Removing `VisionImageRawFrame` lets us simplify LLM services' logic, getting us closer to the idealized architecture where all they care about is handling context frames.
This change is in service of getting us closer to ready to deprecate usage of `OpenAILLMContext` and subclasses in favor of the universal `LLMContext`, at least for the traditional text-to-text LLMs.
Why remove `VisionImageRawFrame` rather than deprecate? It's "internal"—only created by `VisionImageFrameAggregator`—and never intended to be used directly by users (it would be difficult to use directly anyway).
Move the logic that was once in `VisionImageFrameAggregator` directly into the examples. Reasoning:
- If `UserImageRequester` is defined in the examples, it makes sense for `UserImageProcessor` to be too, as it’s the flip side of the same coin, so to speak
- The logic is now pretty trivial
- This kind of one-shot, history-less image-describing pipeline shouldn't be common at all; it's ok for it to live in examples rather than as a dedicated class
- In the short term, this enables us to create `LLMContext`s for services that support it and `OpenAILLMContext`s for services that don't yet (AWS)
This commit also adds missing translation from OpenAI-format image context messages to AWS format. Note that this isn't a wasted effort in the face of the upcoming migration to universal `LLMContext`—this work will be reused as it has to be implemented there too.
Gemini text input works. We translate from OpenAILLMContext format
on the fly in the GoogleLLMService implementation. This commit also
implements image input (vision) in both the GoogleLLMService and in
the OpenAILLMService. Image input is a hack and needs to be revisited.
OpenAI expects images to be uploaded as base64-encoded JPEGs. Google
does not require the base64 encoding. Other than for images, we use
the OpenAI format as our standard, but base64-encoding the images
and then unencoding them in the GoogleLLMService feels wasteful.
