# MOSS - Minimal On-Device Semantic Search
`inferedge-moss` enables **private, on-device semantic search** in your Python applications with cloud storage capabilities.
Built for developers who want **instant, memory-efficient, privacy-first AI features** with seamless cloud integration.
## ✨ Features
- ⚡ **On-Device Vector Search** - Sub-millisecond retrieval with zero network latency
- 🔍 **Semantic Search & Hybrid Search** - Beyond keyword matching
- ☁️ **Cloud Storage Integration** - Automatic index synchronization with cloud storage
- 📦 **Multi-Index Support** - Manage multiple isolated search spaces
- 🛡️ **Privacy-First by Design** - Computation happens locally, only indexes sync to cloud
- 🚀 **High-Performance Rust Core** - Built on optimized Rust bindings for maximum speed
## 📦 Installation
```bash
pip install inferedge-moss
```
## 🚀 Quick Start
```python
import asyncio
from inferedge_moss import MossClient
from moss import DocumentInfo
async def main():
# Initialize search client with project credentials
client = MossClient("your-project-id", "your-project-key")
# Prepare documents to index
documents = [
DocumentInfo(
id="doc1",
text="How do I track my order? You can track your order by logging into your account.",
metadata={"category": "shipping"}
),
DocumentInfo(
id="doc2",
text="What is your return policy? We offer a 30-day return policy for most items.",
metadata={"category": "returns"}
),
DocumentInfo(
id="doc3",
text="How can I change my shipping address? Contact our customer service team.",
metadata={"category": "support"}
)
]
# Create an index with documents (syncs to cloud)
index_name = "faqs"
await client.create_index(index_name, documents, "moss-minilm")
print("Index created and synced to cloud!")
# Load the index (from cloud or local cache)
await client.load_index(index_name)
# Search the index
result = await client.query(
index_name,
"How do I return a damaged product?",
3 # top 3 results
)
# Display results
print(f"Query: {result.query}")
for doc in result.docs:
print(f"Score: {doc.score:.4f}")
print(f"ID: {doc.id}")
print(f"Text: {doc.text}")
print("---")
asyncio.run(main())
```
## 🔥 Example Use Cases
- Smart knowledge base search with cloud backup
- Realtime Voice AI agents with persistent indexes
- Personal note-taking search with sync across devices
- Private in-app AI features with cloud storage
- Local semantic search in edge devices with cloud fallback
## Available Models
- `moss-minilm`: Lightweight model optimized for speed and efficiency
- `moss-mediumlm`: Balanced model offering higher accuracy with reasonable performance
## 🔧 Getting Started
### Prerequisites
- Python 3.8 or higher
- Valid InferEdge project credentials
### Environment Setup
1. **Install the package:**
```bash
pip install inferedge-moss
```
2. **Get your credentials:**
Sign up at [InferEdge Platform](https://platform.inferedge.dev) to get your `project_id` and `project_key`.
3. **Set up environment variables (optional):**
```bash
export MOSS_PROJECT_ID="your-project-id"
export MOSS_PROJECT_KEY="your-project-key"
```
### Basic Usage
```python
import asyncio
from inferedge_moss import MossClient
from moss import DocumentInfo
async def main():
# Initialize client
client = MossClient("your-project-id", "your-project-key")
# Create and populate an index
documents = [
DocumentInfo(id="1", text="Python is a programming language"),
DocumentInfo(id="2", text="Machine learning with Python is popular"),
]
await client.create_index("my-docs", documents, "moss-minilm")
await client.load_index("my-docs")
# Search
results = await client.query("my-docs", "programming language")
for doc in results.docs:
print(f"{doc.id}: {doc.text} (score: {doc.score:.3f})")
asyncio.run(main())
```
## 📚 API Reference
### MossClient
#### `MossClient(project_id: str, project_key: str)`
Initialize the client with your InferEdge project credentials.
#### `create_index(index_name: str, docs: List[DocumentInfo], model_id: str) -> bool`
Create a new search index with documents. The index is automatically synced to cloud storage.
#### `load_index(index_name: str) -> str`
Load an index from cloud storage or local cache for querying.
#### `query(index_name: str, query: str, top_k: int = 5) -> SearchResult`
Search for similar documents using semantic similarity.
#### `add_docs(index_name: str, docs: List[DocumentInfo]) -> Dict[str, int]`
Add new documents to an existing index.
#### `list_indexes() -> List[IndexInfo]`
Get all available indexes in your project.
## 🛠️ Development
For development setup, contributing guidelines, and technical documentation, see [SETUP.md](./SETUP.md).
