Help Center/ PanguLargeModels/ User Guide/ Developing an Agent/ Agent Setup and Configuration/ Improving Skills for Agents/ Configure a Knowledge Base
Updated on 2025-07-28 GMT+08:00
View PDF
Share

Configure a Knowledge Base

A knowledge base is a core component of the agent development platform. It is used to store, manage, and retrieve domain knowledge. The knowledge base provides precise information support for agents through structured storage, intelligent retrieval, and dynamic update mechanisms. The knowledge base supports the upload of multiple formats, such as DOC, PDF, PPTX, XLSX, and CSV. Through multi-source knowledge convergence and vectorization, the knowledge base can understand and reason complex semantics, providing reliable knowledge support for agent decision-making, Q&A, and task execution. Developers can flexibly configure knowledge sources, update policies, and retrieval modes to ensure that agents can quickly invoke accurate information in different scenarios to complete intelligent services.

Adding a Knowledge Base

Knowledge bases can be added for agents. When sending a message, the agent can reference the content in the knowledge base to answer users' questions. Currently, only one knowledge base can be associated.

If you need to add a knowledge base, ensure that the knowledge base has been created. For details about how to create a knowledge base, see Knowledge Base Development and Configuration.

To add a knowledge base, perform the following steps:

  1. In the Knowledge area, click .
  2. In the Add knowledge dialog box, click to add a knowledge base, and then click OK.
    Figure 1 Adding a knowledge base
  3. In the skill > Knowledge area, view the added knowledge base.
    Figure 2 Viewing the knowledge base

Knowledge Base Hit Test

The platform supports the hit test on the created knowledge base to evaluate the effectiveness and accuracy of the knowledge base.

The knowledge base hit test procedure is as follows:

  1. On the Knowledge tab page of the Workbench page, click the required knowledge base, and click Hit Test in the upper right corner.
  2. Enter a question in the text box and click Hit Test. The lower part of the page displays multiple matched contents according to different search modes and sorts the content in descending order by matching score.

    You can evaluate whether the current knowledge base meets the requirements based on the score and the amount of matched information.

Knowledge Base Recall Strategy

  1. In the Knowledge area, click to configure advanced settings for the knowledge base, including Relevance threshold, Topk recall quantity, and FAQ Straight out threshold.
    • Relevance threshold: Search results that exceed the relevance threshold will be submitted to the large model for summary. The other search results will be filtered out. You can adjust the threshold based on the relevance score in the hit test for the knowledge base.
    • Topk recall quantity: indicates the number of top relevant results in the top K search results based on the relevance threshold. For example, if the number of top K recalls is 5, the top 5 relevant results will be recalled and submitted to the large model for summary.
    • FAQ Straight out threshold: FAQs in the knowledge base with scores higher than the threshold will be recalled. In this case, documents in the knowledge base are not searched. If no FAQ meets the threshold requirements, the system continues to search for documents in the knowledge base. You can adjust the threshold by referring to the FAQ hit test result in the knowledge base. The value ranges from 0 to 1.
    Figure 3 Advanced settings for knowledge bases