Retrieval testing and knowledge base settings

Retrieval testing is used to identify similar chunks in response to a query, determining which data chunks will be processed by the language model. Users can submit queries related to the data stored in the knowledge base. The system then retrieves relevant chunks of information, ranking them based on how well they match the user's query. The most relevant chunk, with the highest matching score, is displayed first, followed by chunks with lower scores.

By analyzing the returned chunks, users can assess how well the LLM interprets and retrieves relevant information for various queries.

1. To do retrieval testing, click the ‘Retrieval Testing’ tab and type a query related to your data. Then hit the ‘Test’ button.

2. You will be provided with a retrieval result, which is an array of chunks from the knowledge base.

Knowledge base settings

Using this, users can modify the properties and working methods of the knowledge base.

1. Select the ‘Knowledge Base Settings’ tab to edit the previously set properties and parameters of the knowledge base. Here, you can edit the knowledge base name, its description, vector store, retrieval settings and more.