Simonas Jakubonis comments

Repositories
Issues
Comments

Results 14 comments of


                                            Simonas Jakubonis

trafficstars

Improve accuracy and reduce speed

This is odd, I have a speed of 1 page/s on a Google C4 CPU instance using four cores. Easyocr is a bit slower than Rapid OCR

Add option to export_to_markdown to mark page breaks

Is this deployed in the current version?

ColPali `colbert-embedder`

hey, any updates here?

Langchain - Document loader basic functionality i.e `lazy load` implemented Issue #77

@aravindkarnam, could we have LangChain dependencies as optional extras? LangChain is quite a complex and heavy library, so it would be better to have a core crawl service and then...