chore: setup unit testing from core

.gitmodules

@@ -1,3 +1,3 @@
 [submodule "embedbase"]
-	path = embedbase
+	path = monorepo
 	url = https://github.com/different-ai/embedbase

.vscode/settings.json

@@ -1,3 +1,6 @@
 {
-    "python.formatting.provider": "black"
+    "python.formatting.provider": "none",
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter"
+    }
 }

Makefile

@@ -3,6 +3,7 @@
 install:
 	poetry lock -n
 	poetry install -n
+
 
 #* Formatters
 .PHONY: codestyle

README.md

@@ -3,3 +3,10 @@
 Embedbase + Qdrant - Advanced and high-performant vector similarity search technology in your AI applications
 
 WIP.
+
+
+pip install git+https://github.com/different-ai/embedbase.git@main#subdirectory=tests
+
+git submodule add https://github.com/different-ai/embedbase embedbase
+
+git submodule update --remote embedbase

conftest.py

@@ -0,0 +1,4 @@
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent / "monorepo"))

pyproject.toml

@@ -2,6 +2,10 @@
 requires = ["poetry_core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
 
+[virtualenvs]
+create = true
+in-project = true
+
 [tool.poetry]
 name = "embedbase-qdrant"
 version = "1.0.0"
@@ -47,6 +51,8 @@ coverage = "^6.1.2"
 coverage-badge = "^1.1.0"
 pytest-html = "^3.1.1"
 pytest-cov = "^4.0.0"
+httpx = "^0.24.0"
+pytest-asyncio = "^0.21.0"
 
 [tool.black]
 target-version = ["py38"]

qdrant_db.py

@@ -1,4 +1,7 @@
 from embedbase.database import VectorDatabase
+from abc import ABC, abstractmethod
+from typing import Coroutine, List, Optional
+from pandas import DataFrame
 
 
 class Qdrant(VectorDatabase):
@@ -9,11 +12,86 @@ def __init__(
         Qdrant is powering the next generation of AI applications with advanced
         and high-performant vector similarity search technology.
 
-        Qdrant is a vector database & vector similarity search engine. 
+        Qdrant is a vector database & vector similarity search engine.
         It deploys as an API service providing search for the nearest high-dimensional vectors.
         With Qdrant, embeddings or neural network encoders can be turned into
         full-fledged applications for matching, searching, recommending, and much more!
         """
         raise NotImplementedError(
             "Qdrant is not yet implemented. Please use another database."
         )
+
+    async def select(
+        self,
+        ids: List[str] = [],
+        hashes: List[str] = [],
+        dataset_id: Optional[str] = None,
+        user_id: Optional[str] = None,
+        distinct: bool = True,
+    ) -> List[dict]:
+        """
+        :param ids: list of ids
+        :param hashes: list of hashes
+        :param dataset_id: dataset id
+        :param user_id: user id
+        :param distinct: distinct
+        :return: list of documents
+        """
+        raise NotImplementedError
+
+    async def update(
+        self,
+        df: DataFrame,
+        dataset_id: str,
+        user_id: Optional[str] = None,
+        batch_size: Optional[int] = 100,
+        store_data: bool = True,
+    ) -> Coroutine:
+        """
+        :param df: dataframe
+        :param dataset_id: dataset id
+        :param user_id: user id
+        :param batch_size: batch size
+        :param store_data: store data in database?
+        """
+        raise NotImplementedError
+
+    async def delete(
+        self, ids: List[str], dataset_id: str, user_id: Optional[str] = None
+    ) -> None:
+        """
+        :param ids: list of ids
+        :param dataset_id: dataset id
+        :param user_id: user id
+        """
+        raise NotImplementedError
+
+    async def search(
+        self,
+        vector: List[float],
+        top_k: Optional[int],
+        dataset_ids: List[str],
+        user_id: Optional[str] = None,
+    ) -> List[dict]:
+        """
+        :param vector: vector
+        :param top_k: top k
+        :param dataset_id: dataset id
+        :param user_id: user id
+        :return: list of documents
+        """
+        raise NotImplementedError
+
+    async def clear(self, dataset_id: str, user_id: Optional[str] = None) -> None:
+        """
+        :param dataset_id: dataset id
+        :param user_id: user id
+        """
+        raise NotImplementedError
+
+    async def get_datasets(self, user_id: Optional[str] = None) -> List[dict]:
+        """
+        :param user_id: user id
+        :return: list of datasets
+        """
+        raise NotImplementedError

test_integration.py

@@ -0,0 +1,8 @@
+from monorepo.tests.test_end_to_end import vector_databases
+from qdrant_db import Qdrant
+
+# override default vector databases with our integration
+vector_databases.clear()
+vector_databases.append(Qdrant())
+
+# poetry run pytest test_integration.py