Feature/add docs

[emrgnt-cmplxty]

	🚀 This PR description was created by Ellipsis for commit 42bd470.

Summary:

This PR adds comprehensive documentation for the core features of the application and modifies the _parse_html method in the BasicIngestionPipeline class.

Key points:

• Added documentation for the Ingestion, Embedding, RAG, Evaluation, and Factory pipelines in the /docs/pages/core-features/ directory.
• Modified the _parse_html method in the BasicIngestionPipeline class to expect a bytes object instead of a string.

---

Generated with ❤️ by ellipsis.dev

[ellipsis-dev]

❌ Changes requested.

• Reviewed the entire pull request up to 42bd470
• Looked at 594 lines of code in 7 files
• Took 53 seconds to review

More info

• Skipped 0 files when reviewing.
• Skipped posting 0 additional comments because they didn't meet confidence threshold of 50%.

Workflow ID: wflow_D2GTweVahq3VPWzu

---

Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. We'll respond in a few minutes. Learn more here.

[ellipsis-dev]

The condition for the HTML entry type is incorrect. It checks if entry_data is a bytes object and then attempts to encode it to utf-8. This will raise an error because bytes objects do not need to be encoded. The condition should check if entry_data is a str object and then encode it to utf-8.

Suggested change

	return self._parse_html(entry_data.encode("utf-8"))
	if not isinstance(entry_data, str):
	raise ValueError("HTML data must be a string.")
	return self._parse_html(entry_data.encode("utf-8"))