qdrant-haystack 8.1.0__py3-none-any.whl → 9.1.0__py3-none-any.whl

haystack_integrations/components/retrievers/qdrant/retriever.py

@@ -169,6 +169,50 @@ class QdrantEmbeddingRetriever:
 
         return {"documents": docs}
 
+    @component.output_types(documents=List[Document])
+    async def run_async(
+        self,
+        query_embedding: List[float],
+        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
+        top_k: Optional[int] = None,
+        scale_score: Optional[bool] = None,
+        return_embedding: Optional[bool] = None,
+        score_threshold: Optional[float] = None,
+        group_by: Optional[str] = None,
+        group_size: Optional[int] = None,
+    ):
+        """
+        Asynchronously run the Embedding Retriever on the given input data.
+
+        :param query_embedding: Embedding of the query.
+        :param filters: A dictionary with filters to narrow down the search space.
+        :param top_k: The maximum number of documents to return. If using `group_by` parameters, maximum number of
+             groups to return.
+        :param scale_score: Whether to scale the scores of the retrieved documents or not.
+        :param return_embedding: Whether to return the embedding of the retrieved Documents.
+        :param score_threshold: A minimal score threshold for the result.
+        :param group_by: Payload field to group by, must be a string or number field. If the field contains more than 1
+            value, all values will be used for grouping. One point can be in multiple groups.
+        :param group_size: Maximum amount of points to return per group. Default is 3.
+        :returns:
+            The retrieved documents.
+
+        """
+        filters = apply_filter_policy(self._filter_policy, self._filters, filters)
+
+        docs = await self._document_store._query_by_embedding_async(
+            query_embedding=query_embedding,
+            filters=filters,
+            top_k=top_k or self._top_k,
+            scale_score=scale_score or self._scale_score,
+            return_embedding=return_embedding or self._return_embedding,
+            score_threshold=score_threshold or self._score_threshold,
+            group_by=group_by or self._group_by,
+            group_size=group_size or self._group_size,
+        )
+
+        return {"documents": docs}
+
 
 @component
 class QdrantSparseEmbeddingRetriever:
@@ -336,6 +380,55 @@ class QdrantSparseEmbeddingRetriever:
 
         return {"documents": docs}
 
+    @component.output_types(documents=List[Document])
+    async def run_async(
+        self,
+        query_sparse_embedding: SparseEmbedding,
+        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
+        top_k: Optional[int] = None,
+        scale_score: Optional[bool] = None,
+        return_embedding: Optional[bool] = None,
+        score_threshold: Optional[float] = None,
+        group_by: Optional[str] = None,
+        group_size: Optional[int] = None,
+    ):
+        """
+        Asynchronously run the Sparse Embedding Retriever on the given input data.
+
+        :param query_sparse_embedding: Sparse Embedding of the query.
+        :param filters: Filters applied to the retrieved Documents. The way runtime filters are applied depends on
+                        the `filter_policy` chosen at retriever initialization. See init method docstring for more
+                        details.
+        :param top_k: The maximum number of documents to return. If using `group_by` parameters, maximum number of
+             groups to return.
+        :param scale_score: Whether to scale the scores of the retrieved documents or not.
+        :param return_embedding: Whether to return the embedding of the retrieved Documents.
+        :param score_threshold: A minimal score threshold for the result.
+            Score of the returned result might be higher or smaller than the threshold
+             depending on the Distance function used.
+            E.g. for cosine similarity only higher scores will be returned.
+        :param group_by: Payload field to group by, must be a string or number field. If the field contains more than 1
+            value, all values will be used for grouping. One point can be in multiple groups.
+        :param group_size: Maximum amount of points to return per group. Default is 3.
+        :returns:
+            The retrieved documents.
+
+        """
+        filters = apply_filter_policy(self._filter_policy, self._filters, filters)
+
+        docs = await self._document_store._query_by_sparse_async(
+            query_sparse_embedding=query_sparse_embedding,
+            filters=filters,
+            top_k=top_k or self._top_k,
+            scale_score=scale_score or self._scale_score,
+            return_embedding=return_embedding or self._return_embedding,
+            score_threshold=score_threshold or self._score_threshold,
+            group_by=group_by or self._group_by,
+            group_size=group_size or self._group_size,
+        )
+
+        return {"documents": docs}
+
 