## 📄 License
This package is licensed under the [PolyForm Shield License 1.0.0](./LICENSE).
- ✅ Free for testing, evaluation, internal use, and modifications.
- ❌ Not permitted for production or competing commercial use.
- 📩 For commercial licenses, contact: <contact@inferedge.dev>
## 📬 Contact
For support, commercial licensing, or partnership inquiries, contact us: [contact@inferedge.dev](mailto:contact@inferedge.dev)
Raw data
{
"_id": null,
"home_page": null,
"name": "inferedge-moss",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "search, semantic, embeddings, vector, inferedge",
"author": null,
"author_email": "\"InferEdge Inc.\" <contact@inferedge.dev>",
"download_url": "https://files.pythonhosted.org/packages/33/07/d7ce489eb7740d198096e7180b335824e1860fb80aa0f8ef3dea9e885a87/inferedge_moss-1.0.0b3.tar.gz",
"platform": null,
"description": "# MOSS - Minimal On-Device Semantic Search\n\n`inferedge-moss` enables **private, on-device semantic search** in your Python applications with cloud storage capabilities.\n\nBuilt for developers who want **instant, memory-efficient, privacy-first AI features** with seamless cloud integration.\n\n## \u2728 Features\n\n- \u26a1 **On-Device Vector Search** - Sub-millisecond retrieval with zero network latency\n- \ud83d\udd0d **Semantic Search & Hybrid Search** - Beyond keyword matching\n- \u2601\ufe0f **Cloud Storage Integration** - Automatic index synchronization with cloud storage\n- \ud83d\udce6 **Multi-Index Support** - Manage multiple isolated search spaces\n- \ud83d\udee1\ufe0f **Privacy-First by Design** - Computation happens locally, only indexes sync to cloud\n- \ud83d\ude80 **High-Performance Rust Core** - Built on optimized Rust bindings for maximum speed\n\n## \ud83d\udce6 Installation\n\n```bash\npip install inferedge-moss\n```\n\n## \ud83d\ude80 Quick Start\n\n```python\nimport asyncio\nfrom inferedge_moss import MossClient\nfrom moss import DocumentInfo\n\nasync def main():\n # Initialize search client with project credentials\n client = MossClient(\"your-project-id\", \"your-project-key\")\n\n # Prepare documents to index\n documents = [\n DocumentInfo(\n id=\"doc1\",\n text=\"How do I track my order? You can track your order by logging into your account.\",\n metadata={\"category\": \"shipping\"}\n ),\n DocumentInfo(\n id=\"doc2\", \n text=\"What is your return policy? We offer a 30-day return policy for most items.\",\n metadata={\"category\": \"returns\"}\n ),\n DocumentInfo(\n id=\"doc3\",\n text=\"How can I change my shipping address? Contact our customer service team.\",\n metadata={\"category\": \"support\"}\n )\n ]\n\n # Create an index with documents (syncs to cloud)\n index_name = \"faqs\"\n await client.create_index(index_name, documents, \"moss-minilm\")\n print(\"Index created and synced to cloud!\")\n\n # Load the index (from cloud or local cache)\n await client.load_index(index_name)\n\n # Search the index\n result = await client.query(\n index_name,\n \"How do I return a damaged product?\",\n 3 # top 3 results\n )\n\n # Display results\n print(f\"Query: {result.query}\")\n for doc in result.docs:\n print(f\"Score: {doc.score:.4f}\")\n print(f\"ID: {doc.id}\")\n print(f\"Text: {doc.text}\")\n print(\"---\")\n\nasyncio.run(main())\n```\n\n## \ud83d\udd25 Example Use Cases\n\n- Smart knowledge base search with cloud backup\n- Realtime Voice AI agents with persistent indexes\n- Personal note-taking search with sync across devices\n- Private in-app AI features with cloud storage\n- Local semantic search in edge devices with cloud fallback\n\n## Available Models\n\n- `moss-minilm`: Lightweight model optimized for speed and efficiency\n- `moss-mediumlm`: Balanced model offering higher accuracy with reasonable performance\n\n## \ud83d\udd27 Getting Started\n\n### Prerequisites\n\n- Python 3.8 or higher\n- Valid InferEdge project credentials\n\n### Environment Setup\n\n1. **Install the package:**\n\n```bash\npip install inferedge-moss\n```\n\n2. **Get your credentials:**\n\nSign up at [InferEdge Platform](https://platform.inferedge.dev) to get your `project_id` and `project_key`.