[CAI-629] Code refactor of chatbot

[mdciri]

List of Changes

This pull request introduces major architectural changes to the chatbot system, focusing on refactoring, modularization, and improved payload handling between components. Key improvements include moving monitoring-related functionality from chatbot to chatbot-monitor, introducing payload compression for SQS communication, and updating dependencies for better compatibility and performance.

Architectural Refactoring and Modularization:

• Moved Presidio and DynamoDB functions, as well as the Presidio mask library, from chatbot to chatbot-monitor to better separate monitoring and evaluation concerns.
• Refactored chatbot-evaluate to send score writing operations to chatbot-monitor instead of directly handling them, removing the dependency on Langfuse client code in chatbot-evaluate.

Payload Compression and SQS Communication:

• Added compression and decompression utilities in codec.py and updated lambda_function.py to compress payloads before sending them to SQS, improving efficiency and reliability of inter-service communication.
• Introduced SQS queue configuration and utility functions for monitor queue access, enabling streamlined and configurable message passing.

Dependency and Environment Updates:

• Updated dependencies in pyproject.toml for llama-index and related packages to newer versions, and added jupyter for development.
• Modified Dockerfile to install git, ensuring build compatibility.

Logging and Monitoring Enhancements:

• Refactored logger initialization to support configurable log levels and improved log formatting across modules.
• Added chatbot version tagging to Langfuse for improved traceability.

Documentation and Miscellaneous:

• Added an architecture diagram reference to the README.md for better developer onboarding and system understanding.
• Updated changeset files to document the scope and impact of the refactor and logger updates.

Motivation and Context

move presidio masking into the chatbot-monitor lambda to speed-up the chatbot one. As result, the user should get the chatbot generated response in less time.

How Has This Been Tested?

Locally using docker compose in apps/chatbot/docker and in the DEV environment.

Screenshots (if appropriate):

Types of changes

• Chore (nothing changes by a user perspective)
• 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)

Checklist:

• My change requires a change to the documentation.
• I have updated the documentation accordingly.

[changeset-bot]

🦋 Changeset detected

Latest commit: b47cf8c

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 4 packages

Name	Type
chatbot-evaluate	Minor
chatbot-monitor	Major
chatbot-index	Patch
chatbot	Major

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[github-actions]

This pull request is stale because it has been open for 14 days with no activity. If the pull request is still valid, please update it within 21 days to keep it open or merge it, otherwise it will be closed automatically.

[github-actions]

This pull request is stale because it has been open for 14 days with no activity. If the pull request is still valid, please update it within 21 days to keep it open or merge it, otherwise it will be closed automatically.

[github-actions]

Jira Pull Request Link

This Pull Request refers to the following Jira issue CAI-629

[github-actions]

Branch is not up to date with base branch

@marcobottaro it seems this Pull Request is not updated with base branch.
Please proceed with a merge or rebase to solve this.

[github-actions]

This PR exceeds the recommended size of 800 lines. Please make sure you are NOT addressing multiple issues with one PR. Note this PR might be rejected due to its size.