sie-qdrant 0.1.8__tar.gz

sie_qdrant-0.1.8/.gitignore

@@ -0,0 +1,256 @@
+# 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
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# 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
+
+# vcscode
+.vscode
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# SIE specific
+# Model weights cache
+.cache/
+*.safetensors
+*.bin
+
+# Secrets (never commit)
+*.pem
+*.key
+credentials.json
+*-key.json
+
+# Terraform
+# Local .terraform directories (cached providers/modules)
+**/.terraform/*
+.terraform.lock*
+# State files (contain sensitive data)
+*.tfstate
+*.tfstate.*
+# Crash log files
+crash.log
+crash.*.log
+# Override files (local developer overrides)
+override.tf
+override.tf.json
+*_override.tf
+*_override.tf.json
+# tfvars files may contain secrets
+*.tfvars
+*.tfvars.json
+# Keep .terraform.lock.hcl for reproducibility (provider versions)
+
+# Node.js
+node_modules/
+
+# OS
+.DS_Store
+Thumbs.db
+
+# VIM
+*.swp
+
+# Worktree metadata
+.base-branch
+
+# Temporary files
+tmp/
+.tmp/
+.local/
+
+.requirements-modal.txt

sie_qdrant-0.1.8/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: sie-qdrant
+Version: 0.1.8
+Summary: SIE integration for Qdrant
+Requires-Python: >=3.10
+Requires-Dist: qdrant-client>=1.7
+Requires-Dist: sie-sdk>=0.1.0
+Provides-Extra: dev
+Requires-Dist: pytest-asyncio>=0.24; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# sie-qdrant
+
+SIE integration for Qdrant.
+
+## Installation
+
+```bash
+pip install sie-qdrant
+```
+
+## Dense embeddings
+
+```python
+from qdrant_client import QdrantClient
+from qdrant_client.models import Distance, VectorParams, PointStruct
+from sie_qdrant import SIEVectorizer
+
+vectorizer = SIEVectorizer(base_url="http://localhost:8080", model="BAAI/bge-m3")
+
+qdrant = QdrantClient("http://localhost:6333")
+qdrant.create_collection(
+    collection_name="documents",
+    vectors_config=VectorParams(size=1024, distance=Distance.COSINE),
+)
+
+texts = ["first doc", "second doc"]
+vectors = vectorizer.embed_documents(texts)
+qdrant.upsert(
+    collection_name="documents",
+    points=[
+        PointStruct(id=i, vector=v, payload={"text": t})
+        for i, (t, v) in enumerate(zip(texts, vectors))
+    ],
+)
+
+query_vec = vectorizer.embed_query("search text")
+results = qdrant.query_points(
+    collection_name="documents", query=query_vec, limit=5
+)
+```
+
+## Named vectors (dense + sparse)
+
+SIE's multi-output encode produces dense and sparse vectors in one call.
+Qdrant supports sparse vectors natively via `SparseVector(indices, values)`,
+so no expansion to full vocabulary length is needed:
+
+```python
+from qdrant_client import QdrantClient
+from qdrant_client.models import (
+    Distance, VectorParams, PointStruct,
+    SparseVectorParams, SparseVector,
+)
+from sie_qdrant import SIENamedVectorizer
+
+vectorizer = SIENamedVectorizer(
+    base_url="http://localhost:8080",
+    model="BAAI/bge-m3",
+    output_types=["dense", "sparse"],
+)
+
+qdrant = QdrantClient("http://localhost:6333")
+qdrant.create_collection(
+    collection_name="documents",
+    vectors_config={"dense": VectorParams(size=1024, distance=Distance.COSINE)},
+    sparse_vectors_config={"sparse": SparseVectorParams()},
+)
+
+named = vectorizer.embed_documents(["hello world"])
+qdrant.upsert(
+    collection_name="documents",
+    points=[
+        PointStruct(
+            id=0,
+            vector={
+                "dense": named[0]["dense"],
+                "sparse": SparseVector(**named[0]["sparse"]),
+            },
+            payload={"text": "hello world"},
+        )
+    ],
+)
+```
+
+**Storage advantage:** Unlike integrations that expand sparse vectors to full
+vocabulary length (~30K floats), Qdrant stores sparse vectors in their native
+indices+values form, making hybrid search storage-efficient.
+
+## Testing
+
+```bash
+# Unit tests (no server needed)
+pytest
+
+# Integration tests (requires SIE + Qdrant)
+pytest -m integration
+```

