Hello team,
First of all, thank you for this amazing project! I have been exploring its features and I’m very impressed.
I have a question regarding the backend API configuration. I am trying to build a workflow where I rely exclusively on Google AI Studio (Gemini) and xAI (Grok) APIs, rather than using OpenAI or other services.
Specifically, I would like to know if it is possible to configure these two APIs to handle both of the following tasks:
Prompt Reasoning/LLM Text Generation: Using Google AI Studio or xAI for understanding the context, generating prompts, and text-based reasoning.
Image/Video Generation: Using these APIs to generate images and videos. (I know Google AI Studio has Imagen capabilities, but I’m unsure about the xAI image/video generation support or how to route this in the config).
Questions:
Is there a built-in way or a configuration setting to map these tasks strictly to Google AI Studio and xAI?
If xAI does not support image/video generation yet, can I use Google AI Studio solely for the media generation while xAI handles the prompt reasoning?
Are there any specific environment variables or .env configurations I need to be aware of to make this work smoothly?
What I have tried:
I tried looking into the documentation/configuration files, but I couldn’t find a clear example of using these two providers together as the sole backend for both media generation and reasoning.
Any guidance, documentation links, or configuration examples would be greatly appreciated.
Thank you for your time and help!
Hello team,
First of all, thank you for this amazing project! I have been exploring its features and I’m very impressed.
I have a question regarding the backend API configuration. I am trying to build a workflow where I rely exclusively on Google AI Studio (Gemini) and xAI (Grok) APIs, rather than using OpenAI or other services.
Specifically, I would like to know if it is possible to configure these two APIs to handle both of the following tasks:
Prompt Reasoning/LLM Text Generation: Using Google AI Studio or xAI for understanding the context, generating prompts, and text-based reasoning.
Image/Video Generation: Using these APIs to generate images and videos. (I know Google AI Studio has Imagen capabilities, but I’m unsure about the xAI image/video generation support or how to route this in the config).
Questions:
Is there a built-in way or a configuration setting to map these tasks strictly to Google AI Studio and xAI?
If xAI does not support image/video generation yet, can I use Google AI Studio solely for the media generation while xAI handles the prompt reasoning?
Are there any specific environment variables or .env configurations I need to be aware of to make this work smoothly?
What I have tried:
I tried looking into the documentation/configuration files, but I couldn’t find a clear example of using these two providers together as the sole backend for both media generation and reasoning.
Any guidance, documentation links, or configuration examples would be greatly appreciated.
Thank you for your time and help!