This topic describes how to create and manage knowledge spaces, create knowledge bases, upload documents, and test retrieval in the console.
Availability
The enterprise knowledge space engine is built on the integrated architecture of PolarDB. It includes an orchestration engine, an intelligent search engine PolarSearch (based on inverted indexes and vector database) , and PolarDB for PostgreSQL for metadata management. The supported regions and zones are as follows:
Region | Availability zone |
China (Hangzhou) | Zone K, Zone J |
China (Shanghai) | Zone E, Zone F, Zone L, Zone N |
China (Shenzhen) | Zone C, Zone D, Zone F |
China (Beijing) | Zone F, Zone L, Zone I, Zone K |
China (Zhangjiakou) | Zone B |
China (Ulanqab) | Zone B, Zone C |
China (Hong Kong) | Zone B, Zone D |
Singapore | Zone A, Zone B |
Japan (Tokyo) | Zone A, Zone C |
South Korea (Seoul) | Zone A, Zone B |
Germany (Frankfurt) | Zone A |
US (Silicon Valley) | Zone B |
Philippines (Manila) | Zone A |
Create a knowledge space
You can create a knowledge space in the PolarDB Agent Express console. Creating a knowledge space automatically creates and associates a PolarDB cluster. You can view the associated PolarDB cluster on the knowledge space details page.
Do not modify or delete the doc_search account or the polar_rag_meta database that the enterprise knowledge space automatically creates in the target PolarDB cluster.
-
Log on to the PolarDB console.
-
In the left-side navigation pane, choose .
-
Click Create Knowledge Space.
-
In the dialog box, configure the following parameters.
Parameter
Required
Description
Knowledge Space Name
Yes
Enter a name for the knowledge space. Maximum length: 128 characters.
Knowledge Space Notes
No
Enter a description for the knowledge space. Maximum length: 512 characters.
Vector Model
Yes
Select a vector model. The default is
text-embedding-v4. This setting cannot be changed after creation.Vector Dimensions
Yes
Set the vector dimension, which must match the selected vector model. The default value is
1024.Sorting Model
No
Select a reranker model to reorder the search results. The default is
qwen3-rerank. You can also selectgte-rerank-v2.Sharding Strategy
Yes
Select a document chunking strategy. By default, Intelligent Sharding is used.
Chunk Size (tokens)
No
Set the maximum number of tokens for a single chunk. The default value is
512.OSS Bucket
Yes
Enter the name of the OSS bucket that stores the source documents.
OSS AccessKey
Yes
The AccessKey ID for your OSS bucket.
OSS Secret Key
Yes
The AccessKey Secret for your OSS bucket.
VPC Network
Yes
Select a VPC.
Zone and vSwitch
Yes
Select a zone and a vSwitch. The zone must be one of the supported zones listed in Availability.
-
Click OK.
Configure network
-
Create a Public NAT Gateway: Go to the NAT Gateway - Public NAT Gateway purchase page to create a gateway. During creation, select the same VPC and vSwitch as your enterprise knowledge space.
-
Configure an SNAT entry: Go to the Public NAT Gateway page. In the Operation column for the target gateway, click Configure SNAT, and then click Create SNAT Entry. Configure the following parameters:
-
SNAT entry scope: VPC.
-
Select Elastic IP Address: Select an EIP from the drop-down list to provide public access.
-
Enabling public access incurs fees for the Public NAT Gateway and public network traffic. For more information about billing, see NAT Gateway billing.
Manage knowledge spaces
After you create a knowledge space, you can view and manage existing knowledge spaces on the Enterprise Knowledge Space tab.
Edit a knowledge space
On the knowledge space card, click Edit to modify the name and description of the knowledge space.
Delete a knowledge space
Deleting a knowledge space also deletes all associated resources, including indexes, pipelines, models, and connectors. This action is irreversible. Proceed with caution.
On the knowledge space card, click Delete, and then click Delete in the confirmation dialog box.
View knowledge space details
On the knowledge space card, click View Details to go to the Storage Management page. This page shows the basic information of the knowledge space, such as the vector model, dimensions, reranker model, chunking strategy, and OSS bucket, as well as the list of knowledge bases in the space.
Create and manage knowledge bases
A knowledge base is a logical grouping unit within a knowledge space for organizing and managing documents. You can create multiple knowledge bases in a single knowledge space.
Create a knowledge base
-
On the knowledge space details page, click Create Knowledge Base.
-
In the dialog box, configure the following parameters.
Parameter
Required
Description
Knowledge Base Name
Yes
Enter a name for the knowledge base. Maximum length: 128 characters.
Remarks
No
Enter a description for the knowledge base. Maximum length: 512 characters.
Search Mode
Yes
Select a retrieval mode. Valid values:
-
Balanced Mode (default, BM25 50% + KNN 50%)
-
Precise Mode (BM25 70% + KNN 30%)
-
Semantic Mode (BM25 30% + KNN 70%)
-
KNN (pure vector search)
-
RRF Fusion (rank fusion)
-
-
Click Create.
Edit a knowledge base
On the knowledge base card, click Edit to modify the name, retrieval mode, and description of the knowledge base.
Delete a knowledge base
On the knowledge base card, click Delete, and then click Delete in the confirmation dialog box.
Upload and manage documents
You can upload documents from the console or upload files to the OSS path of the knowledge base. After upload, the system automatically parses, chunks, and indexes the documents.
Upload from the console
-
On the knowledge space details page, click the target knowledge base to go to the knowledge base details page.
-
On the File Overview tab, click Upload File.
-
In the upload dialog box, select a file and click OK. The maximum file size is 5 GB.
Upload from OSS
You can also upload files directly to the OSS path of the knowledge base. The path format is:
oss://<Bucket name>/<Knowledge space ID>/<Knowledge base ID>/Example: oss://my-rag-bucket/space_001/kb_001/report.pdf
Synchronize documents
Files uploaded through OSS are automatically synchronized to the knowledge base on a regular basis. To synchronize immediately, on the knowledge base details page, click the File Overview tab and then click Trigger Sync.
Document processing statuses
Uploaded documents go through the following statuses during processing:
|
Status |
Description |
|
Pending |
Submitted. Waiting for processing resources to be allocated. |
|
Chunking |
The document is being chunked. |
|
Vectorizing |
Vector indexes are being generated. |
|
Completed |
Processing is complete. The document is available for retrieval. |
|
Failed |
Processing failed. Check the file format or contact technical support. |
View document chunks
In the row of the target document, click View Shards to view the chunk details of the document.
Delete a document
Deleting a document also deletes the document from your OSS bucket (<Bucket name>/<Knowledge space ID>/<Knowledge base ID>/). This action is irreversible. Proceed with caution.
In the row of the target document, click Delete, and then click Delete in the confirmation dialog box.
Test retrieval
After documents are processed, you can test retrieval on the knowledge base details page.
-
On the knowledge base details page, click the Retrieval Test tab.
-
Configure the retrieval parameters.
Parameter
Description
Query Statement
Enter the text to search for.
Search Method
Select AISearch or Keyword Search.
Return Count (Top-K)
Set the number of most relevant results to return.
Similarity Threshold
Set the minimum similarity score threshold. Results with scores below this threshold are excluded.
Reranking
Specifies whether to enable the reranker model to reorder the results. Valid values: Enabled - Use Sorting Model and Close.
-
Click Start Retrieval. In the Search Results section, view the matched document chunks, including the source file, similarity score, and chunk content.