[Feature Request]: Speech to text and audio files support (OpenAI Whisper) #1514
Description
Is there an existing issue for the same feature request?
- I have checked the existing issues.
Is your feature request related to a problem?
No response
Describe the feature you'd like
Give the option to upload audio files to the knowledge bases, and support the option on model providers to use speech to text models like OpenAI Whisper, so we can extract text from the audio files and integrate it as knowledge on the "Rag" process.
Whisper could be loaded via an API key from OpenAI or from XInference.
Describe implementation you've considered
No response
Documentation, adoption, use case
No response
Additional information
No response