chore: Enable keyword search for Milvus inline (#3073)

# What does this PR do?
With https://github.com/milvus-io/milvus-lite/pull/294 - Milvus Lite
supports keyword search using BM25. While introducing keyword search we
had explicitly disabled it for inline milvus. This PR removes the need
for the check, and enables `inline::milvus` for tests.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
Run llama stack with `inline::milvus` enabled:

```
pytest tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes --stack-config=http://localhost:8321 --embedding-model=all-MiniLM-L6-v2 -v
```

```
INFO     2025-08-07 17:06:20,932 tests.integration.conftest:64 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS                                        
=========================================================================================== test session starts ============================================================================================
platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.12.11', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}}
rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0
asyncio: mode=Mode.AUTO
collected 3 items                                                                                                                                                                                          

tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-vector] PASSED                                                   [ 33%]
tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-keyword] PASSED                                                  [ 66%]
tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-hybrid] PASSED                                                   [100%]

============================================================================================ 3 passed in 4.75s =============================================================================================
```

Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>

llama_stack/providers/remote/vector_io/milvus/milvus.py

@@ -413,15 +413,6 @@ class MilvusVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolP
         index = await self._get_and_cache_vector_db_index(vector_db_id)
         if not index:
             raise VectorStoreNotFoundError(vector_db_id)
-
-        if params and params.get("mode") == "keyword":
-            # Check if this is inline Milvus (Milvus-Lite)
-            if hasattr(self.config, "db_path"):
-                raise NotImplementedError(
-                    "Keyword search is not supported in Milvus-Lite. "
-                    "Please use a remote Milvus server for keyword search functionality."
-                )
-
         return await index.query_chunks(query, params)
 
     async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:

pyproject.toml

@@ -93,6 +93,7 @@ unit = [
     "blobfile",
     "faiss-cpu",
     "pymilvus>=2.5.12",
+    "milvus-lite>=2.5.0",
     "litellm",
     "together",
     "coverage",
@@ -118,6 +119,7 @@ test = [
     "sqlalchemy[asyncio]>=2.0.41",
     "requests",
     "pymilvus>=2.5.12",
+    "milvus-lite>=2.5.0",
     "weaviate-client>=4.16.4",
 ]
 docs = [

tests/integration/vector_io/test_openai_vector_stores.py

@@ -56,6 +56,7 @@ def skip_if_provider_doesnt_support_openai_vector_stores_search(client_with_mode
         "keyword": [
             "inline::sqlite-vec",
             "remote::milvus",
+            "inline::milvus",
         ],
         "hybrid": [
             "inline::sqlite-vec",

uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 3
+revision = 2
 requires-python = ">=3.12"
 resolution-markers = [
     "(python_full_version >= '3.13' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.13' and sys_platform != 'darwin' and sys_platform != 'linux')",
@@ -1809,6 +1809,7 @@ test = [
     { name = "chardet" },
     { name = "datasets" },
     { name = "mcp" },
+    { name = "milvus-lite" },
     { name = "openai" },
     { name = "pymilvus" },
     { name = "pypdf" },
@@ -1831,6 +1832,7 @@ unit = [
     { name = "faiss-cpu" },
     { name = "litellm" },
     { name = "mcp" },
+    { name = "milvus-lite" },
     { name = "ollama" },
     { name = "openai" },
     { name = "pymilvus" },
@@ -1925,6 +1927,7 @@ test = [
     { name = "chardet" },
     { name = "datasets" },
     { name = "mcp" },
+    { name = "milvus-lite", specifier = ">=2.5.0" },
     { name = "openai" },
     { name = "pymilvus", specifier = ">=2.5.12" },
     { name = "pypdf" },
@@ -1946,6 +1949,7 @@ unit = [
     { name = "faiss-cpu" },
     { name = "litellm" },
     { name = "mcp" },
+    { name = "milvus-lite", specifier = ">=2.5.0" },
     { name = "ollama" },
     { name = "openai" },
     { name = "pymilvus", specifier = ">=2.5.12" },