e9f0a1fa4a
Some checks failed
- 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>
21 lines
919 B
Python
21 lines
919 B
Python
from mcp_server_qdrant.embeddings.base import EmbeddingProvider
|
|
from mcp_server_qdrant.embeddings.types import EmbeddingProviderType
|
|
from mcp_server_qdrant.settings import EmbeddingProviderSettings
|
|
|
|
|
|
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, enable_sparse=enable_sparse)
|
|
else:
|
|
raise ValueError(f"Unsupported embedding provider: {settings.provider_type}")
|