Update the "InterleavedTextMedia" type (#635)

## What does this PR do?

This is a long-pending change and particularly important to get done
now.

Specifically:
- we cannot "localize" (aka download) any URLs from media attachments
anywhere near our modeling code. it must be done within llama-stack.
- `PIL.Image` is infesting all our APIs via `ImageMedia ->
InterleavedTextMedia` and that cannot be right at all. Anything in the
API surface must be "naturally serializable". We need a standard `{
type: "image", image_url: "<...>" }` which is more extensible
- `UserMessage`, `SystemMessage`, etc. are moved completely to
llama-stack from the llama-models repository.

See https://github.com/meta-llama/llama-models/pull/244 for the
corresponding PR in llama-models.

## Test Plan

```bash
cd llama_stack/providers/tests

pytest -s -v -k "fireworks or ollama or together" inference/test_vision_inference.py
pytest -s -v -k "(fireworks or ollama or together) and llama_3b" inference/test_text_inference.py
pytest -s -v -k chroma memory/test_memory.py \
  --env EMBEDDING_DIMENSION=384 --env CHROMA_DB_PATH=/tmp/foobar

pytest -s -v -k fireworks agents/test_agents.py  \
   --safety-shield=meta-llama/Llama-Guard-3-8B \
   --inference-model=meta-llama/Llama-3.1-8B-Instruct
```

Updated the client sdk (see PR ...), installed the SDK in the same
environment and then ran the SDK tests:

```bash
cd tests/client-sdk
LLAMA_STACK_CONFIG=together pytest -s -v agents/test_agents.py
LLAMA_STACK_CONFIG=ollama pytest -s -v memory/test_memory.py

# this one needed a bit of hacking in the run.yaml to ensure I could register the vision model correctly
INFERENCE_MODEL=llama3.2-vision:latest LLAMA_STACK_CONFIG=ollama pytest -s -v inference/test_inference.py
```

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -8,7 +8,6 @@ import logging
 from typing import AsyncGenerator
 
 from llama_models.llama3.api.chat_format import ChatFormat
-from llama_models.llama3.api.datatypes import Message
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import all_registered_models
 
@@ -22,6 +21,7 @@ from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,
 )
 from llama_stack.providers.utils.inference.openai_compat import (
+    convert_message_to_openai_dict,
     get_sampling_options,
     process_chat_completion_response,
     process_chat_completion_stream_response,
@@ -30,7 +30,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     chat_completion_request_to_prompt,
     completion_request_to_prompt,
     content_has_media,
-    convert_message_to_dict,
+    interleaved_content_as_str,
     request_has_media,
 )
 
@@ -71,7 +71,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
     async def completion(
         self,
         model_id: str,
-        content: InterleavedTextMedia,
+        content: InterleavedContent,
         sampling_params: Optional[SamplingParams] = SamplingParams(),
         response_format: Optional[ResponseFormat] = None,
         stream: Optional[bool] = False,
@@ -163,7 +163,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
             if media_present:
                 # vllm does not seem to work well with image urls, so we download the images
                 input_dict["messages"] = [
-                    await convert_message_to_dict(m, download=True)
+                    await convert_message_to_openai_dict(m, download=True)
                     for m in request.messages
                 ]
             else:
@@ -202,7 +202,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
     async def embeddings(
         self,
         model_id: str,
-        contents: List[InterleavedTextMedia],
+        contents: List[InterleavedContent],
     ) -> EmbeddingsResponse:
         model = await self.model_store.get_model(model_id)
 
@@ -215,7 +215,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
         ), "VLLM does not support media for embeddings"
         response = self.client.embeddings.create(
             model=model.provider_resource_id,
-            input=[interleaved_text_media_as_str(content) for content in contents],
+            input=[interleaved_content_as_str(content) for content in contents],
             **kwargs,
         )