Information Schema
The information schema is used to create structured data from unstructured data like PDF files, text files etc. This structured information provides insights into important information from large files with the help of LLM models, which can be used for decision-making and querying the bot.
The steps to create and use information schema are as follows -
Create a knowledge base using unstructured data files such as a pdf/text file.
You can see the uploaded files in the Knowledge Source tab. Click on any file to view its content.
In order to create an information schema for your knowledge base, go to the Information Schema tab.
Click on the Add button to create a new schema.
Now, you can provide the column details you want to extract from the unstructured data. Here, you can provide the Column Name, Data Type, and provide Prompt for retrieving data.
You can add multiple columns and click on the Update button to save it.
Click on the Run Schema button on top to run the information schema that you have created.
This will redirect you to the Data Preview tab, where you will be able to view the result. Using the information schema result, you will be able to query data using both knowledge base data as well as the information schema created.
In the App's Configure your Bot section, you can manage the knowledge base and schema required for the particular app by selecting it and saving it.
While querying your bot, you can use both your knowledge base and information schema to get the desired result.
Last updated
