cognee-community-vector-adapter-qdrant 0.0.2__tar.gz → 0.0.3__tar.gz

cognee_community_vector_adapter_qdrant-0.0.3/PKG-INFO

@@ -0,0 +1,52 @@
+Metadata-Version: 2.3
+Name: cognee-community-vector-adapter-qdrant
+Version: 0.0.3
+Summary: Qdrant vector database adapter for cognee
+Requires-Python: >=3.11,<=3.13
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: cognee (>=0.2.4)
+Requires-Dist: qdrant-client (>=1.14.2)
+Description-Content-Type: text/markdown
+
+# Cognee Qdrant Adapter
+
+## Installation
+
+If published, the package can be simply installed via pip:
+
+```bash
+pip install cognee-community-vector-adapter-qdrant
+```
+
+In case it is not published yet, you can use poetry to locally build the adapter package:
+
+```bash
+pip install poetry
+poetry install # run this command in the directory containing the pyproject.toml file
+```
+
+## Connection Setup
+
+For a quick local setup, you can run a docker container that qdrant provides (https://qdrant.tech/documentation/quickstart/). 
+After this, you will be able to connect to the Qdrant DB through the appropriate ports. The command for running the docker 
+container looks something like the following:
+
+```
+docker run -p 6333:6333 -p 6334:6334 \
+    -v "$(pwd)/qdrant_storage:/qdrant/storage:z" \
+    qdrant/qdrant
+```
+
+## Usage
+
+Import and register the adapter in your code:
+```python
+from cognee_community_vector_adapter_qdrant import register
+```
+
+## Example
+See example in `example.py` file.
+

cognee_community_vector_adapter_qdrant-0.0.3/README.md

@@ -0,0 +1,38 @@
+# Cognee Qdrant Adapter
+
+## Installation
+
+If published, the package can be simply installed via pip:
+
+```bash
+pip install cognee-community-vector-adapter-qdrant
+```
+
+In case it is not published yet, you can use poetry to locally build the adapter package:
+
+```bash
+pip install poetry
+poetry install # run this command in the directory containing the pyproject.toml file
+```
+
+## Connection Setup
+
+For a quick local setup, you can run a docker container that qdrant provides (https://qdrant.tech/documentation/quickstart/). 
+After this, you will be able to connect to the Qdrant DB through the appropriate ports. The command for running the docker 
+container looks something like the following:
+
+```
+docker run -p 6333:6333 -p 6334:6334 \
+    -v "$(pwd)/qdrant_storage:/qdrant/storage:z" \
+    qdrant/qdrant
+```
+
+## Usage
+
+Import and register the adapter in your code:
+```python
+from cognee_community_vector_adapter_qdrant import register
+```
+
+## Example
+See example in `example.py` file.

{cognee_community_vector_adapter_qdrant-0.0.2 → cognee_community_vector_adapter_qdrant-0.0.3}/cognee_community_vector_adapter_qdrant/__init__.py

@@ -1,3 +1,3 @@
 from .qdrant_adapter import QDrantAdapter
 
-__all__ = ["QDrantAdapter"] 
+__all__ = ["QDrantAdapter"]

{cognee_community_vector_adapter_qdrant-0.0.2 → cognee_community_vector_adapter_qdrant-0.0.3}/cognee_community_vector_adapter_qdrant/qdrant_adapter.py

@@ -2,14 +2,16 @@ import asyncio
 from typing import Dict, List, Optional
 from qdrant_client import AsyncQdrantClient, models
 
-from cognee.exceptions import InvalidValueError
 from cognee.shared.logging_utils import get_logger
 
 from cognee.infrastructure.engine import DataPoint
 from cognee.infrastructure.engine.utils import parse_id
+from cognee.infrastructure.databases.exceptions import MissingQueryParameterError
 from cognee.infrastructure.databases.vector import VectorDBInterface
 from cognee.infrastructure.databases.vector.models.ScoredResult import ScoredResult
-from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
+from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import (
+    EmbeddingEngine,
+)
 from cognee.infrastructure.databases.vector.exceptions import CollectionNotFoundError
 
 logger = get_logger("QDrantAdapter")
@@ -21,7 +23,6 @@ class IndexSchema(DataPoint):
     metadata: dict = {"index_fields": ["text"]}
 
 
-
 def create_hnsw_config(hnsw_config: Dict):
     if hnsw_config is not None:
         return models.HnswConfig()
@@ -46,7 +47,9 @@ class QDrantAdapter(VectorDBInterface):
     api_key: str = None
     qdrant_path: str = None
 
