Audio query functionality to multimodal backend

[okhleif-IL]

Description

This PR enables audio as a query in the backend, where the expected input to the gateway is a b64 string.

Issues

Part of RFC --> https://github.com/opea-project/docs/blob/main/community/rfcs/24-10-02-GenAIExamples-001-Image_and_Audio_Support_in_MultimodalQnA.md

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

N/A

Tests

Verify with curl command:

curl http://${host_ip}:8888/v1/multimodalqna -H "Content-Type: application/json" -d '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}]}]}'

curl http://${host_ip}:8888/v1/multimodalqna -H "Content-Type: application/json" -d '{"messages": [{"role": "user", "content": [{"type": "audio", "audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA, "}]}, {"role": "assistant", "content": "How may I help?"}, {"role": "user", "content": [{"type": "text", "text": "what pronoun did I tell you?"}]}]}

Need to add automated test.

[dmsuehir]

LGTM, thanks