docling-project / docling-project/docling-sdg

Expand .env capability to cover conceptual generation parameters such as embed model

Open
#39 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
51
Forks
21
PR merge metrics
No merged PRs in 30d

Description

As noted in https://github.com/docling-project/docling-sdg/pull/38#discussion_r2242356006:

The constants in conceptual_generate.py starting with EMBED_MODEL_ID should probably be configurable. The proposed mechanism for doing that proposed in the comment above is:

- move the file docling_sdg/resources/watsonx_example.env to the root of the repository
- rename it to .env.example
- add this option with the feature name as prefix, e.g. CONCEPTUAL_GEN__EMBED_MODEL_ID with a default value (e.g., IBM Granite)
- leverage [pydantic settings](https://docs.pydantic.dev/latest/concepts/pydantic_settings/#parsing-environment-variable-values) to parse nested variables.
- rename the existing Watsonx variables according to pydantic settings conventions for nested variables.
- update the documentation

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.