-
Type:
Task
-
Resolution: Unresolved
-
Priority:
Unknown
-
None
-
Affects Version/s: None
-
Component/s: AI/ML
-
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.
- blocks
-
INTPYTHON-586 Add "quantization" as option to Vector stores
-
- Closed
-