You can test how well your vectorized grounding documents can answer questions by submitting test queries to the vector index asset after it is created.

1. From the Prompt Lab in chat mode only: Click the Grounding with documents icon at the start of the page, and then click View vector index details.

2. From the vector index asset details page, click the Test tab.

3. Submit test queries to view the document passages that are returned from the connected vector index.

4. If a search returns bad answers, adjust query settings to improve responses.

   • To control the number of search results to include in the prompt as contextual information, click Adjust search settings, and then edit the Top K value.

   With a higher Top K number, more information is available for the foundation model to use in its response. However, the token count of the input also increases. By default, the top three search results are included.

   • If answers are missing or incomplete, review the chunk size and overlap settings to help ensure that the document is being indexed properly. Click Edit vector index, and then expand Advanced settings. Review the current embedding settings and make any necessary changes.

   Don't forget that you can adjust the foundation model parameters for prompting in Prompt Lab to improve answers. Although you must clear the chat text before you can edit the foundation model parameters, any documents that were uploaded continue to be associated with the chat. For more information, see Model parameters for prompting.

5. When a query that you enter to search the vector index returns good contextual information, you can click Add as sample question to save the query.

   Saved sample questions are displayed as quick start samples from chat mode in the Prompt Lab whenever this vector index asset is associated with a prompt.