AI Lab

AI Lab (Test Framework) feature enables users to upload test cases and view test results directly on the platform.

Limitations for the Knowledge Management (KM) System:

  1. CSV File Validation: Imported .CSV files must undergo validation to ensure they meet the specified header requirements and data integrity before being accepted into the system.

  2. Single Knowledge Base: The system does not support the use of assistants with more than one Knowledge Base at a time, limiting users to managing knowledge within a single base for streamlined operations.

In order to upload a test case file, you need to have these columns as follow:

Input Column (* Mandatory)

  • no.*: Test case number (Format: case-[case]-[step])

  • question*: The test case prepared to assess Generative AI.

  • expected chunk id: The knowledge chunk expected to be used for answering the question.

  • expected answer: The answer anticipated from Generative AI.

The action of testing AI Lab consists of 3 options, as follows:

  1. Search KM Answer: Tests the selected chunk to generate an answer and automatically verifies document match between the expected and actual chunk.

  2. Generate Answer with Actual KM: Tests the entire process of answer generation by the Generative AI.

  3. Generate Answer with Expected KM: Tests only generating answer with using expected chunk from input file.

After finish executing, the test history will appear. User can click download as a zip file, consists of:

  1. Summary: Show the overall summary of test case.

  2. Test-cases: Show the result of each test case.

Warning:

The result will be displayed only once. Leaving the page will reset the test history and the test result.

Last updated