numpy-vector-store 0.1.0__tar.gz

numpy_vector_store-0.1.0/.github/FUNDING.yml

@@ -0,0 +1,3 @@
+# These are supported funding model platforms
+
+buy_me_a_coffee: tim.vanreenen

numpy_vector_store-0.1.0/.github/workflows/publish-pypi.yml

@@ -0,0 +1,35 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types:
+      - published
+
+jobs:
+  publish-pypi:
+    name: Publish to PyPI
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tooling
+        run: python -m pip install --upgrade build twine
+
+      - name: Build distributions
+        run: python -m build
+
+      - name: Check distribution metadata
+        run: python -m twine check dist/*
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

numpy_vector_store-0.1.0/.github/workflows/publish-testpypi.yml

@@ -0,0 +1,35 @@
+name: Publish to TestPyPI
+
+on:
+  workflow_dispatch:
+
+jobs:
+  publish-testpypi:
+    name: Publish to TestPyPI
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tooling
+        run: python -m pip install --upgrade build twine
+
+      - name: Build distributions
+        run: python -m build
+
+      - name: Check distribution metadata
+        run: python -m twine check dist/*
+
+      - name: Publish package distributions to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/

numpy_vector_store-0.1.0/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

numpy_vector_store-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Tim VanReenen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

numpy_vector_store-0.1.0/PKG-INFO

@@ -0,0 +1,205 @@
+Metadata-Version: 2.4
+Name: numpy-vector-store
+Version: 0.1.0
+Summary: A fast, lightweight, and zero-setup in-memory vector store powered by NumPy
+Project-URL: Homepage, https://github.com/tvanreenen/numpy-vector-store
+Project-URL: Repository, https://github.com/tvanreenen/numpy-vector-store
+Project-URL: Issues, https://github.com/tvanreenen/numpy-vector-store/issues
+Author: Tim VanReenen
+License: MIT
+License-File: LICENSE
+Keywords: embeddings,numpy,search,store,vector
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
+Requires-Dist: numpy>=1.20.0
+Description-Content-Type: text/markdown
+
+# NumPy Vector Store
+
+A fast, lightweight, and zero-setup in-memory vector store powered by NumPy.
+
+- **High-performance** index-free O(n) cosine similarity searches
+- **Vectorized** metadata queries with NumPy operations
+- **Easy persistence** to and from compressed NumPy binary files (.npz)
+- **Zero dependency** on external services or data stores
+
+## Why?
+
+This library is purpose-built for small to medium-scale vector search tasks and offers a simple, lightweight alternative to heavyweight solutions like Pinecone, Qdrant, Weaviate, Postgres + pgvector, or Azure AI Search—no complex setup or infrastructure required.
+
+> Sometimes you don't need a sledgehammer to crack a nut.
+
+## When/Where?
+
+Below are benchmark results for the module's search method to help you assess its suitability for your use case.
+
+| Embedding Type | Dimensions | ~5ms | ~25ms | ~100ms | ~500ms |
+|----------------|------------|------|-------|--------|--------|
+| **Sentence Transformers** | 384 | 1K vectors<br/>1.5MB | 10K vectors<br/>15MB | 100K vectors<br/>147MB | 500K vectors<br/>732MB |
+| **OpenAI Small** | 1536 | 500 vectors<br/>3MB | 5K vectors<br/>29MB | 25K vectors<br/>147MB | 100K vectors<br/>586MB |
+| **OpenAI Large** | 3072 | 200 vectors<br/>2MB | 2.5K vectors<br/>29MB | 5K vectors<br/>59MB | 25K vectors<br/>293MB |
+
+*Benchmarks performed on Apple M2 hardware*
+
+## Installation
+
+**⚠️ Pending submission to PyPI**
+
+```bash
+uv add numpy-vector-store
+```
+
+## Quick Start
+
+```python
+import numpy as np
+from numpy_vector_store import VectorStore
+
+# Load your vector store
+store = VectorStore(dimensions=1536, file_path='vectors.npz')
+store.load()
+
+# Embed your search query
+query = np.array([0.2, 0.3, 0.4, ...])
+
