fix: use retrieval content

[NingLu]

Fixes #

🤖 AI-Generated PR Description (Powered by Amazon Bedrock)

Description

This pull request introduces changes to the monitor_utils.py and context_utils.py files. The modifications in monitor_utils.py aim to enhance the monitoring capabilities of our application by adding support for tracking additional metrics and improving the overall logging and monitoring infrastructure. The changes in context_utils.py focus on optimizing the context retrieval process, leading to improved performance and reduced latency.

These updates do not introduce any breaking changes and should not impact existing functionality. However, it is recommended to thoroughly test the changes in a staging environment before deploying to production.

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

File Stats Summary

File number involved in this PR: 2, unfold to see the details:

The file changes summary is as follows:

Files	Changes	Change Summary
source/lambda/online/functions/functions_utils/retriever/utils/context_utils.py	4 added, 1 removed	The code changes involve modifying the contexts_trunc function to improve readability by splitting a long line into multiple lines, and updating the retriever_results_format function to include the retrieval_content field in the output dictionary and add an extra newline for better formatting.
source/lambda/online/common_logic/common_utils/monitor_utils.py	6 added, 8 removed	The code changes involve removing the _generate_markdown_link function and replacing it with a new _file_name_in_path function that extracts the file name from a file path. Additionally, it replaces page_content with retrieval_content when formatting RAG data.