chore: use ollama/all-minilm:l6-v2 for ollama tests (#3537)

# What does this PR do?

use ollama embedding models for ollama test, previously using
sentence-transformer

recordings:
- ./scripts/integration-tests.sh --stack-config server:ci-tests --suite
base --setup ollama --inference-mode record
- ./scripts/integration-tests.sh --stack-config server:ci-tests --suite
vision --setup ollama-vision --inference-mode record

## Test Plan

ci w/ added skip base64 embedding test

tests/integration/inference/test_openai_embeddings.py

@@ -44,6 +44,7 @@ def skip_if_model_doesnt_support_encoding_format_base64(client, model_id):
         "remote::together",  # param silently ignored, always returns floats
         "remote::databricks",  # param silently ignored, always returns floats
         "remote::fireworks",  # param silently ignored, always returns list of floats
+        "remote::ollama",  # param silently ignored, always returns list of floats
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support encoding_format='base64'.")