 @component
 class QdrantHybridRetriever:
@@ -501,3 +594,52 @@ class QdrantHybridRetriever:
         )
 
         return {"documents": docs}
+
+    @component.output_types(documents=List[Document])
+    async def run_async(
+        self,
+        query_embedding: List[float],
+        query_sparse_embedding: SparseEmbedding,
+        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
+        top_k: Optional[int] = None,
+        return_embedding: Optional[bool] = None,
+        score_threshold: Optional[float] = None,
+        group_by: Optional[str] = None,
+        group_size: Optional[int] = None,
+    ):
+        """
+        Asynchronously run the Sparse Embedding Retriever on the given input data.
+
+        :param query_embedding: Dense embedding of the query.
+        :param query_sparse_embedding: Sparse embedding of the query.
+        :param filters: Filters applied to the retrieved Documents. The way runtime filters are applied depends on
+                        the `filter_policy` chosen at retriever initialization. See init method docstring for more
+                        details.
+        :param top_k: The maximum number of documents to return. If using `group_by` parameters, maximum number of
+             groups to return.
+        :param return_embedding: Whether to return the embedding of the retrieved Documents.
+        :param score_threshold: A minimal score threshold for the result.
+            Score of the returned result might be higher or smaller than the threshold
+             depending on the Distance function used.
+            E.g. for cosine similarity only higher scores will be returned.
+        :param group_by: Payload field to group by, must be a string or number field. If the field contains more than 1
+             value, all values will be used for grouping. One point can be in multiple groups.
+        :param group_size: Maximum amount of points to return per group. Default is 3.
+        :returns:
+            The retrieved documents.
+
+        """
+        filters = apply_filter_policy(self._filter_policy, self._filters, filters)
+
+        docs = await self._document_store._query_hybrid_async(
+            query_embedding=query_embedding,
+            query_sparse_embedding=query_sparse_embedding,
+            filters=filters,
+            top_k=top_k or self._top_k,
+            return_embedding=return_embedding or self._return_embedding,
+            score_threshold=score_threshold or self._score_threshold,
+            group_by=group_by or self._group_by,
+            group_size=group_size or self._group_size,
+        )
+
+        return {"documents": docs}

haystack_integrations/document_stores/qdrant/converters.py

@@ -1,7 +1,7 @@
-import logging
 import uuid
 from typing import List, Union
 
+from haystack import logging
 from haystack.dataclasses import Document
 from qdrant_client.http import models as rest
 
@@ -23,14 +23,6 @@ def convert_haystack_documents_to_qdrant_points(
     for document in documents:
         payload = document.to_dict(flatten=False)
 
-        if payload.pop("dataframe", None):
-            logger.warning(
-                "Document %s has the `dataframe` field set,"
-                "QdrantDocumentStore no longer supports dataframes and this field will be ignored. "
-                "The `dataframe` field will soon be removed from Haystack Document.",
-                document.id,
-            )
-
         if use_sparse_embeddings:
             vector = {}
 
@@ -73,14 +65,6 @@ def convert_qdrant_point_to_haystack_document(point: QdrantPoint, use_sparse_emb
     payload = {**point.payload}
     payload["score"] = point.score if hasattr(point, "score") else None
 
-    if payload.pop("dataframe", None):
-        logger.warning(
-            "Document %s has the `dataframe` field set,"
-            "QdrantDocumentStore no longer supports dataframes and this field will be ignored. "
-            "The `dataframe` field will soon be removed from Haystack Document.",
-            payload["id"],
-        )
-
     if not use_sparse_embeddings:
         payload["embedding"] = point.vector if hasattr(point, "vector") else None
     elif hasattr(point, "vector") and point.vector is not None: