Skip to content

Decoupled Producer/Consumer #11

@h4gen

Description

@h4gen

Implementation

Use an internal asyncio.Queue to separate the Fetch (fast) from the Vectorization (slow/API-bound).

Why

Allows fetching the next batch while the current one is still waiting for an LLM response, maximizing throughput.

Metadata

Metadata

Assignees

No one assigned

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions