sie-chroma

SIE integration for ChromaDB.

Installation

pip install sie-chroma

Features

SIEEmbeddingFunction: Custom embedding function for ChromaDB collections

Quick Start

Basic Usage

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

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:

# 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:

mise run serve -- -d cpu -p 8080

Testing

# Unit tests (no server required)
pytest

# Integration tests (requires running server)
pytest -m integration

Metadata

Release files for sie-chroma 0.9.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sie-chroma 0.9.0
File	Size	Uploaded
sie_chroma-0.9.0.tar.gz	10.9 kB	Sep 30, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for sie-chroma 0.9.0
File	Interpreter	ABI	Platform	Reset
sie_chroma-0.9.0-py3-none-any.whl 4.4 kB Sep 30, 2026	Python 3	none	any	Details

Total release size: 15.3 kB

Release files / sie_chroma-0.9.0.tar.gz

Download URL	sie_chroma-0.9.0.tar.gz
Size	10.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`e21a63674eea434bade6becb2a0c021515534a9b73d167ab09915f45cad714c9`
BLAKE2b-256 checksum How to use checksums	`99ef7d6da1fdf122e5e38935ca25f5a94db1ffbc29226ae82b1be3b675ce67a3`
Upload date	Sep 30, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/superlinked/sie
Publishing commit: github.com/superlinked/sie/tree/2337fad783aeb20d8ae974c287c503820c7d07fa

Workflow

Publishing configuration: github.com/superlinked/sie/blob/2337fad783aeb20d8ae974c287c503820c7d07fa/.github/workflows/release.yml
Publishing logs: github.com/superlinked/sie/actions/runs/36720830955/attempts/1

Artifact

Subject: sie_chroma-0.9.0.tar.gz
SHA-256 checksum: e21a63674eea434bade6becb2a0c021515534a9b73d167ab09915f45cad714c9 Verifying attestations

Release files / sie_chroma-0.9.0-py3-none-any.whl

Download URL	sie_chroma-0.9.0-py3-none-any.whl
Size	4.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`980be50aa494f150ffd8d20ec8968a36c33254143d73b5d7ec5d7b4d643ac474`
BLAKE2b-256 checksum How to use checksums	`3667bbe26f7ccad6d0d511e5350308036d941874bcc546fdb318da969acb34d1`
Upload date	Sep 30, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/superlinked/sie
Publishing commit: github.com/superlinked/sie/tree/2337fad783aeb20d8ae974c287c503820c7d07fa

Workflow

Publishing configuration: github.com/superlinked/sie/blob/2337fad783aeb20d8ae974c287c503820c7d07fa/.github/workflows/release.yml
Publishing logs: github.com/superlinked/sie/actions/runs/36720830955/attempts/1

Artifact

Subject: sie_chroma-0.9.0-py3-none-any.whl
SHA-256 checksum: 980be50aa494f150ffd8d20ec8968a36c33254143d73b5d7ec5d7b4d643ac474 Verifying attestations