Currently our LLM interface and ExtractByLlm builtin function only supports text prompt. We want it to support image inputs too.

• Extend LlmGenerateRequest to accept image bytes as input:
  

  cocoindex/src/llm/mod.rs

  Line 34 in f368a9a

  pub struct LlmGenerateRequest<'a> {

• Implement existing LLM clients to pass this to different APIs (usually as base64)
• Extend the ExtractByLlm function to accept an optional image as input
• Can be tested by the existing image_search_example example. It's using customized code to send image to LLM now. We should be able to replace it with the ExtractByLlm function.

❤️ Contributors, please refer to 📙Contributing Guide.
Unless the PR can be sent immediately (e.g. just a few lines of code), we recommend you to leave a comment on the issue like I'm working on it or Can I work on this issue? to avoid duplicating work. Our Discord server is always open and friendly.