[CAI-879] Add the google reranker by LlamaIndex

[mdciri]

List of Changes

Add the use of the Google Ranker by LlamaIndex with safe asynchronicity.

Motivation and Context

Use a maintained library.

How Has This Been Tested?

Locally in docker compose and in DEV

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: 6c373bd

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

This PR includes changesets to release 1 package

Name	Type
chatbot	Patch

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]

Branch is not up to date with base branch

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

[Copilot]

Pull request overview

This PR migrates the chatbot’s Google reranking integration to the maintained LlamaIndex Google reranker package and adds a small wrapper to avoid asyncio event-loop binding issues during async request handling.

Changes:

• Replace the custom Google reranker implementation with a wrapper around llama_index.postprocessor.google_rerank.GoogleRerank that lazily creates the async Discovery Engine client.
• Update RAG tool setup to construct scoped service-account credentials and configure the reranker with model/project/location.
• Switch the local __main__ server entrypoint to llama_index.core.async_utils.asyncio_run.

Reviewed changes

Copilot reviewed 5 out of 6 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
apps/chatbot/src/modules/tools/rag_tool.py	Wires in AsyncSafeGoogleRerank and builds Google service-account credentials for reranking.
apps/chatbot/src/modules/google_reranker.py	Replaces the custom reranker with an async-safe wrapper around LlamaIndex’s Google reranker.
apps/chatbot/src/app/main.py	Uses LlamaIndex’s asyncio_run helper to run the Hypercorn server coroutine.
apps/chatbot/pyproject.toml	Adds the LlamaIndex Google rerank postprocessor dependency.
apps/chatbot/poetry.lock	Locks the new dependency (and updates lock metadata).

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 5 out of 6 changed files in this pull request and generated 2 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

Jira Pull Request Link

This Pull Request refers to the following Jira issue CAI-879