+# Search using cosine similarity
+results = store.search(query, top_k=3)
+
+# Compare the results
+for index, similarity, meta in results:
+    print(f"{meta['title']}: {similarity:.3f}")
+```
+
+## Usage Examples
+
+### Adding Vectors
+
+#### Adding Vectors in Batch
+
+The `add_vectors` method takes a **2D NumPy array** where each row is a vector, and a **1D NumPy array** of metadata objects.
+
+```python
+# 2D np.array of vectors
+embeddings = np.array([
+    [0.1, 0.2, 0.3, ...],  # Text embedding 1
+    [0.4, 0.5, 0.6, ...],  # Text embedding 2
+    [0.7, 0.8, 0.9, ...]   # Text embedding 3
+])
+
+# 1D np.array of metadata objects
+metadata = np.array([
+    {"title": "AI Overview", "word_count": 12},
+    {"title": "Python Guide", "word_count": 10},
+    {"title": "Vector DBs", "word_count": 8}
+])
+
+# Vectors and metadata added using efficient vectorized NumPy operations
+store.add_vectors(embeddings, metadata)
+```
+
+#### Adding Vectors Individually
+
+Batch operations are generally preferable and more efficient. But individual vectors can be added with the same method.
+
+```python
+store.add_vectors(
+    np.array([new_embedding]), # or np.atleast_2d(new_embedding)
+    np.array([{"title": "Neural Networks Paper", "word_count": 15}])
+)
+```
+
+### Save the Vector Store
+
+Save to a gzip compressed NumPy binary file directly
+
+```python
+store.save()
+```
+
+Or use context manager for automatic persistence
+
+```python
+with VectorStore(dimensions=3, file_path="vectors.npz") as store:
+    store.add_vectors(vectors_2d, metadata_array)
+
+# Automatically saves when exiting the context
+```
+
+### Working with Metadata
+
+Work with flexible, unstructured metadata using standard Python operations. No schema required - perfect for getting started quickly:
+
+```python
+# Access individual metadata
+first_metadata = store.metadata[0]
+print(f"First entry: {first_metadata}")
+
+# Iterate through all metadata
+for i, metadata in enumerate(store.metadata):
+    print(f"Entry {i}: {metadata}")
+```
+
+### Advanced: Structured Metadata for Performance
+
+If you define a homogeneous NumPy schema upfront, you get **significant performance improvements** for metadata operations. Instead of Python loops and dictionary lookups, you get **vectorized NumPy operations** that are orders of magnitude faster.
+
+> **Learn more**: [NumPy Structured Arrays Documentation](https://numpy.org/doc/stable/user/basics.rec.html)
+
+```python
+# Define schema for performance
+store = VectorStore(
+    dimensions=512,
+    metadata_schema={'title': 'U200', 'year': 'i4', 'citations': 'i4'}
+)
+store.add_vectors(
+    np.array([vector1, vector2]),
+    np.array([
+        {"title": "Paper 1", "year": 2023, "citations": 100},
+        {"title": "Paper 2", "year": 2022, "citations": 50}
+    ])
+)
+
+# Perform vectorized NumPy operations on metadata
+recent_mask = store.metadata['year'] == 2023
+recent_vectors = np.array(store.vectors)[recent_mask]
+
+# Sort by citations
+sorted_indices = np.argsort(store.metadata['citations'])[::-1]
+top_vectors = np.array(store.vectors)[sorted_indices]
+
+# Complex filtering
+high_impact = store.metadata['citations'] > 100
+recent = store.metadata['year'] > 2020
+combined_mask = high_impact & recent
+filtered_vectors = np.array(store.vectors)[combined_mask]
+```
+
+## Contributing
+
+### Setup Development Environment
+
+```bash
+git clone https://github.com/tvanreenen/numpy-vector-store.git
+cd numpy-vector-store
+uv sync --frozen --group dev
+```
+
+### Before Submitting a Pull Request
+
+Please ensure:
+
+1. **Code Quality**: Run `uv run ruff check` - should show no issues
+2. **Formatting**: Run `uv run ruff format` - should show "files left unchanged"
+3. **Type Checking**: Run `uv run mypy src/` - should show no errors
+4. **Tests**: Run `uv run pytest` - all tests should pass
+
+## License
+
+MIT License - see [LICENSE](LICENSE) file for details.

