate quick browsing of core information. If turned off, newly uploaded documents will no longer automatically generate summaries.

Metadata

Metadata is data used to describe data, such as file size, name, location, etc. In AI Central, metadata is used to enhance file management and knowledge base retrieval capabilities.

The Role of Metadata in AI Central

File-level Metadata:

• When uploading files, the system automatically saves basic metadata such as file size, name, storage location, etc.

• Users can customize metadata, such as tags, categories, uploader, etc., for more precise file management.

• When retrieving knowledge base files, filtering based on metadata can improve search hit rates.

Knowledge Base-level Metadata:

• The knowledge base itself can also be configured with metadata, such as theme, industry category, permission information, etc.

• Through knowledge base metadata, more advanced classification and retrieval can be achieved, improving knowledge management efficiency.

Automatic Inheritance and Filling Mechanism of Metadata

• In the SERVICEME knowledge base structure, if a folder is configured with a metadata template (i.e., specific Keys are defined), then newly uploaded or synchronized files in that folder will automatically inherit these metadata Keys.

• If the file has the "Summarization" feature enabled, the system will automatically fill in relevant field information based on file content and metadata during file processing and parsing, making the semantic features and business tags of the file more consistent, thereby improving the accuracy and contextual relevance of AI summarization and retrieval.

User Management

Owner: The knowledge base owner has all permissions for this knowledge base, including management, editing, and access permissions.

Editor: Knowledge base editors have the right to operate all file functions, such as uploading, deleting files, etc.

Visitor: Visitors can only view the knowledge base content and cannot make any modifications to the knowledge base content.

Knowledge Base Member Permission Configuration

Before understanding how to manage knowledge base member permissions through roles, it is necessary to understand three concepts: Role, User Authorization, Function Authorization.

• Role: Roles are created by administrators and can be created for different scenarios.

• User Authorization: After creating a role, users can be added to this role, which can also be understood as assigning a role to a user.

• Function Authorization: Function authorization of a role refers to what functions this role can have.

💡 Tip: From the above, it can be seen that: Function Authorization + Role Authorization = Granting a certain permission to a user.

⏳ example: Grant DemoUser the management permission of the Demo knowledge base.

• Click "Add" on the right side of the role list to create a new role named "Knowledge Base Management";

• After creating the knowledge base management role, click "Function Authorization" corresponding to the role, find "Space Management", under space management find and check "Demo" in knowledge bases, then click "Save";

• Next, add the test account to this role, click "User Authorization" after the corresponding role, find and check DemoUser according to the test account's organization, then click "Save";

• After completing the above operations, DemoUser will be successfully granted the management permission of the Demo knowledge base.

How to Delete Org Spaces and Knowledge Bases?

Delete Knowledge Base

To delete a knowledge base, simply navigate to the knowledge base overview page, find the corresponding knowledge base card, and click the “🗑️” at the bottom right of the card to delete the knowledge base. The deletion method is the same for both My Space and Org Space.

As shown below:

Delete Org Space

Deleting an Org space requires a user with space management permissions to navigate to "Settings -> Knowledge Management -> Org Space", click the “⚙️” next to the Org space, select the Org space to delete on the popped-up Org space page, click "Delete" at the top right, and confirm the deletion.

As shown below:

Comparison of File-Related Operations Between My Space and Enterprise Space