qdrant-haystack 0.0.4__py3-none-any.whl → 0.0.5__py3-none-any.whl

qdrant_haystack/document_stores/qdrant.py

@@ -37,6 +37,7 @@ class QdrantDocumentStore(BaseDocumentStore):
 
     def __init__(
         self,
+        location: Optional[str] = None,
         url: Optional[str] = None,
         port: int = 6333,
         grpc_port: int = 6334,
@@ -46,6 +47,7 @@ class QdrantDocumentStore(BaseDocumentStore):
         prefix: Optional[str] = None,
         timeout: Optional[float] = None,
         host: Optional[str] = None,
+        path: Optional[str] = None,
         index: str = "Document",
         embedding_dim: int = 768,
         hnsw_config: Optional[Dict] = None,
@@ -62,6 +64,7 @@ class QdrantDocumentStore(BaseDocumentStore):
         super().__init__()
 
         self.client = qdrant_client.QdrantClient(
+            location=location,
             url=url,
             port=port,
             grpc_port=grpc_port,
@@ -71,6 +74,7 @@ class QdrantDocumentStore(BaseDocumentStore):
             prefix=prefix,
             timeout=timeout,
             host=host,
+            path=path,
             **kwargs,
         )
 
@@ -165,10 +169,11 @@ class QdrantDocumentStore(BaseDocumentStore):
 
         next_offset = None
         stop_scrolling = False
+        scroll_filter = self.qdrant_filter_converter.convert(None, ids)
         while not stop_scrolling:
             records, next_offset = self.client.scroll(
                 collection_name=index,
-                scroll_filter=self.qdrant_filter_converter.convert(None, ids),
+                scroll_filter=scroll_filter,
                 limit=batch_size,
                 offset=next_offset,
                 with_payload=True,
@@ -201,7 +206,10 @@ class QdrantDocumentStore(BaseDocumentStore):
                 count_filter=qdrant_filters,
             )
             return response.count
-        except UnexpectedResponse:
+        except (UnexpectedResponse, ValueError):
+            # Qdrant local raises ValueError if the collection is not found, but
+            # with the remote server UnexpectedResponse is raised. Until that's unified,
+            # we need to catch both.
             return 0
 
     def get_embedding_count(
@@ -490,30 +498,36 @@ class QdrantDocumentStore(BaseDocumentStore):
             # Check if the collection already exists and validate its
             # current configuration with the parameters.
             collection_info = self.client.get_collection(collection_name)
-            current_distance = collection_info.config.params.vectors.distance
-            current_vector_size = collection_info.config.params.vectors.size
-
-            if current_distance != distance:
-                raise ValueError(
-                    f"Collection '{collection_name}' already exists in Qdrant, "
-                    f"but it is configured with a similarity '{current_distance.name}'. "
-                    f"If you want to use that collection, but with a different "
-                    f"similarity, please set `recreate_collection=True` argument."
-                )
-
-            if current_vector_size != embedding_dim:
-                raise ValueError(
-                    f"Collection '{collection_name}' already exists in Qdrant, "
-                    f"but it is configured with a vector size '{current_vector_size}'. "
-                    f"If you want to use that collection, but with a different "
-                    f"vector size, please set `recreate_collection=True` argument."
-                )
-        except (UnexpectedResponse, _InactiveRpcError):
+        except (UnexpectedResponse, _InactiveRpcError, ValueError):
             # That indicates the collection does not exist, so it can be
             # safely created with any configuration.
+            #
+            # Qdrant local raises ValueError if the collection is not found, but
+            # with the remote server UnexpectedResponse / _InactiveRpcError is raised.
+            # Until that's unified, we need to catch both.
             self._recreate_collection(
                 collection_name, distance, embedding_dim, hnsw_config
             )
+            return
+
+        current_distance = collection_info.config.params.vectors.distance
+        current_vector_size = collection_info.config.params.vectors.size
+
+        if current_distance != distance:
+            raise ValueError(
+                f"Collection '{collection_name}' already exists in Qdrant, "
+                f"but it is configured with a similarity '{current_distance.name}'. "
+                f"If you want to use that collection, but with a different "
+                f"similarity, please set `recreate_collection=True` argument."
+            )
+
+        if current_vector_size != embedding_dim:
+            raise ValueError(
+                f"Collection '{collection_name}' already exists in Qdrant, "
+                f"but it is configured with a vector size '{current_vector_size}'. "
+                f"If you want to use that collection, but with a different "
+                f"vector size, please set `recreate_collection=True` argument."
+            )
 
     def _recreate_collection(
         self, collection_name, distance, embedding_dim, hnsw_config

