Enabling data ingestion pipelines about quivr HOT 3 CLOSED

Cool, I see, so for pdf files I can basically start from backend/core/quivr_core/processor/implementations/megaparse_processor.py and modify as I want

from quivr.

CORE-196 Enabling data ingestion pipelines

from quivr.

quivr-core basically uses the registry to find the processor that matches a file extension.

The internal implementation of the processor could be as complex or as we want. As long as the processor implements ProcessorBase it can be added to the registry 👍🏼 The internal steps / parsing will all be internal to the processor and can use any external dependencies as we want.

from quivr.