MultiVectorRetriever - using only a specific Docstore table / specific vectorstore collection?

[Txm1906]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

retriever = createMultiVectorRetriever(
        vectorstore=temp_collection,
        docstore=docstore,  # Point to the temporary SQL table?
        
        id_key="doc_id", 
        top_k=4,  
    )

def createMultiVectorRetriever(vectorstore, docstore, id_key, top_k=4):
    retriever = MultiVectorRetriever(
        vectorstore=vectorstore,
        docstore=docstore,
        id_key=id_key,
        search_kwargs={"k": top_k},
    )  # langchain MultiVectorRetriever

    return retriever

Description

My docstore has multipe tables, but i only want to use one specific table for the retrieval. The MultiVectorRetriever expects docstore to be a database and not a table.

How can i only use a specific table?

Same applies for the vectorstore, i have two collections in the vectorstore. How can i only specify the usage of one?

Thanks!

System Info

not necessary in this case