sqlitesearch 0.0.1__tar.gz

sqlitesearch-0.0.1/.github/workflows/tests.yml

@@ -0,0 +1,38 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12', '3.13']
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install uv
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
+
+      - name: Install dependencies
+        run: uv sync --dev
+
+      - name: Run tests with coverage
+        run: uv run pytest --cov=sqlitesearch --cov-report=xml --cov-report=term-missing
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          file: ./coverage.xml
+          fail_ci_if_error: false

sqlitesearch-0.0.1/.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__/

sqlitesearch-0.0.1/CLAUDE.md

@@ -0,0 +1,68 @@
+## CRITICAL: File Editing on Windows
+
+### ⚠️ MANDATORY: Always Use Backslashes on Windows for File Paths
+
+When using Edit or MultiEdit tools on Windows, you MUST use backslashes (`\`) in file paths, NOT forward slashes (`/`).
+
+❌ WRONG - Will cause errors:
+```
+Edit(file_path: "D:/repos/project/file.tsx", ...)
+MultiEdit(file_path: "D:/repos/project/file.tsx", ...)
+```
+
+✅ CORRECT - Always works:
+```
+Edit(file_path: "D:\repos\project\file.tsx", ...)
+MultiEdit(file_path: "D:\repos\project\file.tsx", ...)
+```
+
+### ⚠️ "File has been unexpectedly modified" Error
+
+If you get this error: **"File has been unexpectedly modified. Read it again before attempting to write it"**
+
+**Root cause:** The file was modified after you last read it (by linter, formatter, git, or external process).
+
+**Solution: Re-read the file immediately before editing:**
+
+```bash
+# 1. Read the file again
+Read(file_path: "path\to\file.txt")
+
+# 2. Then immediately edit
+Edit(file_path: "path\to\file.txt", old_string="...", new_string="...")
+```
+
+**Tool requirements:**
+
+- Edit - Must `Read` immediately before - `old_string` must match current content
+- Write - Must `Read` once per conversation before first write
+
+**Common triggers:**
+- Linters/formatters running on save
+- Git operations (checkout, merge, rebase)
+- File watchers or build processes
+
+**Tip:** If this happens repeatedly, consider disabling auto-formatting for files you're actively editing with Claude Code.
+
+### ⚠️ Use UV for Python Package Management
+
+When installing Python packages, use `uv` instead of `pip`. See `/uv` for details.
+
+❌ WRONG:
+```bash
+pip install djangorestframework
+```
+
+✅ CORRECT:
+```bash
+cd backend-django
+uv add djangorestframework
+```
+
+Run Django commands:
+```bash
+cd backend-django
+uv run python manage.py makemigrations
+uv run python manage.py migrate
+uv run python manage.py test
+```

sqlitesearch-0.0.1/Makefile

@@ -0,0 +1,25 @@
+.PHONY: test setup shell coverage publish-build publish-test publish publish-clean
+
+test:
+	uv run pytest
+
+coverage:
+	uv run pytest --cov=sqlitesearch --cov-report=term-missing --cov-report=html
+
+setup:
+	uv sync --dev
+
+shell:
+	uv shell
+
+publish-build:
+	uv run hatch build
+
+publish-test:
+	uv run hatch publish --repo test
+
+publish:
+	uv run hatch publish
+
+publish-clean:
+	rm -r dist/