\n\n3. **Set up environment variables (optional):**\n\n```bash\nexport MOSS_PROJECT_ID=\"your-project-id\"\nexport MOSS_PROJECT_KEY=\"your-project-key\"\n```\n\n### Basic Usage\n\n```python\nimport asyncio\nfrom inferedge_moss import MossClient\nfrom moss import DocumentInfo\n\nasync def main():\n # Initialize client\n client = MossClient(\"your-project-id\", \"your-project-key\")\n \n # Create and populate an index\n documents = [\n DocumentInfo(id=\"1\", text=\"Python is a programming language\"),\n DocumentInfo(id=\"2\", text=\"Machine learning with Python is popular\"),\n ]\n \n await client.create_index(\"my-docs\", documents, \"moss-minilm\")\n await client.load_index(\"my-docs\")\n \n # Search\n results = await client.query(\"my-docs\", \"programming language\")\n for doc in results.docs:\n print(f\"{doc.id}: {doc.text} (score: {doc.score:.3f})\")\n\nasyncio.run(main())\n```\n\n## \ud83d\udcda API Reference\n\n### MossClient\n\n#### `MossClient(project_id: str, project_key: str)`\n\nInitialize the client with your InferEdge project credentials.\n\n#### `create_index(index_name: str, docs: List[DocumentInfo], model_id: str) -> bool`\n\nCreate a new search index with documents. The index is automatically synced to cloud storage.\n\n#### `load_index(index_name: str) -> str`\n\nLoad an index from cloud storage or local cache for querying.\n\n#### `query(index_name: str, query: str, top_k: int = 5) -> SearchResult`\n\nSearch for similar documents using semantic similarity.\n\n#### `add_docs(index_name: str, docs: List[DocumentInfo]) -> Dict[str, int]`\n\nAdd new documents to an existing index.\n\n#### `list_indexes() -> List[IndexInfo]`\n\nGet all available indexes in your project.\n\n## \ud83d\udee0\ufe0f Development\n\nFor development setup, contributing guidelines, and technical documentation, see [SETUP.md](./SETUP.md).\n\n## \ud83d\udcc4 License\n\nThis package is licensed under the [PolyForm Shield License 1.0.0](./LICENSE).\n\n- \u2705 Free for testing, evaluation, internal use, and modifications.\n- \u274c Not permitted for production or competing commercial use.\n- \ud83d\udce9 For commercial licenses, contact: <contact@inferedge.dev>\n\n## \ud83d\udcec Contact\n\nFor support, commercial licensing, or partnership inquiries, contact us: [contact@inferedge.dev](mailto:contact@inferedge.dev)\n",
"bugtrack_url": null,
"license": null,
"summary": "Python SDK for semantic search with on-device AI capabilities",
"version": "1.0.0b3",
"project_urls": {
"Documentation": "https://docs.inferedge.com/moss",
"Homepage": "https://github.com/inferedge/moss",
"Repository": "https://github.com/inferedge/moss"
},
"split_keywords": [
"search",
" semantic",
" embeddings",
" vector",
" inferedge"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "38251e4523e6804ecc6af7eca847371269fbb2e059539e153c5a44182e493f13",
"md5": "93867df9d12b957c7ce35cd349bed87b",
"sha256": "a4ce3605be9b08aa0ef7d6e4367625156ae1aa9faee2cd3fb5c1a87a266f6539"
},
"downloads": -1,
"filename": "inferedge_moss-1.0.0b3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "93867df9d12b957c7ce35cd349bed87b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 19482,
"upload_time": "2025-10-09T23:50:57",
"upload_time_iso_8601": "2025-10-09T23:50:57.687381Z",
"url": "https://files.pythonhosted.org/packages/38/25/1e4523e6804ecc6af7eca847371269fbb2e059539e153c5a44182e493f13/inferedge_moss-1.0.0b3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "3307d7ce489eb7740d198096e7180b335824e1860fb80aa0f8ef3dea9e885a87",
"md5": "781892fc06bd8836eac52ad3a4e6ac92",
"sha256": "81c915de65a96260ef93039a29219a9e30ac383d4baa0ddcc547e89446ca9b30"
},
"downloads": -1,
"filename": "inferedge_moss-1.0.0b3.tar.gz",
"has_sig": false,
"md5_digest": "781892fc06bd8836eac52ad3a4e6ac92",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 20739,
"upload_time": "2025-10-09T23:50:58",
"upload_time_iso_8601": "2025-10-09T23:50:58.503722Z",
"url": "https://files.pythonhosted.org/packages/33/07/d7ce489eb7740d198096e7180b335824e1860fb80aa0f8ef3dea9e885a87/inferedge_moss-1.0.0b3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-09 23:50:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "inferedge",
"github_project": "moss",
"github_not_found": true,
"lcname": "inferedge-moss"
}
JSON
