​
What is a Table + Search node?

​
Node in Stack AI

Table + Search helps you ask questions about a specific table so that an LLM can use that information.

​
How to use it?

​
How to connect with other nodes

To utilize the Table + Search node, you must establish connections to both its input and output edges:

  • Input: This node necessitates a text input. Typically, you would connect the input to an Input node. Through this input, you will need to provide the text query that you want to search for in your tables (i.e., CSV).
  • Output: This node outputs chunks of information, after having filter the information based on your query (your input). Typically, you would connect the output to an LLM or Output node.

​
Tables upload

Additionally, you will need to upload your table to the node. The file has to be in CSV format. To do so, click on the Upload CSV button and select the file you want to upload.

​
Table + Search node settings

By clicking on the settings icon, you can access the settings modal. Here you can do the following:

  • LLM provider: as default, OpenAI is selected although you have the option to select Azure. This will be the model used to transform your querty into SQL query to be able to search through the CSV table.
  • Chunking algorithm: by default, the system uses sentence. You can also choose naive.
  • Chunk length: by default, the system uses 1500. You can also choose as many as you want by clicking the number and editing it.
  • LLM API key: by default, the text field is empty. Stack AI’s API key are used. If you would like to use yours, then include your API key in this text field.
WebsitesSharepoint Node