fix: delete and add test

.github/workflows/test.yml

@@ -0,0 +1,56 @@
+name: test
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+    paths-ignore:
+      - '**/*.md'
+      - '**/*.ipynb'
+      - 'examples/**'
+  pull_request:
+    branches:
+      - main
+      - dev
+    paths-ignore:
+      - '**/*.md'
+      - '**/*.ipynb'
+      - 'examples/**'
+
+jobs:
+  test:
+    name: Tests on ${{ matrix.os }} for ${{ matrix.python-version }}
+    strategy:
+      matrix:
+        python-version: [3.9, 3.11]
+        os: [ubuntu-latest, windows-latest]
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install -r requirements-dev.txt
+      - name: Lint with flake8
+        run: |
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+      - name: Build and Test
+        run: |
+          python -m pytest -o log_cli=true -o log_cli_level="INFO" --cov=nano_vectordb --cov-report=xml -v ./
+      - name: Check codecov file
+        id: check_files
+        uses: andstor/file-existence-action@v1
+        with:
+          files: './coverage.xml'
+      - name: Upload coverage from test to Codecov
+        uses: codecov/codecov-action@v2
+        with:
+          file: ./coverage.xml
+          token: ${{ secrets.CODECOV_TOKEN }}

nano_vectordb/__init__.py

@@ -1,5 +1,5 @@
 from .dbs import NanoVectorDB
 
-__version__ = "0.0.2"
+__version__ = "0.0.3"
 __author__ = "Jianbai Ye"
 __url__ = "https://github.com/gusye1234/nano-vectordb"

nano_vectordb/dbs.py

@@ -119,8 +119,6 @@ def delete(self, ids: list[str]):
             if data[f_ID] in ids:
                 delete_index.append(i)
                 ids.remove(data[f_ID])
-                if len(ids) == 0:
-                    break
             else:
                 left_data.append(data)
         self.__storage["data"] = left_data
@@ -136,6 +134,9 @@ def save(self):
         with open(self.storage_file, "w") as f:
             json.dump(storage, f, ensure_ascii=False)
 
+    def __len__(self):
+        return len(self.__storage["data"])
+
     def query(
         self, query: np.ndarray, top_k: int = 10, better_than_threshold: float = None
     ):

requirements-dev.txt

@@ -1 +1,3 @@
-pytest
+pytest
+pytest-cov
+flake8

tests/test_init.py

@@ -23,9 +23,8 @@ def test_init():
     a = NanoVectorDB(fake_dim)
 
     start = time()
-    r = a.query(np.random.rand(fake_dim), 10)
+    r = a.query(np.random.rand(fake_dim), 10, better_than_threshold=0.01)
     print("Query", time() - start)
-    assert len(r) > 0
     print(r)
     os.remove("nano-vectordb.json")
 
@@ -47,3 +46,33 @@ def test_same_upsert():
     fakes_data = [{"__vector__": fake_embeds[i]} for i in range(data_len)]
     r2 = a.upsert(fakes_data)
     assert r2["update"] == r1["insert"]
+
+
+def test_get():
+    a = NanoVectorDB(1024)
+    a.upsert(
+        [
+            {"__vector__": np.random.rand(1024), "__id__": str(i), "content": i}
+            for i in range(100)
+        ]
+    )
+    r = a.get(["0", "1", "2"])
+    assert len(r) == 3
+    assert r[0]["content"] == 0
+    assert r[1]["content"] == 1
+    assert r[2]["content"] == 2
+
+
+def test_delete():
+    a = NanoVectorDB(1024)
+    a.upsert(
+        [
+            {"__vector__": np.random.rand(1024), "__id__": str(i), "content": i}
+            for i in range(100)
+        ]
+    )
+    a.delete(["0", "50", "99"])
+
+    r = a.get(["0", "50", "99"])
+    assert len(r) == 0
+    assert len(a) == 97