-    def __init__(self, url, api_key, embedding_engine: EmbeddingEngine, qdrant_path=None):
+    def __init__(
+        self, url, api_key, embedding_engine: EmbeddingEngine, qdrant_path=None
+    ):
         self.embedding_engine = embedding_engine
 
         if qdrant_path is not None:
@@ -86,14 +89,17 @@ class QDrantAdapter(VectorDBInterface):
                     collection_name=collection_name,
                     vectors_config={
                         "text": models.VectorParams(
-                            size=self.embedding_engine.get_vector_size(), distance="Cosine"
+                            size=self.embedding_engine.get_vector_size(),
+                            distance="Cosine",
                         )
                     },
                 )
 
             await client.close()
 
-    async def create_data_points(self, collection_name: str, data_points: List[DataPoint]):
+    async def create_data_points(
+        self, collection_name: str, data_points: List[DataPoint]
+    ):
         from qdrant_client.http.exceptions import UnexpectedResponse
 
         client = self.get_qdrant_client()
@@ -145,7 +151,9 @@ class QDrantAdapter(VectorDBInterface):
 
     async def retrieve(self, collection_name: str, data_point_ids: list[str]):
         client = self.get_qdrant_client()
-        results = await client.retrieve(collection_name, data_point_ids, with_payload=True)
+        results = await client.retrieve(
+            collection_name, data_point_ids, with_payload=True
+        )
         await client.close()
         return results
 
@@ -160,7 +168,7 @@ class QDrantAdapter(VectorDBInterface):
         from qdrant_client.http.exceptions import UnexpectedResponse
 
         if query_text is None and query_vector is None:
-            raise InvalidValueError(message="One of query_text or query_vector must be provided!")
+            raise MissingQueryParameterError()
 
         if not await self.has_collection(collection_name):
             return []
@@ -172,6 +180,9 @@ class QDrantAdapter(VectorDBInterface):
             client = self.get_qdrant_client()
             if limit == 0:
                 collection_size = await client.count(collection_name=collection_name)
+                limit = collection_size.count
+            if limit == 0:
+                return []
 
             results = await client.search(
                 collection_name=collection_name,
@@ -181,7 +192,7 @@ class QDrantAdapter(VectorDBInterface):
                     if query_vector is not None
                     else (await self.embed_data([query_text]))[0],
                 ),
-                limit=limit if limit > 0 else collection_size.count,
+                limit=limit,
                 with_vectors=with_vector,
             )
 
@@ -236,11 +247,16 @@ class QDrantAdapter(VectorDBInterface):
         client = self.get_qdrant_client()
 
         # Perform batch search with the dynamically generated requests
-        results = await client.search_batch(collection_name=collection_name, requests=requests)
+        results = await client.search_batch(
+            collection_name=collection_name, requests=requests
+        )
 
         await client.close()
 
-        return [filter(lambda result: result.score > 0.9, result_group) for result_group in results]
+        return [
+            filter(lambda result: result.score > 0.9, result_group)
+            for result_group in results
+        ]
 
     async def delete_data_points(self, collection_name: str, data_point_ids: list[str]):
         client = self.get_qdrant_client()

{cognee_community_vector_adapter_qdrant-0.0.2 → cognee_community_vector_adapter_qdrant-0.0.3}/pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "cognee-community-vector-adapter-qdrant"
-version = "0.0.2"
+version = "0.0.3"
 description = "Qdrant vector database adapter for cognee"
 readme = "README.md"
 requires-python = ">=3.11,<=3.13"
 dependencies = [
     "qdrant-client>=1.14.2",
-    "cognee>=0.2.1",
+    "cognee>=0.2.4",
 ]

cognee_community_vector_adapter_qdrant-0.0.2/PKG-INFO

@@ -1,28 +0,0 @@
-Metadata-Version: 2.3
-Name: cognee-community-vector-adapter-qdrant
-Version: 0.0.2
-Summary: Qdrant vector database adapter for cognee
-Requires-Python: >=3.11,<=3.13
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: cognee (>=0.2.1)
-Requires-Dist: qdrant-client (>=1.14.2)
-Description-Content-Type: text/markdown
-
-# Cognee Qdrant Adapter
-
-## Install
-
-Install [`qdrant-client`](https://pypi.org/project/qdrant-client/) in your project.
-
-Put this line of code somewhere at the start of the execution, before cognee is initiated.
-
-```python
-import packages.vector.qdrant.register
-```
-
-## Example
-See example in `example.py` file.
-

cognee_community_vector_adapter_qdrant-0.0.2/README.md

@@ -1,14 +0,0 @@
-# Cognee Qdrant Adapter
-
-## Install
-
-Install [`qdrant-client`](https://pypi.org/project/qdrant-client/) in your project.
-
-Put this line of code somewhere at the start of the execution, before cognee is initiated.
-
-```python
-import packages.vector.qdrant.register
-```
-
-## Example
-See example in `example.py` file.