👐 Import data into MongoDB

The documentation agent has two tools- a vector search tool to retrieve information from documentation to answer questions, and another tool to get the content from specific documentation pages for summarization.

Let's import the data required by these tools into two MongoDB collections. This is as simple as making a POST request to a serverless function that we have created for you.

Run the cells under the Step 2: Import data into MongoDB section in the notebook to import the data required by the agent's tools, into MongoDB collections.

To verify that the data has been imported into your MongoDB cluster, navigate to the Overview page in the Atlas UI. In the Clusters section, select your cluster and click Browse collections.

Ensure that you see a database called mongodb_genai_devday, and two collections namely mongodb-docs and mongodb-docs-embedded under it. Note the number and format of documents in both the collections.

The mongodb-docs-embedded collection chunked versions of documents in the mongodb-docs collection, and hence has a higher document count.