LangChain: Add support for "Indexing"

XMLWordPrintableJSON

    • Type: Improvement
    • Resolution: Done
    • Priority: Major - P3
    • None
    • Affects Version/s: None
    • Component/s: AI/ML
    • None
    • None
    • Python Drivers
    • Hide

      1. What would you like to communicate to the user about this feature?
      2. Would you like the user to see examples of the syntax and/or executable code and its output?
      3. Which versions of the driver/connector does this apply to?

      Show
      1. What would you like to communicate to the user about this feature? 2. Would you like the user to see examples of the syntax and/or executable code and its output? 3. Which versions of the driver/connector does this apply to?
    • None
    • None
    • None
    • None
    • None
    • None

      TLDR: Set custom ids on `add_documents` in MongoDBAtlasVectorSearch

      Context

      One of our stakeholders wants support for a LangChain feature [LangChain Indexing|https://python.langchain.com/docs/modules/data_connection/indexing/] and our library currently does not support it. In order to get that support, we need to add `ids` to our function `add_documents` function signature and entertain submitting documents with custom ids rather than the explicit MongoDB defined ones.

      Our change will need to be made to the `add_texts` which is the inner function called by `add_documents`.

            Assignee:
            Casey Clements
            Reporter:
            Jib Adegunloye
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

              Created:
              Updated:
              Resolved: