An indexing job reads each document through the source's API, with the credentials you gave.
Documentation and articles: one sentence per passage, which keeps the sentences around it. Slack threads and Jira issues: larger chunks.
An embedding model on AWS Bedrock turns each passage into a list of numbers that stands for its meaning.
[0.12, −0.48, 0.07, …]Each passage goes into your organization's own table in the search database: its text for keyword search, its embedding for semantic search, and its labels.