sqlitesearch-0.0.1/PKG-INFO

@@ -0,0 +1,200 @@
+Metadata-Version: 2.4
+Name: sqlitesearch
+Version: 0.0.1
+Summary: A tiny, SQLite-backed search library for small, local projects
+Author: sqlitesearch contributors
+License: MIT
+Keywords: fts,hybrid-search,lsh,search,sqlite,vector-search
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Requires-Dist: numpy>=1.24.0
+Description-Content-Type: text/markdown
+
+# sqlitesearch
+
+A tiny, SQLite-backed search library for small, local projects. sqlitesearch is a persistent sibling of [minsearch](https://github.com/alexeygrigorev/minsearch) - same API, but stores data on disk.
+
+
+sqlitesearch provides
+
+- text search using SQLite FTS5 and persistent
+- vector search using LSH (random projections) with exact reranking
+- hybrid search (Todo explain)
+
+It stores the index in a single SQLite file, making it perfect for applications
+that need search functionality without running a separate search server.
+
+## When to use
+
+- minsearch - in-memory, for experiments and notebooks
+- sqlitesearch - persistent (SQLite file), for pet projects and prototypes
+- Postgres/Elasticsearch/Qdrant/etc - production workloads with high traffic
+
+
+## Installation
+
+```bash
+uv add sqlitesearch
+```
+
+## Text Search
+
+Text search uses SQLite's FTS5 (Full-Text Search) extension with BM25 ranking.
+
+### Basic usage
+
+```python
+from sqlitesearch import TextSearchIndex
+
+# Create an index
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    keyword_fields=["category"],
+    db_path="search.db"
+)
+
+# Index some documents
+documents = [
+    {"id": 1, "title": "Python Tutorial", "description": "Learn Python basics", "category": "tutorial"},
+    {"id": 2, "title": "Java Guide", "description": "Java programming guide", "category": "guide"},
+]
+index.fit(documents)
+
+# Search
+results = index.search("python programming")
+for result in results:
+    print(result["title"], result["score"])
+```
+
+### Filtering
+
+```python
+# Filter by keyword fields
+results = index.search(
+    "python",
+    filter_dict={"category": "tutorial"}
+)
+```
+
+### Field boosting
+
+```python
+# Boost title matches higher than description
+results = index.search(
+    "python",
+    boost_dict={"title": 2.0, "description": 1.0}
+)
+```
+
+### Stemming
+
+Enable Porter stemming for better matching of word variants:
+
+```python
+# With stemming, "running" matches "run", "courses" matches "course", etc.
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    stemming=True,
+    db_path="search.db"
+)
+```
+
+By default, stemming is disabled to match minsearch behavior.
+
+### Adding documents
+
+```python
+# Add documents one by one
+index.add({
+    "id": 3,
+    "title": "Advanced Python",
+    "description": "Deep dive into Python",
+    "category": "tutorial"
+})
+```
+
+### Custom ID field
+
+```python
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    id_field="doc_id",
+    db_path="search.db"
+)
+
+results = index.search("python", output_ids=True)
+# Results will include 'id' field with the doc_id value
+```
+
+## Vector Search
+
+Vector search uses Locality-Sensitive Hashing (LSH) with random projections
+for fast approximate nearest neighbor search, followed by exact cosine
+similarity reranking.
+
+### Basic usage
+
+```python
+import numpy as np
+from sqlitesearch import VectorSearchIndex
+
+# Create an index
+index = VectorSearchIndex(
+    keyword_fields=["category"],
+    n_tables=8,      # Number of hash tables (more = better recall)
+    hash_size=16,    # Bits per hash (more = better precision)
+    db_path="vectors.db"
+)
+
+# Index vectors with documents
+vectors = np.random.rand(100, 384)  # 100 documents, 384 dimensions
+documents = [{"category": "test"} for _ in range(100)]
+index.fit(vectors, documents)
+
+# Search
+query = np.random.rand(384)
+results = index.search(query)
+```
+
+### Filtering
+
+```python
+results = index.search(
+    query,
+    filter_dict={"category": "test"}
+)
+```
+
+## Persistence
+
+Both index types automatically persist to disk. You can reopen an existing index:
+
+```python
+# Open existing index
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    db_path="search.db"
+)
+# Ready to search immediately
+```
+
+## Clearing the index
+
+```python
+index.clear()  # Remove all documents
+```
+
+## API Compatibility
+
+The API is designed to match minsearch for easy migration:
+
+- `fit(docs)` - Index documents (only if index is empty)
+- `add(doc)` - Add a single document
+- `search(query, filter_dict=None, boost_dict=None, num_results=10)` - Search

