Vector store inference api (#598)

# What does this PR do?
Moves all the memory providers to use the inference API and improved the
memory tests to setup the inference stack correctly and use the
embedding models


## Test Plan
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.2-3B-Instruct"
--embedding-model="sentence-transformers/all-MiniLM-L6-v2"
llama_stack/providers/tests/inference/test_embeddings.py --env
EMBEDDING_DIMENSION=384


pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=weaviate"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY> --env
WEAVIATE_API_KEY=foo --env WEAVIATE_CLUSTER_URL=bar
 
pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=chroma"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY>--env
CHROMA_HOST=localhost --env CHROMA_PORT=8000

pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=pgvector"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
PGVECTOR_DB=postgres --env PGVECTOR_USER=postgres --env
PGVECTOR_PASSWORD=mysecretpassword --env PGVECTOR_HOST=0.0.0.0 --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY>

pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=faiss"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY>

llama_stack/providers/tests/memory/conftest.py

@@ -6,9 +6,65 @@
 
 import pytest
 
+from ..conftest import get_provider_fixture_overrides
+
+from ..inference.fixtures import INFERENCE_FIXTURES
 from .fixtures import MEMORY_FIXTURES
 
 
+DEFAULT_PROVIDER_COMBINATIONS = [
+    pytest.param(
+        {
+            "inference": "meta_reference",
+            "memory": "faiss",
+        },
+        id="meta_reference",
+        marks=pytest.mark.meta_reference,
+    ),
+    pytest.param(
+        {
+            "inference": "ollama",
+            "memory": "pgvector",
+        },
+        id="ollama",
+        marks=pytest.mark.ollama,
+    ),
+    pytest.param(
+        {
+            "inference": "together",
+            "memory": "chroma",
+        },
+        id="chroma",
+        marks=pytest.mark.chroma,
+    ),
+    pytest.param(
+        {
+            "inference": "bedrock",
+            "memory": "qdrant",
+        },
+        id="qdrant",
+        marks=pytest.mark.qdrant,
+    ),
+    pytest.param(
+        {
+            "inference": "fireworks",
+            "memory": "weaviate",
+        },
+        id="weaviate",
+        marks=pytest.mark.weaviate,
+    ),
+]
+
+
+def pytest_addoption(parser):
+    parser.addoption(
+        "--embedding-model",
+        action="store",
+        default=None,
+        help="Specify the embedding model to use for testing",
+    )
+
+
 def pytest_configure(config):
     for fixture_name in MEMORY_FIXTURES:
         config.addinivalue_line(
@@ -18,12 +74,22 @@ def pytest_configure(config):
 
 
 def pytest_generate_tests(metafunc):
+    if "embedding_model" in metafunc.fixturenames:
+        model = metafunc.config.getoption("--embedding-model")
+        if not model:
+            raise ValueError(
+                "No embedding model specified. Please provide a valid embedding model."
+            )
+        params = [pytest.param(model, id="")]
+
+        metafunc.parametrize("embedding_model", params, indirect=True)
     if "memory_stack" in metafunc.fixturenames:
-        metafunc.parametrize(
-            "memory_stack",
-            [
-                pytest.param(fixture_name, marks=getattr(pytest.mark, fixture_name))
-                for fixture_name in MEMORY_FIXTURES
-            ],
-            indirect=True,
+        available_fixtures = {
+            "inference": INFERENCE_FIXTURES,
+            "memory": MEMORY_FIXTURES,
+        }
+        combinations = (
+            get_provider_fixture_overrides(metafunc.config, available_fixtures)
+            or DEFAULT_PROVIDER_COMBINATIONS
         )
+        metafunc.parametrize("memory_stack", combinations, indirect=True)