Uploaded image for project: 'Python Integrations'
  1. Python Integrations
  2. INTPYTHON-585

Update VectorStores to take BSON Binary Vectors

    • 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

      Context

      In How Vector Search Scales by henry.weller@mongodb.com, a new "quantization" field is shown added the to our "vector" indexes. See below. In order for this quantization to work, will the "path" have to be a binary vector subtype? If so, I imagine that the binary values will already have to match the type specified in the quantization, right? To my knowledge, we don't have this work on our roadmap, not even for our langchain repo.

      Definition of done

      This task is to create binary.from_vector on embedding vectors before storing them in our collections.

       

      Pitfalls

      Backward compatibility must be considered. Note that vectors are rarely returned during queries, according to Product team.

       

            Assignee:
            Unassigned Unassigned
            Reporter:
            casey.clements@mongodb.com Casey Clements
            Votes:
            0 Vote for this issue
            Watchers:
            2 Start watching this issue

              Created:
              Updated: