Add BM25 hybrid search (dense + sparse vectors with RRF)

- Add SparseTextEmbedding("Qdrant/bm25") to FastEmbedProvider for BM25 tokenization
- Add sparse vector config (IDF modifier) to collection creation
- Store both dense and sparse vectors per document
- Use Qdrant prefetch + Reciprocal Rank Fusion for hybrid search
- Add HYBRID_SEARCH env var (default: false) for backward compatibility

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/mcp_server_qdrant/embeddings/factory.py

@@ -3,15 +3,18 @@ from mcp_server_qdrant.embeddings.types import EmbeddingProviderType
 from mcp_server_qdrant.settings import EmbeddingProviderSettings
 
 
-def create_embedding_provider(settings: EmbeddingProviderSettings) -> EmbeddingProvider:
+def create_embedding_provider(
+    settings: EmbeddingProviderSettings, enable_sparse: bool = False
+) -> EmbeddingProvider:
     """
     Create an embedding provider based on the specified type.
     :param settings: The settings for the embedding provider.
+    :param enable_sparse: Whether to enable sparse (BM25) embeddings.
     :return: An instance of the specified embedding provider.
     """
     if settings.provider_type == EmbeddingProviderType.FASTEMBED:
         from mcp_server_qdrant.embeddings.fastembed import FastEmbedProvider
 
-        return FastEmbedProvider(settings.model_name)
+        return FastEmbedProvider(settings.model_name, enable_sparse=enable_sparse)
     else:
         raise ValueError(f"Unsupported embedding provider: {settings.provider_type}")