How to Build an ETL App for Mistral AI Data in Python with CData

The rich ecosystem of Python modules lets you get to work quickly and integrate your systems more effectively. With the CData API Driver for Python and the petl framework, you can build Mistral AI-connected applications and pipelines for extracting, transforming, and loading Mistral AI data. This article shows how to connect to Mistral AI with the CData Python Connector and use petl and pandas to extract, transform, and load Mistral AI data.

With built-in, optimized data processing, the CData Python Connector offers unmatched performance for interacting with live Mistral AI data in Python. When you issue complex SQL queries from Mistral AI, the driver pushes supported SQL operations, like filters and aggregations, directly to Mistral AI and utilizes the embedded SQL engine to process unsupported operations client-side (often SQL functions and JOIN operations).

Connecting to Mistral AI Data

Connecting to Mistral AI data looks just like connecting to any relational data source. Create a connection string using the required connection properties. For this article, you will pass the connection string as a parameter to the create_engine function.

The MistralAI API uses API key authentication.

Using API Key Authentication

Your MistralAI API Key is required to create a connection to MistralAI. API Keys can be obtained from your MistralAI account at console.mistral.ai by navigating to the API Keys section. Once you have obtained the API key, set it in the ProfileSettings connection property.

Example Connection string

Profile=C:\profiles\MistralAI.apip;ProfileSettings='APIKey=my_api_key;';AuthScheme=APIKey;

After installing the CData Mistral AI Connector, follow the procedure below to install the other required modules and start accessing Mistral AI through Python objects.

Install Required Modules

Use the pip utility to install the required modules and frameworks:

pip install petl
pip install pandas

Build an ETL App for Mistral AI Data in Python

Once the required modules and frameworks are installed, we are ready to build our ETL app. Code snippets follow, but the full source code is available at the end of the article.

First, be sure to import the modules (including the CData Connector) with the following:

import petl as etl
import pandas as pd
import cdata.api as mod

You can now connect with a connection string. Use the connect function for the CData Mistral AI Connector to create a connection for working with Mistral AI data.

cnxn = mod.connect("Profile=C:\profiles\MistralAI.apip;ProfileSettings='APIKey=my_api_key;';AuthScheme=APIKey;")

Create a SQL Statement to Query Mistral AI

Use SQL to create a statement for querying Mistral AI. In this article, we read data from the AudioTranscriptions entity.

sql = "SELECT ,  FROM AudioTranscriptions WHERE Model = 'voxtral-mini-latest'"

Extract, Transform, and Load the Mistral AI Data

With the query results stored in a DataFrame, we can use petl to extract, transform, and load the Mistral AI data. In this example, we extract Mistral AI data, sort the data by the column, and load the data into a CSV file.

Loading Mistral AI Data into a CSV File

table1 = etl.fromdb(cnxn,sql)

table2 = etl.sort(table1,'')

etl.tocsv(table2,'audiotranscriptions_data.csv')

With the CData API Driver for Python, you can work with Mistral AI data just like you would with any database, including direct access to data in ETL packages like petl.

Free Trial & More Information

Download a free, 30-day trial of the CData API Driver for Python to start building Python apps and scripts with connectivity to Mistral AI data. Reach out to our Support Team if you have any questions.

Full Source Code

import petl as etl
import pandas as pd
import cdata.api as mod

cnxn = mod.connect("Profile=C:\profiles\MistralAI.apip;ProfileSettings='APIKey=my_api_key;';AuthScheme=APIKey;")

sql = "SELECT ,  FROM AudioTranscriptions WHERE Model = 'voxtral-mini-latest'"

table1 = etl.fromdb(cnxn,sql)

table2 = etl.sort(table1,'')

etl.tocsv(table2,'audiotranscriptions_data.csv')