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/nvidia/nvidia.py

@@ -8,14 +8,7 @@ import warnings
 from typing import AsyncIterator, List, Optional, Union
 
 from llama_models.datatypes import SamplingParams
-from llama_models.llama3.api.datatypes import (
-    ImageMedia,
-    InterleavedTextMedia,
-    Message,
-    ToolChoice,
-    ToolDefinition,
-    ToolPromptFormat,
-)
+from llama_models.llama3.api.datatypes import ToolDefinition, ToolPromptFormat
 from llama_models.sku_list import CoreModelId
 from openai import APIConnectionError, AsyncOpenAI
 
@@ -28,13 +21,17 @@ from llama_stack.apis.inference import (
     CompletionResponseStreamChunk,
     EmbeddingsResponse,
     Inference,
+    InterleavedContent,
     LogProbConfig,
+    Message,
     ResponseFormat,
+    ToolChoice,
 )
 from llama_stack.providers.utils.inference.model_registry import (
     build_model_alias,
     ModelRegistryHelper,
 )
+from llama_stack.providers.utils.inference.prompt_adapter import content_has_media
 
 from . import NVIDIAConfig
 from .openai_utils import (
@@ -123,17 +120,14 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
     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,
         logprobs: Optional[LogProbConfig] = None,
     ) -> Union[CompletionResponse, AsyncIterator[CompletionResponseStreamChunk]]:
-        if isinstance(content, ImageMedia) or (
-            isinstance(content, list)
-            and any(isinstance(c, ImageMedia) for c in content)
-        ):
-            raise NotImplementedError("ImageMedia is not supported")
+        if content_has_media(content):
+            raise NotImplementedError("Media is not supported")
 
         await check_health(self._config)  # this raises errors
 
@@ -165,7 +159,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
     async def embeddings(
         self,
         model_id: str,
-        contents: List[InterleavedTextMedia],
+        contents: List[InterleavedContent],
     ) -> EmbeddingsResponse:
         raise NotImplementedError()