sie-chroma 0.1.7__tar.gz

sie_chroma-0.1.7/.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_chroma-0.1.7/PKG-INFO

@@ -0,0 +1,138 @@
+Metadata-Version: 2.4
+Name: sie-chroma
+Version: 0.1.7
+Summary: SIE integration for ChromaDB
+Requires-Python: >=3.10
+Requires-Dist: chromadb>=0.4
+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-chroma
+
+SIE integration for [ChromaDB](https://www.trychroma.com/).
+
+## Installation
+
+```bash
+pip install sie-chroma
+```
+
+## Features
+
+- **SIEEmbeddingFunction**: Custom embedding function for ChromaDB collections
+
+## Quick Start
+
+### Basic Usage
+
+```python
+import chromadb
+from sie_chroma import SIEEmbeddingFunction
+
+# Create SIE embedding function
+embedding_function = SIEEmbeddingFunction(
+    base_url="http://localhost:8080",
+    model="BAAI/bge-m3",
+)
+
+# Create ChromaDB client and collection
+client = chromadb.Client()
+collection = client.create_collection(
+    name="my_collection",
+    embedding_function=embedding_function,
+)
+
+# Add documents (embeddings are generated automatically)
+collection.add(
+    documents=[
+        "Machine learning enables pattern recognition.",
+        "Deep learning uses neural networks.",
+        "Natural language processing analyzes text.",
+    ],
+    ids=["doc1", "doc2", "doc3"],
+)
+
+# Query the collection
+results = collection.query(
+    query_texts=["What is deep learning?"],
+    n_results=2,
+)
+print(results["documents"])
+```
+
+### With Persistent Storage
+
+```python
+import chromadb
+from sie_chroma import SIEEmbeddingFunction
+
+# Persistent client
+client = chromadb.PersistentClient(path="./chroma_data")
+
+embedding_function = SIEEmbeddingFunction(
+    base_url="http://localhost:8080",
+    model="BAAI/bge-m3",
+)
+
+# Get or create collection
+collection = client.get_or_create_collection(
+    name="research_papers",
+    embedding_function=embedding_function,
+)
+
+# Add documents with metadata
+collection.add(
+    documents=["Paper about transformers...", "Study on attention mechanisms..."],
+    metadatas=[{"year": 2023}, {"year": 2024}],
+    ids=["paper1", "paper2"],
+)
+
+# Query with metadata filtering
+results = collection.query(
+    query_texts=["attention in neural networks"],
+    n_results=5,
+    where={"year": {"$gte": 2023}},
+)
+```
+
+### With LangChain or LlamaIndex
+
+The SIEEmbeddingFunction works with ChromaDB's LangChain and LlamaIndex integrations:
+
+```python
+# LangChain
+from langchain_chroma import Chroma
+from sie_chroma import SIEEmbeddingFunction
+
+embedding_function = SIEEmbeddingFunction(model="BAAI/bge-m3")
+vectorstore = Chroma(
+    collection_name="docs",
+    embedding_function=embedding_function,  # Works directly!
+)
+
+# LlamaIndex
+from llama_index.vector_stores.chroma import ChromaVectorStore
+
+# SIE can also be used via LlamaIndex's SIEEmbedding
+```
+
+## SIE Server
+
+Start the SIE server before using this integration:
+
+```bash
+mise run serve -d cpu -p 8080
+```
+
+## Testing
+
+```bash
+# Unit tests (no server required)
+pytest
+
+# Integration tests (requires running server)
+pytest -m integration
+```

