Introduce Quantization into our main VectorStore(s) / create VoyageAI VectorStore

XMLWordPrintableJSON

    • Type: Task
    • Resolution: Unresolved
    • Priority: Unknown
    • None
    • Affects Version/s: None
    • Component/s: AI/ML
    • 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

      Describe the background behind the problem.

      VoyageAI produces Quantization-aware models. Our main Vector stores, like `MongoDBAtlasVectorSearch` should highlight this power of ours by making this a component of the entry-level tooling.

      Pitfalls

      What should the implementer watch out for? What are the risks?

      We should consider design. For backwards compatibility, it is definitely easier to create a subclass that is Voyage-specific. This is still valuable, and could slowly become our default.

      Definition of done

      What must be done to consider the task complete?

      Create a new VectorStore with quantization built into it. Take advantage and show off Voyage's capabilities.

              Assignee:
              Unassigned
              Reporter:
              Casey Clements
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

                Created:
                Updated: