feat: Implement hybrid search in SQLite-vec (#2312)

# What does this PR do?
Add support for hybrid search mode in SQLite-vec provider, which
combines
keyword and vector search for better results. The implementation:

- Adds hybrid search mode as a new option alongside vector and keyword
search
- Implements query_hybrid method in SQLiteVecIndex that:
  - First performs keyword search to get candidate matches
  - Then applies vector similarity search on those candidates
- Updates documentation to reflect the new search mode

This change improves search quality by leveraging both semantic
similarity
and keyword matching, while maintaining backward compatibility with
existing
vector and keyword search modes.

## Test Plan
```
pytest tests/unit/providers/vector_io/test_sqlite_vec.py -v -s --tb=short
/Users/vnarsing/miniconda3/envs/stack-client/lib/python3.10/site-packages/pytest_asyncio/plugin.py:217: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"

  warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
=============================================================================================== test session starts ===============================================================================================
platform darwin -- Python 3.10.16, pytest-8.3.5, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.10.16', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '8.3.5', 'pluggy': '1.5.0'}, 'Plugins': {'html': '4.1.1', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'anyio': '4.8.0', 'asyncio': '0.26.0', 'nbval': '0.11.0', 'cov': '6.1.1'}}
rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack
configfile: pyproject.toml
plugins: html-4.1.1, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, anyio-4.8.0, asyncio-0.26.0, nbval-0.11.0, cov-6.1.1
asyncio: mode=strict, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function
collected 10 items                                                                                                                                                                                                

tests/unit/providers/vector_io/test_sqlite_vec.py::test_add_chunks PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_vector PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_full_text_search PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_hybrid PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_full_text_search_k_greater_than_results PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_chunk_id_conflict PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_generate_chunk_id PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_hybrid_no_keyword_matches PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_hybrid_score_threshold PASSED
tests/unit/providers/vector_io/test_sqlite_vec.py::test_query_chunks_hybrid_different_embedding PASSED
```

---------

Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>

llama_stack/providers/utils/memory/vector_store.py

@@ -32,6 +32,10 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 log = logging.getLogger(__name__)
 
+# Constants for reranker types
+RERANKER_TYPE_RRF = "rrf"
+RERANKER_TYPE_WEIGHTED = "weighted"
+
 
 def parse_pdf(data: bytes) -> str:
     # For PDF and DOC/DOCX files, we can't reliably convert to string
@@ -202,6 +206,18 @@ class EmbeddingIndex(ABC):
     async def query_keyword(self, query_string: str, k: int, score_threshold: float) -> QueryChunksResponse:
         raise NotImplementedError()
 
+    @abstractmethod
+    async def query_hybrid(
+        self,
+        embedding: NDArray,
+        query_string: str,
+        k: int,
+        score_threshold: float,
+        reranker_type: str,
+        reranker_params: dict[str, Any] | None = None,
+    ) -> QueryChunksResponse:
+        raise NotImplementedError()
+
     @abstractmethod
     async def delete(self):
         raise NotImplementedError()
@@ -245,10 +261,29 @@ class VectorDBWithIndex:
         k = params.get("max_chunks", 3)
         mode = params.get("mode")
         score_threshold = params.get("score_threshold", 0.0)
+
+        # Get ranker configuration
+        ranker = params.get("ranker")
+        if ranker is None:
+            # Default to RRF with impact_factor=60.0
+            reranker_type = RERANKER_TYPE_RRF
+            reranker_params = {"impact_factor": 60.0}
+        else:
+            reranker_type = ranker.type
+            reranker_params = (
+                {"impact_factor": ranker.impact_factor} if ranker.type == RERANKER_TYPE_RRF else {"alpha": ranker.alpha}
+            )
+
         query_string = interleaved_content_as_str(query)
         if mode == "keyword":
             return await self.index.query_keyword(query_string, k, score_threshold)
+
+        # Calculate embeddings for both vector and hybrid modes
+        embeddings_response = await self.inference_api.embeddings(self.vector_db.embedding_model, [query_string])
+        query_vector = np.array(embeddings_response.embeddings[0], dtype=np.float32)
+        if mode == "hybrid":
+            return await self.index.query_hybrid(
+                query_vector, query_string, k, score_threshold, reranker_type, reranker_params
+            )
         else:
-            embeddings_response = await self.inference_api.embeddings(self.vector_db.embedding_model, [query_string])
-            query_vector = np.array(embeddings_response.embeddings[0], dtype=np.float32)
             return await self.index.query_vector(query_vector, k, score_threshold)