chore: Add new session-level service for getting embeddings of a specific collection MCP-246

[kmruiz]

Proposed changes

This PR adds a new session level service called VectorSearchEmbeddings, that is responsible of:

1. Understanding if Atlas Search is available
2. Retrieving which fields of a collection are embeddings, based on Atlas Search index definitions.
3. Validating that, given a document, it's valid according to the embedding definitions.

Given that the embedding combinations and detection can be inaccurate, we also provide a new configuration option called "disableEmbeddingsValidation" that can be set up by CLI/Env and when true, the validation is bypassed.

This PR also introduces the embedding validation in the insertMany tool, so users can not randomly add data that can break
existing models or indexes unknowingly.

We depend on #628 to be merged, as it implements a method to detect if Atlas Search is available. Whenever the PR is merged, I'll refactor the method introduced there and use VectorSearchEmbeddings, so we have only one single place for search detection.

Checklist

• I have signed the MongoDB CLA

[Copilot]

Pull Request Overview

Copilot reviewed 23 out of 23 changed files in this pull request and generated 2 comments.