sie_chroma-0.1.7/README.md

@@ -0,0 +1,126 @@
+# sie-chroma
+
+SIE integration for [ChromaDB](https://www.trychroma.com/).
+
+## Installation
+
+```bash
+pip install sie-chroma
+```
+
+## Features
+
+- **SIEEmbeddingFunction**: Custom embedding function for ChromaDB collections
+
+## Quick Start
+
+### Basic Usage
+
+```python
+import chromadb
+from sie_chroma import SIEEmbeddingFunction
+
+# Create SIE embedding function
+embedding_function = SIEEmbeddingFunction(
+    base_url="http://localhost:8080",
+    model="BAAI/bge-m3",
+)
+
+# Create ChromaDB client and collection
+client = chromadb.Client()
+collection = client.create_collection(
+    name="my_collection",
+    embedding_function=embedding_function,
+)
+
+# Add documents (embeddings are generated automatically)
+collection.add(
+    documents=[
+        "Machine learning enables pattern recognition.",
+        "Deep learning uses neural networks.",
+        "Natural language processing analyzes text.",
+    ],
+    ids=["doc1", "doc2", "doc3"],
+)
+
+# Query the collection
+results = collection.query(
+    query_texts=["What is deep learning?"],
+    n_results=2,
+)
+print(results["documents"])
+```
+
+### With Persistent Storage
+
+```python
+import chromadb
+from sie_chroma import SIEEmbeddingFunction
+
+# Persistent client
+client = chromadb.PersistentClient(path="./chroma_data")
+
+embedding_function = SIEEmbeddingFunction(
+    base_url="http://localhost:8080",
+    model="BAAI/bge-m3",
+)
+
+# Get or create collection
+collection = client.get_or_create_collection(
+    name="research_papers",
+    embedding_function=embedding_function,
+)
+
+# Add documents with metadata
+collection.add(
+    documents=["Paper about transformers...", "Study on attention mechanisms..."],
+    metadatas=[{"year": 2023}, {"year": 2024}],
+    ids=["paper1", "paper2"],
+)
+
+# Query with metadata filtering
+results = collection.query(
+    query_texts=["attention in neural networks"],
+    n_results=5,
+    where={"year": {"$gte": 2023}},
+)
+```
+
+### With LangChain or LlamaIndex
+
+The SIEEmbeddingFunction works with ChromaDB's LangChain and LlamaIndex integrations:
+
+```python
+# LangChain
+from langchain_chroma import Chroma
+from sie_chroma import SIEEmbeddingFunction
+
+embedding_function = SIEEmbeddingFunction(model="BAAI/bge-m3")
+vectorstore = Chroma(
+    collection_name="docs",
+    embedding_function=embedding_function,  # Works directly!
+)
+
+# LlamaIndex
+from llama_index.vector_stores.chroma import ChromaVectorStore
+
+# SIE can also be used via LlamaIndex's SIEEmbedding
+```
+
+## SIE Server
+
+Start the SIE server before using this integration:
+
+```bash
+mise run serve -d cpu -p 8080
+```
+
+## Testing
+
+```bash
+# Unit tests (no server required)
+pytest
+
+# Integration tests (requires running server)
+pytest -m integration
+```

sie_chroma-0.1.7/pyproject.toml

@@ -0,0 +1,31 @@
+[project]
+name = "sie-chroma"
+version = "0.1.7"
+description = "SIE integration for ChromaDB"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "sie-sdk>=0.1.0",
+    "chromadb>=0.4",
+]
+
+[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_chroma"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+asyncio_mode = "auto"
+markers = [
+    "integration: marks tests as integration tests (require running SIE server)",
+]
+addopts = "-v --tb=short -m 'not integration'"

sie_chroma-0.1.7/src/sie_chroma/__init__.py

@@ -0,0 +1,45 @@
+"""SIE integration for ChromaDB.
+
+This package provides embedding functions for ChromaDB:
+
+- SIEEmbeddingFunction: Dense embeddings for standard ChromaDB collections
+- SIESparseEmbeddingFunction: Sparse embeddings for Chroma Cloud hybrid search
+
+Example usage (dense):
+
+    import chromadb
+    from sie_chroma import SIEEmbeddingFunction
+
+    embedding_function = SIEEmbeddingFunction(
+        base_url="http://localhost:8080",
+        model="BAAI/bge-m3",
+    )
+
+    client = chromadb.Client()
+    collection = client.create_collection(
+        name="my_collection",
+        embedding_function=embedding_function,
+    )
+
+    collection.add(
+        documents=["doc1", "doc2"],
+        ids=["id1", "id2"],
+    )
+
+Example usage (sparse for hybrid search with Chroma Cloud):
+
+    from sie_chroma import SIESparseEmbeddingFunction
+
+    sparse_ef = SIESparseEmbeddingFunction(
+        base_url="http://localhost:8080",
+        model="BAAI/bge-m3",
+    )
+    # Use with SparseVectorIndexConfig for hybrid search
+"""
+
+from sie_chroma.embedding_function import SIEEmbeddingFunction, SIESparseEmbeddingFunction
+
+__all__ = [
+    "SIEEmbeddingFunction",
+    "SIESparseEmbeddingFunction",
+]