Refactor the `kotaemon/pipelines` module to `kotaemon/indices`. Create the VectorIndex. Note: currently I place `qa` to be inside `kotaemon/indices` since at the moment we only have `qa` in RAG. At the same time, I think `qa` can be an independent module in `kotaemon/qa`. Since this can be changed later, I still go at the 1st option for now to observe if we can change it later.
20 lines
494 B
Python
20 lines
494 B
Python
from ..base import DocTransformer, LlamaIndexDocTransformerMixin
|
|
|
|
|
|
class BaseDocParser(DocTransformer):
|
|
...
|
|
|
|
|
|
class TitleExtractor(LlamaIndexDocTransformerMixin, BaseDocParser):
|
|
def _get_li_class(self):
|
|
from llama_index.extractors import TitleExtractor
|
|
|
|
return TitleExtractor
|
|
|
|
|
|
class SummaryExtractor(LlamaIndexDocTransformerMixin, BaseDocParser):
|
|
def _get_li_class(self):
|
|
from llama_index.extractors import SummaryExtractor
|
|
|
|
return SummaryExtractor
|