Context:
A self-querying retriever is one that, as the name suggests, has the ability to query itself. Specifically, given any natural language query, the retriever uses a query-constructing LLM chain to write a structured query and then applies that structured query to its underlying VectorStore. This allows the retriever to not only use the user-input query for semantic similarity comparison with the contents of stored documents but to also extract filters from the user query on the metadata of stored documents and to execute those filters.

DOD:
There is an existing implementation for MongoDB in the langchain-community package, which can be migrated over to LangChain-MongoDB package.

MongoDB Atlas has basic implicit support for self-querying as demonstrated in this notebook. Enhance the features like support for filters, etc 

https://python.langchain.com/docs/integrations/retrievers/self_query/mongodb_atlas/

The query constructor is defined here :https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/query_constructors/mongodb_atlas.py

The API reference for the SelfQuery retriever is defined here https://python.langchain.com/api_reference/langchain/retrievers/langchain.retrievers.self_query.base.SelfQueryRetriever.html