numpy_vector_store-0.1.0/README.md

@@ -0,0 +1,182 @@
+# NumPy Vector Store
+
+A fast, lightweight, and zero-setup in-memory vector store powered by NumPy.
+
+- **High-performance** index-free O(n) cosine similarity searches
+- **Vectorized** metadata queries with NumPy operations
+- **Easy persistence** to and from compressed NumPy binary files (.npz)
+- **Zero dependency** on external services or data stores
+
+## Why?
+
+This library is purpose-built for small to medium-scale vector search tasks and offers a simple, lightweight alternative to heavyweight solutions like Pinecone, Qdrant, Weaviate, Postgres + pgvector, or Azure AI Search—no complex setup or infrastructure required.
+
+> Sometimes you don't need a sledgehammer to crack a nut.
+
+## When/Where?
+
+Below are benchmark results for the module's search method to help you assess its suitability for your use case.
+
+| Embedding Type | Dimensions | ~5ms | ~25ms | ~100ms | ~500ms |
+|----------------|------------|------|-------|--------|--------|
+| **Sentence Transformers** | 384 | 1K vectors<br/>1.5MB | 10K vectors<br/>15MB | 100K vectors<br/>147MB | 500K vectors<br/>732MB |
+| **OpenAI Small** | 1536 | 500 vectors<br/>3MB | 5K vectors<br/>29MB | 25K vectors<br/>147MB | 100K vectors<br/>586MB |
+| **OpenAI Large** | 3072 | 200 vectors<br/>2MB | 2.5K vectors<br/>29MB | 5K vectors<br/>59MB | 25K vectors<br/>293MB |
+
+*Benchmarks performed on Apple M2 hardware*
+
+## Installation
+
+**⚠️ Pending submission to PyPI**
+
+```bash
+uv add numpy-vector-store
+```
+
+## Quick Start
+
+```python
+import numpy as np
+from numpy_vector_store import VectorStore
+
+# Load your vector store
+store = VectorStore(dimensions=1536, file_path='vectors.npz')
+store.load()
+
+# Embed your search query
+query = np.array([0.2, 0.3, 0.4, ...])
+
+# Search using cosine similarity
+results = store.search(query, top_k=3)
+
+# Compare the results
+for index, similarity, meta in results:
+    print(f"{meta['title']}: {similarity:.3f}")
+```
+
+## Usage Examples
+
+### Adding Vectors
+
+#### Adding Vectors in Batch
+
+The `add_vectors` method takes a **2D NumPy array** where each row is a vector, and a **1D NumPy array** of metadata objects.
+
+```python
+# 2D np.array of vectors
+embeddings = np.array([
+    [0.1, 0.2, 0.3, ...],  # Text embedding 1
+    [0.4, 0.5, 0.6, ...],  # Text embedding 2
+    [0.7, 0.8, 0.9, ...]   # Text embedding 3
+])
+
+# 1D np.array of metadata objects
+metadata = np.array([
+    {"title": "AI Overview", "word_count": 12},
+    {"title": "Python Guide", "word_count": 10},
+    {"title": "Vector DBs", "word_count": 8}
+])
+
+# Vectors and metadata added using efficient vectorized NumPy operations
+store.add_vectors(embeddings, metadata)
+```
+
+#### Adding Vectors Individually
+
+Batch operations are generally preferable and more efficient. But individual vectors can be added with the same method.
+
+```python
+store.add_vectors(
+    np.array([new_embedding]), # or np.atleast_2d(new_embedding)
+    np.array([{"title": "Neural Networks Paper", "word_count": 15}])
+)
+```
+
+### Save the Vector Store
+
+Save to a gzip compressed NumPy binary file directly
+
+```python
+store.save()
+```
+
+Or use context manager for automatic persistence
+
+```python
+with VectorStore(dimensions=3, file_path="vectors.npz") as store:
+    store.add_vectors(vectors_2d, metadata_array)
+
+# Automatically saves when exiting the context
+```
+
+### Working with Metadata
+
+Work with flexible, unstructured metadata using standard Python operations. No schema required - perfect for getting started quickly:
+
+```python
+# Access individual metadata
+first_metadata = store.metadata[0]
+print(f"First entry: {first_metadata}")
+
+# Iterate through all metadata
+for i, metadata in enumerate(store.metadata):
+    print(f"Entry {i}: {metadata}")
+```
+
+### Advanced: Structured Metadata for Performance
+
+If you define a homogeneous NumPy schema upfront, you get **significant performance improvements** for metadata operations. Instead of Python loops and dictionary lookups, you get **vectorized NumPy operations** that are orders of magnitude faster.
+
+> **Learn more**: [NumPy Structured Arrays Documentation](https://numpy.org/doc/stable/user/basics.rec.html)
+
+```python
+# Define schema for performance
+store = VectorStore(
+    dimensions=512,
+    metadata_schema={'title': 'U200', 'year': 'i4', 'citations': 'i4'}
+)
+store.add_vectors(
+    np.array([vector1, vector2]),
+    np.array([
+        {"title": "Paper 1", "year": 2023, "citations": 100},
+        {"title": "Paper 2", "year": 2022, "citations": 50}
+    ])
+)
+
+# Perform vectorized NumPy operations on metadata
+recent_mask = store.metadata['year'] == 2023
+recent_vectors = np.array(store.vectors)[recent_mask]
+
+# Sort by citations
+sorted_indices = np.argsort(store.metadata['citations'])[::-1]
+top_vectors = np.array(store.vectors)[sorted_indices]
+
+# Complex filtering
+high_impact = store.metadata['citations'] > 100
+recent = store.metadata['year'] > 2020
+combined_mask = high_impact & recent
+filtered_vectors = np.array(store.vectors)[combined_mask]
+```
+
+## Contributing
+
+### Setup Development Environment
+
+```bash
+git clone https://github.com/tvanreenen/numpy-vector-store.git
+cd numpy-vector-store
+uv sync --frozen --group dev
+```
+
+### Before Submitting a Pull Request
+
+Please ensure:
+
+1. **Code Quality**: Run `uv run ruff check` - should show no issues
+2. **Formatting**: Run `uv run ruff format` - should show "files left unchanged"
+3. **Type Checking**: Run `uv run mypy src/` - should show no errors
+4. **Tests**: Run `uv run pytest` - all tests should pass
+
+## License
+
+MIT License - see [LICENSE](LICENSE) file for details.

numpy_vector_store-0.1.0/justfile

@@ -0,0 +1,4 @@
+# Clean build artifacts and cache directories
+clean:
+    rm -rf .venv .pytest_cache .ruff_cache .mypy_cache .coverage htmlcov ssl
+    find . -name "__pycache__" -type d -exec rm -rf {} + 2>/dev/null || true