Explore Re-ingestion of Astro readdocs

[davidgxue]

Please describe the feature you'd like to see
Explore Re-ingestion of Astro readdocs without other response quality degrading.

Describe the solution you'd like

• Reingest Astro readdocs while making sure the response qualities do not degrade because of it
• Requires data cleaning during ingestion
• Additional mechanisms such as skipping some webpages of the readdocs may also be needed.

Acceptance Criteria

• Re-ingest ask astro readdocs with no degrade in response quality
• Add data cleaning in data ingestion