How to use DocumentDB as a Vector Store with Langchain?

DocumentDB released its vector search capabilities. Since it's MongoDB compatible, I figured we could use the same code for MongoDB Atlas seen in https://python.langchain.com/docs/integrations/vectorstores/mongodb_atlas.

I've successfully connected to my DocDB cluster however, when I run the following code

vector_search = MongoDBAtlasVectorSearch.from_documents(    documents=docs,    embedding=bedrock_embeddings,    collection=MONGODB_COLLECTION)

I get an error: ValueError: Error raised by inference endpoint: 'Database' object is not callable.

At this point it's driving me crazy and I'm wondering if anyone has any insight on what might be causing this.

The differences from the example are that I'm using DocumentDB instead of MongoDB and Bedrock embeddings instead of OpenAI embeddings.

Attempted to upload documents to DocumentDB with Langchain. Expected Documents to be uploaded but was met with errors.