Anastas Stoyanovsky

Related JIRA ticket: [SLF4J-168](https://jira.qos.ch/projects/SLF4J/issues/SLF4J-168) For cloud development, the ability to log numeric values in JSON logs is essential to be able to do aggregations for statistics on logged numeric values...

## 📚 Documentation As seen in the README [here](https://github.com/Unbabel/MT-Telescope#command-line-interface-cli): ``` Usage: telescope compare [OPTIONS] Options: ... -o, --output_folder TEXT Folder you wish to use to save plots. ... --sample_ratio FLOAT...

feat: Pass parallel_tool_calls correctly

3

# What does this PR do? Closes #4123 A set of changes were introduced by the pre-commit hook. The relevant change here is in `streaming.py`. ## Test Plan Manual verification.

docs: Delete parallel tool calls section from known limitations documentation because it has now been implemented

3

Remove section on "rumored" (thereafter confirmed and corrected) issue with parallel tool calls. Fixed in #4124 and #4196.

Introduce more flexibility for QA generation output persistence

1

Right now, the output file for QA generation [is specified in `GenerationOptions`](https://github.com/docling-project/docling-sdg/blob/main/docling_sdg/qa/base.py#L110), as used [in QA gen here](https://github.com/docling-project/docling-sdg/blob/main/docling_sdg/qa/generate.py#L234). When using this to write a demo notebook in #11 and wanting...

Add concurrency support to QA generation

2

Currently, it [loops through chunks serially](https://github.com/docling-project/docling-sdg/blob/main/docling_sdg/qa/generate.py#L133). Using externally hosted model providers should allow concurrent request execution to greatly speed up QA generation.