{qdrant_haystack-0.0.4.dist-info → qdrant_haystack-0.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qdrant-haystack
-Version: 0.0.4
+Version: 0.0.5
 Summary: An integration of Qdrant ANN vector database backend with Haystack
 License: Apache 2.0
 Author: Kacper Łukawski
@@ -12,7 +12,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: farm-haystack (>=1.13.0,<2.0.0)
-Requires-Dist: qdrant-client (>=1.0.2,<2.0.0)
+Requires-Dist: qdrant-client (>=1.1.2,<2.0.0)
 Description-Content-Type: text/markdown
 
 # qdrant-haystack
@@ -45,7 +45,7 @@ embeddings.
 from qdrant_haystack import QdrantDocumentStore
 
 document_store = QdrantDocumentStore(
-    url="localhost",
+    "localhost",
     index="Document",
     embedding_dim=512,
     recreate_index=True,
@@ -56,6 +56,51 @@ document_store = QdrantDocumentStore(
 The list of parameters accepted by `QdrantDocumentStore` is complementary to those used in the
 official [Python Qdrant client](https://github.com/qdrant/qdrant_client).
 
+### Using local in-memory / disk-persisted mode
+
+Qdrant Python client, from version 1.1.1, supports local in-memory/disk-persisted mode. That's
+a good choice for any test scenarios and quick experiments in which you do not plan to store
+lots of vectors. In such a case spinning a Docker container might be even not required.
+
+The local mode was also implemented in `qdrant-haystack` integration.
+
+#### In-memory storage
+
+In case you want to have a transient storage, for example in case of automated tests launched
+during your CI/CD pipeline, using Qdrant Local mode with in-memory storage might be a preferred
+option. It might be simply enabled by passing `:memory:` as first parameter, while creating an
+instance of `QdrantDocumentStore`.
+
+```python
+from qdrant_haystack import QdrantDocumentStore
+
+document_store = QdrantDocumentStore(
+    ":memory:",
+    index="Document",
+    embedding_dim=512,
+    recreate_index=True,
+    hnsw_config={"m": 16, "ef_construct": 64}  # Optional
+)
+```
+
+#### On disk storage
+
+However, if you prefer to keep the vectors between different runs of your application, it
+might be better to use on disk storage and pass the path that should be used to persist
+the data.
+
+```python
+from qdrant_haystack import QdrantDocumentStore
+
+document_store = QdrantDocumentStore(
+    path="/home/qdrant/storage_local",
+    index="Document",
+    embedding_dim=512,
+    recreate_index=True,
+    hnsw_config={"m": 16, "ef_construct": 64}  # Optional
+)
+```
+
 ### Connecting to Qdrant Cloud cluster
 
 If you prefer not to manage your own Qdrant instance, [Qdrant Cloud](https://cloud.qdrant.io/)
@@ -65,7 +110,7 @@ might be a better option.
 from qdrant_haystack import QdrantDocumentStore
 
 document_store = QdrantDocumentStore(
-    url="https://YOUR-CLUSTER-URL.aws.cloud.qdrant.io",
+    "https://YOUR-CLUSTER-URL.aws.cloud.qdrant.io",
     index="Document",
     api_key="<< YOUR QDRANT CLOUD API KEY >>",
     embedding_dim=512,

{qdrant_haystack-0.0.4.dist-info → qdrant_haystack-0.0.5.dist-info}/RECORD

@@ -2,9 +2,9 @@ qdrant_haystack/__init__.py,sha256=F7uhTaB7pul_sbPyBQNYIz5eTOVCW5f9qF3FjiN8CRM,1
 qdrant_haystack/document_stores/__init__.py,sha256=RbJ_JV8mXcmWI9LrHj0gPPEokPfoKGi6zFwkpXvHsjA,107
 qdrant_haystack/document_stores/converters.py,sha256=UkmoK2AMS_zEUy2C9B-04DdMdL0KxANB5d7QBOySzY0,2285
 qdrant_haystack/document_stores/filters.py,sha256=lZumUKgAz1vlWkI0x2jqITDaHDGkth8n3bw1uXTqmjM,8295
-qdrant_haystack/document_stores/qdrant.py,sha256=kwQACKRDGOQ29x9MwTj5RRj7bRNliUeYYnlN26Fxpk8,18456
+qdrant_haystack/document_stores/qdrant.py,sha256=hekVs25mnqHcjId9buWzlr7aIsMIq1YjkZbGEQrm3Uw,19054
 qdrant_haystack/utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-qdrant_haystack-0.0.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-qdrant_haystack-0.0.4.dist-info/METADATA,sha256=__Q-cDKSu-hVJfAX4yX8sWQZEs3vp6ldNGprt3G3cyo,2333
-qdrant_haystack-0.0.4.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-qdrant_haystack-0.0.4.dist-info/RECORD,,
+qdrant_haystack-0.0.5.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+qdrant_haystack-0.0.5.dist-info/METADATA,sha256=LVmmp970YdLGka5aLH-ycUMttzzbr8bpjH83iJUgiDg,3797
+qdrant_haystack-0.0.5.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+qdrant_haystack-0.0.5.dist-info/RECORD,,