How to create a knowledge base?

This guide details the steps involved in creating a knowledge base within your ZBrain account.

1. Begin by logging into your ZBrain account. Once logged in, click the ‘Create’ button to create a knowledge base.

2. Then, you will be directed to a screen where you can either upload a document from your device or import it from a data source.

3. After uploading or importing the data, you will be prompted to provide a name and description for the chosen file/data. Additionally, you will have the option to summarize the document. To enable summarization, activate the toggle bar for this option and proceed to select a suitable summarization model.

4. Complete all the required fields and click the ‘Next’ button to proceed to the data source configuration page.

5. You will be directed to the ‘Text Data Refinement’ step of the knowledge base creation process. Here, you can define parameters for how ZBrain processes and stores your uploaded text data for efficient retrieval and knowledge base creation. On this page, you can find the following:

Data processing options

ZBrain offers two data processing options:

• Automatic: This option is recommended for users unfamiliar with the process. ZBrain will automatically set chunk and preprocessing rules based on best practices.

• Custom: This option allows experienced users to define custom configurations for chunk rules, chunk length, and preprocessing rules.

Vector store selection

ZBrain allows you to select a vector store for storing and indexing your text data for efficient retrieval. Here are the available vector store options:

• Pinecone: This option leverages the scalability of Pinecone, a third-party vector indexing service, directly within ZBrain.

• Economical: This option utilizes ZBrain's built-in vector store with cost-effective vector engines and keyword indexes for efficient data handling.

File store selection

• ZBrain S3 storage: This option utilizes ZBrain's secure and scalable S3 storage for data management. It offers enhanced data management features and precise retrieval results without incurring additional token costs.

Retrieval settings

ZBrain offers various retrieval settings to define how users can search and retrieve information from a knowledge base. Here's an overview of the available settings:

• Search type: You can choose between three search types:

  • Vector search: This method uses vector representations of text data for efficient retrieval. ZBrain utilizes an inverted index structure to map terms to relevant text chunks.

  • Full-text search: This method indexes all terms within your documents, allowing users to search and retrieve documents based on keywords.

  • Hybrid search: This option combines vector search and full-text search. ZBrain performs both searches simultaneously and then re-ranks the results to prioritize the most relevant documents for the user's query. To utilize hybrid search, you'll need to configure a Rerank model API.

• Top K: This setting determines the number of most relevant results returned for a user's search query. You can specify the desired number of results (default is 50).

• Score threshold: This setting defines the minimum score a result needs to achieve to be included in the search results. You can specify a score between 0 and 1 (default is 0.2).

6. Once you have confirmed your selections, click the ‘Next’ button.

7. On the next screen, review the details of the knowledge base you provided earlier. If everything appears accurate, click the ‘Manage Knowledge Base’ button to complete the creation process.

8. Your newly created knowledge base is now accessible for use within your ZBrain applications. You can create additional knowledge bases by clicking on the ‘Add’ button or delete existing ones using the ‘Delete’ button.