sqlitesearch-0.0.1/README.md

@@ -0,0 +1,181 @@
+# sqlitesearch
+
+A tiny, SQLite-backed search library for small, local projects. sqlitesearch is a persistent sibling of [minsearch](https://github.com/alexeygrigorev/minsearch) - same API, but stores data on disk.
+
+
+sqlitesearch provides
+
+- text search using SQLite FTS5 and persistent
+- vector search using LSH (random projections) with exact reranking
+- hybrid search (Todo explain)
+
+It stores the index in a single SQLite file, making it perfect for applications
+that need search functionality without running a separate search server.
+
+## When to use
+
+- minsearch - in-memory, for experiments and notebooks
+- sqlitesearch - persistent (SQLite file), for pet projects and prototypes
+- Postgres/Elasticsearch/Qdrant/etc - production workloads with high traffic
+
+
+## Installation
+
+```bash
+uv add sqlitesearch
+```
+
+## Text Search
+
+Text search uses SQLite's FTS5 (Full-Text Search) extension with BM25 ranking.
+
+### Basic usage
+
+```python
+from sqlitesearch import TextSearchIndex
+
+# Create an index
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    keyword_fields=["category"],
+    db_path="search.db"
+)
+
+# Index some documents
+documents = [
+    {"id": 1, "title": "Python Tutorial", "description": "Learn Python basics", "category": "tutorial"},
+    {"id": 2, "title": "Java Guide", "description": "Java programming guide", "category": "guide"},
+]
+index.fit(documents)
+
+# Search
+results = index.search("python programming")
+for result in results:
+    print(result["title"], result["score"])
+```
+
+### Filtering
+
+```python
+# Filter by keyword fields
+results = index.search(
+    "python",
+    filter_dict={"category": "tutorial"}
+)
+```
+
+### Field boosting
+
+```python
+# Boost title matches higher than description
+results = index.search(
+    "python",
+    boost_dict={"title": 2.0, "description": 1.0}
+)
+```
+
+### Stemming
+
+Enable Porter stemming for better matching of word variants:
+
+```python
+# With stemming, "running" matches "run", "courses" matches "course", etc.
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    stemming=True,
+    db_path="search.db"
+)
+```
+
+By default, stemming is disabled to match minsearch behavior.
+
+### Adding documents
+
+```python
+# Add documents one by one
+index.add({
+    "id": 3,
+    "title": "Advanced Python",
+    "description": "Deep dive into Python",
+    "category": "tutorial"
+})
+```
+
+### Custom ID field
+
+```python
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    id_field="doc_id",
+    db_path="search.db"
+)
+
+results = index.search("python", output_ids=True)
+# Results will include 'id' field with the doc_id value
+```
+
+## Vector Search
+
+Vector search uses Locality-Sensitive Hashing (LSH) with random projections
+for fast approximate nearest neighbor search, followed by exact cosine
+similarity reranking.
+
+### Basic usage
+
+```python
+import numpy as np
+from sqlitesearch import VectorSearchIndex
+
+# Create an index
+index = VectorSearchIndex(
+    keyword_fields=["category"],
+    n_tables=8,      # Number of hash tables (more = better recall)
+    hash_size=16,    # Bits per hash (more = better precision)
+    db_path="vectors.db"
+)
+
+# Index vectors with documents
+vectors = np.random.rand(100, 384)  # 100 documents, 384 dimensions
+documents = [{"category": "test"} for _ in range(100)]
+index.fit(vectors, documents)
+
+# Search
+query = np.random.rand(384)
+results = index.search(query)
+```
+
+### Filtering
+
+```python
+results = index.search(
+    query,
+    filter_dict={"category": "test"}
+)
+```
+
+## Persistence
+
+Both index types automatically persist to disk. You can reopen an existing index:
+
+```python
+# Open existing index
+index = TextSearchIndex(
+    text_fields=["title", "description"],
+    db_path="search.db"
+)
+# Ready to search immediately
+```
+
+## Clearing the index
+
+```python
+index.clear()  # Remove all documents
+```
+
+## API Compatibility
+
+The API is designed to match minsearch for easy migration:
+
+- `fit(docs)` - Index documents (only if index is empty)
+- `add(doc)` - Add a single document
+- `search(query, filter_dict=None, boost_dict=None, num_results=10)` - Search