OpenAI's Batch API Support

[kluhan]

Is your feature request related to a problem? Please describe.
Currently, Haystack doesn’t support OpenAI’s batch API, which limits throughput and efficiency when processing large amounts of data with OpenAI models. This leads to higher latency and increased costs due to individual API calls for each request.

Describe the solution you'd like
I’d like to see Haystack support or enable leveraging the capabilities of OpenAI’s batch API.

Describe alternatives you've considered
I’ve considered workarounds, such as building a custom component that sends requests to a server, collects several requests for batching, and returns the results after processing. However, this approach would require running hundreds of pipeline instances in parallel, adding significant complexity.

Additional context
Batch API support would be a valuable enhancement, particularly for large-scale applications. Any information on potential plans or timelines for this feature would be appreciated.