Shahrokh Daijavad comments

Results 118 comments of


                                            Shahrokh Daijavad

[Feature] IBM's SmolDocling integration for ocr ai as an another option for ocr in pdf2parquet

Thank you for your investigation of this, @ShiroYasha18. This is useful. I think, as DPK moves in the direction of supporting some multimedia transforms (there is an outstanding PR for...

[Bug] pdf_processing_1_python.ipynb is not working, complaining for ModuleNotFoundError: No module named 'humanfriendly'

@santoshborse, There are multiple problems associated with this notebook, as you can see in the PR #1259. Last week, @sujee, who originally developed this notebook, asked us to re-engage, and...

[Bug] Web2Parquet DataAccessLocal Update needed

@touma-I and @swith005, what do you think?

Updating RAG example to use Granite model

Thanks, @sujee I tested this with the Granite model you have set up as: MY_CONFIG.LLM_MODEL = "ibm-granite/granite-20b-code-instruct-8k" And it is fine. Doesn't it make sense to change the name of...

Updating RAG example to use Granite model

@sujee If you are ok with changing the name of the notebook, please remember to change the README file, too: https://github.com/IBM/data-prep-kit/blob/dev/examples/notebooks/rag/README.md

Updating RAG example to use Granite model

@sujee In the meeting with Hima this morning, she said that IBM will open-source the Granite "language" models in a week or so and using the "code" model "ibm-granite/granite-20b-code-instruct-8k" (I...

Updating RAG example to use Granite model

@sujee I see that the Granite language models are now available on replicate.com (see: https://replicate.com/search?query=granite). Please change to these models (2b and 8b) and tag me for testing.

Updating RAG example to use Granite model

This is the same PR as #745, so I will close this one.