sie_qdrant-0.1.8/README.md

@@ -0,0 +1,97 @@
+# sie-qdrant
+
+SIE integration for Qdrant.
+
+## Installation
+
+```bash
+pip install sie-qdrant
+```
+
+## Dense embeddings
+
+```python
+from qdrant_client import QdrantClient
+from qdrant_client.models import Distance, VectorParams, PointStruct
+from sie_qdrant import SIEVectorizer
+
+vectorizer = SIEVectorizer(base_url="http://localhost:8080", model="BAAI/bge-m3")
+
+qdrant = QdrantClient("http://localhost:6333")
+qdrant.create_collection(
+    collection_name="documents",
+    vectors_config=VectorParams(size=1024, distance=Distance.COSINE),
+)
+
+texts = ["first doc", "second doc"]
+vectors = vectorizer.embed_documents(texts)
+qdrant.upsert(
+    collection_name="documents",
+    points=[
+        PointStruct(id=i, vector=v, payload={"text": t})
+        for i, (t, v) in enumerate(zip(texts, vectors))
+    ],
+)
+
+query_vec = vectorizer.embed_query("search text")
+results = qdrant.query_points(
+    collection_name="documents", query=query_vec, limit=5
+)
+```
+
+## Named vectors (dense + sparse)
+
+SIE's multi-output encode produces dense and sparse vectors in one call.
+Qdrant supports sparse vectors natively via `SparseVector(indices, values)`,
+so no expansion to full vocabulary length is needed:
+
+```python
+from qdrant_client import QdrantClient
+from qdrant_client.models import (
+    Distance, VectorParams, PointStruct,
+    SparseVectorParams, SparseVector,
+)
+from sie_qdrant import SIENamedVectorizer
+
+vectorizer = SIENamedVectorizer(
+    base_url="http://localhost:8080",
+    model="BAAI/bge-m3",
+    output_types=["dense", "sparse"],
+)
+
+qdrant = QdrantClient("http://localhost:6333")
+qdrant.create_collection(
+    collection_name="documents",
+    vectors_config={"dense": VectorParams(size=1024, distance=Distance.COSINE)},
+    sparse_vectors_config={"sparse": SparseVectorParams()},
+)
+
+named = vectorizer.embed_documents(["hello world"])
+qdrant.upsert(
+    collection_name="documents",
+    points=[
+        PointStruct(
+            id=0,
+            vector={
+                "dense": named[0]["dense"],
+                "sparse": SparseVector(**named[0]["sparse"]),
+            },
+            payload={"text": "hello world"},
+        )
+    ],
+)
+```
+
+**Storage advantage:** Unlike integrations that expand sparse vectors to full
+vocabulary length (~30K floats), Qdrant stores sparse vectors in their native
+indices+values form, making hybrid search storage-efficient.
+
+## Testing
+
+```bash
+# Unit tests (no server needed)
+pytest
+
+# Integration tests (requires SIE + Qdrant)
+pytest -m integration
+```

sie_qdrant-0.1.8/pyproject.toml

@@ -0,0 +1,31 @@
+[project]
+name = "sie-qdrant"
+version = "0.1.8"
+description = "SIE integration for Qdrant"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "sie-sdk>=0.1.0",
+    "qdrant-client>=1.7",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0",
+    "pytest-asyncio>=0.24",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/sie_qdrant"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+asyncio_mode = "auto"
+markers = [
+    "integration: marks tests as integration tests (require running SIE server and Qdrant instance)",
+]
+addopts = "-v --tb=short -m 'not integration'"

sie_qdrant-0.1.8/src/sie_qdrant/__init__.py

@@ -0,0 +1,93 @@
+"""SIE integration for Qdrant.
+
+This package provides vectorizer helpers for Qdrant:
+
+- SIEVectorizer: Compute dense embeddings via SIE for Qdrant collections
+- SIENamedVectorizer: Compute multiple vector types (dense + sparse) for Qdrant named vectors
+
+Qdrant supports both dense and sparse vectors natively. Dense vectors are
+stored as ``list[float]``, and sparse vectors use ``SparseVector(indices, values)``
+— no expansion to full vocabulary length is needed (unlike Weaviate).
+
+Example usage (dense):
+
+    from qdrant_client import QdrantClient
+    from qdrant_client.models import Distance, VectorParams, PointStruct
+    from sie_qdrant import SIEVectorizer
+
+    vectorizer = SIEVectorizer(
+        base_url="http://localhost:8080",
+        model="BAAI/bge-m3",
+    )
+
+    qdrant = QdrantClient("http://localhost:6333")
+    qdrant.create_collection(
+        collection_name="documents",
+        vectors_config=VectorParams(size=1024, distance=Distance.COSINE),
+    )
+
+    # Embed and insert
+    texts = ["first doc", "second doc"]
+    vectors = vectorizer.embed_documents(texts)
+    qdrant.upsert(
+        collection_name="documents",
+        points=[
+            PointStruct(id=i, vector=v, payload={"text": t})
+            for i, (t, v) in enumerate(zip(texts, vectors))
+        ],
+    )
+
+    # Embed query and search
+    query_vector = vectorizer.embed_query("search text")
+    results = qdrant.query_points(
+        collection_name="documents",
+        query=query_vector,
+        limit=5,
+    )
+
+Example usage (named vectors for hybrid search):
+
+    from qdrant_client import QdrantClient
+    from qdrant_client.models import (
+        Distance, VectorParams, PointStruct,
+        SparseVectorParams, SparseVector,
+    )
+    from sie_qdrant import SIENamedVectorizer
+
+    vectorizer = SIENamedVectorizer(
+        base_url="http://localhost:8080",
+        model="BAAI/bge-m3",
+    )
+
+    qdrant = QdrantClient("http://localhost:6333")
+    qdrant.create_collection(
+        collection_name="documents",
+        vectors_config={"dense": VectorParams(size=1024, distance=Distance.COSINE)},
+        sparse_vectors_config={"sparse": SparseVectorParams()},
+    )
+
+    # Embed with both dense and sparse in one SIE call
+    texts = ["first doc", "second doc"]
+    named = vectorizer.embed_documents(texts)
+    qdrant.upsert(
+        collection_name="documents",
+        points=[
+            PointStruct(
+                id=i,
+                vector={
+                    "dense": v["dense"],
+                    "sparse": SparseVector(**v["sparse"]),
+                },
+                payload={"text": t},
+            )
+            for i, (t, v) in enumerate(zip(texts, named))
+        ],
+    )
+"""
+
+from sie_qdrant.vectorizer import SIENamedVectorizer, SIEVectorizer
+
+__all__ = [
+    "SIENamedVectorizer",
+    "SIEVectorizer",
+]