Generate Insights
v.1.0.0
Last updated
Was this helpful?
v.1.0.0
Last updated
Was this helpful?
The generate_insights tool allows the user to add explanatory insights, generated with OpenAI API, to a dataset of various natures. This could be generic data provided by the user, such as a table, a bar chart, etc., or it could be an output file generated by one of our tools. Currently, the implemented tools are as follows:
generic_insights: For any table introduced by the user, a series of bullet points with insights about the data is returned.
partial_dependence: Given the data frame containing the partial dependence evaluations, df_pdp.csv
, generated in the function, this tool provides a textual explanation of each potential one-dimensional partial dependence graph available.
drivers_barriers: This tool starts from the table of drivers and barriers, df_db.csv, generated in the or functions. To every row, it adds a textual description explaining which inputs contribute the most, both positively and negatively, to the target taking a specific value. Executions are currently limited to 15 rows at a time.
Version 1.0.0 of the tool requires user access to the OpenAI model gpt-4-1106-preview
, to ensure proper functionality.
Make sure you have followed these steps first: Setup and Requirements
Import necessary libraries and initialize the Shimoku client with your credentials. Define a workspace and a menu path for organizing your AI models.
Note: you must have your SHIMOKU_TOKEN,
UNIVERSE_ID
, WORKSPACE_ID,
OPENAI_API_KEY
and OPENAI_ORG_ID
saved as environment variables.
Upload any type of table on which you wish to request relevant information. No additional format is imposed.
Call the insight generator function and adjust the arguments for the generic_insights task.
ai_function: str Label for this functionality, which will have the value 'generate_insights'.
openai_api_key: str Your OpenAI unique API key.
openai_org_id: str Your OpenAI organization id.
task: str 'generic_insight' requests to generate insights about a table in any type of format.
data: str Name chosen in create_input_files to refer to the table.
Wait for the insights to be generated and the outputs to be uploaded.
Once execution is complete, insights are available.
Upload the resulting partial dependence file, df_pdp.csv, as it was returned by our function.
Upload the drivers and barriers file, df_db.csv, as it was generated by one of our functions, the or . Also, you will need to upload the dataset you used to train your model. Here are the files we used in the example of .