Andrea Ruggerini

icon location Modena

Results 9 comments of Andrea Ruggerini

Question: typesense as Retriever for RAG applications

Thank you for the link. As far as I understand from the documentation , typensense does not internally handle the splitting of long documents so I should also take care...

ALTER TABLE support for adding constraints

Hello @papparapa , I am interested in this functionality as well. Did you make any progress?

[Feature]: Integrations with other backends via hOcr (naive implementation of easyOcr backend inside)

Oh, nevwrmind about the easyocr stuff, I see there's an official plugin (I'll look into that). I still would be grateful of @jbarlow83 can comment on the issue in general:...

[Feature]: Integrations with other backends via hOcr (naive implementation of easyOcr backend inside)

Thanks for the response, it's appreciated to have some help and orientation with this. > I wrote easyocr as direct to PDF, and then significantly improved hocr to PDF so...

true_which_overlapped_with_pred does not get updated properly (1)

Hey @ivyleavedtoadflax , I see this is still an issue. Do you have any suggestions to fix it?

[Question]: Approaches to searching documents requiring different kind of embeddings (multimodal too)

the response from dosubot is useful, but nothing beats a human. Thank you @logan-markewich !

Suggested patterns for storing job results

Hey @medihack thanks for getting back to me! > In contrast to Celery, with Procrastinate it’s always clear that there’s a PostgreSQL database that can be used for storage Yes,...

Suggested patterns for storing job results

Hello @ewjoachim, thanks for the detailed response. That's very helpful. I have a few follow-up questions to make sure I understand correctly: - Defining "High Load": I appreciate the project's...

Suggested patterns for storing job results

Hello, @ewjoachim , @medihack , I ended up going a different route, but after running the test I must say I am honestly amazed by how effective Postgres/Procrastinate is as...