[128] - Add GCS functionality to Existing Speech Workflow

[MustafaAkolawala]

Reviewer: @markbotterill Estimate: 20 mins

---

Ticket

Fixes: JIRA_TICKET_LINK

Description

This PR integrates Google Cloud Storage (GCS) functionality into the end-to-end speech workflow, enabling cloud-based file upload and retrieval.

Goal

the Goal of this PR is To enhance the existing speech-to-speech workflow by leveraging cloud storage, eliminating the need for local disk operations and facilitating easier file management.

Changes

• Implemented two new functions in core_backend/app/utils for GCS file upload and retrieval.
• Integrated these functions into the stt-llm-response endpoint and generate_speech component.

How has this been tested?

• dev environment
• docker compose
• Unit Tests

How to test this?

1. Set the appropriate GCS variables from template.core_backend.env (according to your gcs bucket name, by default we using "aaq-speech-test")
2. Send a POST request to thestt-llm-response endpoint.
3. Verify the Uploaded file in the GCS Bucket .
4. If generate_tts is set to true in the QueryResponse Schema, a signed URL will be generated. Access this URL to play the generated MP3 file for text-to-speech output.

Checklist

Fill with x for completed.

• [x] My code follows the style guidelines of this project
• [x] I have reviewed my own code to ensure good quality
• [x] I have tested the functionality of my code to ensure it works as intended
• [x] I have resolved merge conflicts
• [x] I have updated the automated tests
• [x] I have updated the requirements