Skip to main content
AI Chatbots

Knowledge test

In the Knowledge base training view, under Other, you can check the answer given by the text generation model to a specific question.

  1. Click on Knowledge test.
  2. In the text field, type the question you want the text generation model to answer.
  3. To access additional options, click the additional option icon.

knowledge test options icon

  1. In the Prompt field, specify a prompt if necessary. To select a prompt previously defined in the Prompts view, click in the field and choose the necessary prompt from the offered values.
  2. Fill the Tags field, if documents in the knowledge base are marked with tags and functions include text generation from separate document sets.
  3. In the Threshold field you can specify semantic similarity index between 0.0 and 2.0. The higher the value, the less similar the fragments are. The default value is 0.9. Fragments with a similarity index higher than the threshold are rejected.
  4. Click Test.
  5. The question the system has created from the conversation history and the question asked, appears next to the title Expanded question.
  6. The generated text appears next to the Response.
  7. The Context section shows the data with the highest similarity, which was used by the text generation model to create the response. Data segments are displayed sequentially with the corresponding metadata: segment number, names, file location, URL address (if found in the text), file name, tag information, etc. To open the corresponding file, click the notepad icon next to the segment.
  8. The History section shows conversation history.
  9. The Request section shows all information that was sent to the text generation model to generate the answer.

The Knowledge Test interface showing the question, prompt, response, and context fields.

Request​

In the Conversations view, by opening one of the conversations handled by the virtual assistant and clicking on the user input, you can view the request that was sent to the automatic text generation model.

request

The request contains the prompt, selected segments, and the conversation history. By clicking Send, the request is sent to the large language model, and the generated response is displayed in the Response field. This window can be used when working with automatic text generation by modifying the request data and trying out other requests.

request_window

If, when modifying the request data, a notification appears stating that the request text must include the user’s question, make sure it is included in the following format:

user: here is the user’s question

assistant:

Read more