# HACS Pinecone Integration
[](https://badge.fury.io/py/hacs-pinecone)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/Apache-2.0)
**Pinecone vector database integration for HACS (Healthcare Agent Communication Standard)**
This package provides seamless integration between HACS and Pinecone, enabling healthcare AI agents to store and retrieve vector embeddings for clinical data with enterprise-grade performance and scalability.
## Table of Contents
- [Introduction](#introduction)
- [Features](#features)
- [Installation](#installation)
- [Quick Start](#quick-start)
- [Configuration](#configuration)
- [Usage Examples](#usage-examples)
- [API Reference](#api-reference)
- [Healthcare Compliance](#healthcare-compliance)
- [Performance](#performance)
- [Contributing](#contributing)
- [License](#license)
## Introduction
The HACS Pinecone integration enables healthcare AI systems to leverage Pinecone's high-performance vector database for storing and retrieving clinical embeddings. This integration is designed specifically for healthcare applications with built-in support for:
- **Clinical Data Embeddings**: Store vector representations of patient data, observations, and clinical notes
- **Semantic Search**: Find similar patients, conditions, or treatments using vector similarity
- **FHIR Compliance**: Maintain healthcare interoperability standards
- **Privacy Protection**: Built-in safeguards against PHI exposure
- **Audit Trails**: Comprehensive logging for healthcare compliance
## Features
### 🏥 Healthcare-First Design
- **FHIR-Compliant Metadata**: Store FHIR resource references with embeddings
- **PHI Protection**: Automatic detection and prevention of sensitive data storage
- **Clinical Terminology**: Support for LOINC, SNOMED CT, and ICD-10 codes
- **Audit Logging**: Complete audit trails for regulatory compliance
### 🚀 High Performance
- **Lazy Loading**: Import Pinecone only when needed
- **Batch Operations**: Efficient bulk embedding storage and retrieval
- **Automatic Indexing**: Smart index creation and management
- **Scalable Architecture**: Handle millions of clinical embeddings
### 🔧 Easy Integration
- **HACS Native**: Seamless integration with HACS models and tools
- **Multiple Embeddings**: Support for OpenAI, Hugging Face, and custom models
- **Flexible Configuration**: Environment-based and programmatic configuration
- **Error Handling**: Robust error handling with healthcare-specific messaging
## Installation
### Prerequisites
- Python 3.10 or higher
- Pinecone account and API key
- HACS core packages
### Install from PyPI
```bash
# Install hacs-pinecone
pip install hacs-pinecone
# Or install with HACS suite
pip install healthcare-hacs[vectorization]
```
### Development Installation
```bash
# Clone the HACS repository
git clone https://github.com/solanovisitor/hacs.git
cd hacs
# Install in development mode
pip install -e packages/hacs-pinecone
```
## Quick Start
### 1. Set Up Pinecone Credentials
```bash
# Set environment variables
export PINECONE_API_KEY="your-api-key"
export PINECONE_ENVIRONMENT="your-environment" # e.g., "us-west1-gcp"
```
### 2. Basic Usage
```python
from hacs_pinecone import PineconeVectorStore
from hacs_models import Patient, Observation
from hacs_core import Actor
# Initialize the vector store
vector_store = PineconeVectorStore(
index_name="healthcare-embeddings",
dimension=1536, # OpenAI embedding dimension
api_key="your-api-key",
environment="us-west1-gcp"
)
# Create a healthcare actor
actor = Actor(
id="physician-001",
name="Dr. Sarah Johnson",
role="physician"
)
# Store patient embedding
patient = Patient(
id="patient-001",
given=["John"],
family="Doe",
birth_date="1985-03-15"
)
# Store embedding with clinical metadata
embedding = [0.1, 0.2, 0.3, ...] # Your embedding vector
vector_store.store_embedding(
embedding=embedding,
resource_id=patient.id,
resource_type="Patient",
metadata={
"fhir_resource": patient.model_dump(),
"clinical_context": "routine_checkup",
"actor_id": actor.id
},
actor=actor
)
# Search for similar patients
similar_patients = vector_store.similarity_search(
query_embedding=embedding,
top_k=5,
filter_metadata={"resource_type": "Patient"}
)
print(f"Found {len(similar_patients)} similar patients")
```
## Configuration
### Environment Variables
```bash
# Required
PINECONE_API_KEY=your-api-key
PINECONE_ENVIRONMENT=your-environment
# Optional
PINECONE_INDEX_NAME=healthcare-embeddings
PINECONE_DIMENSION=1536
PINECONE_METRIC=cosine
HACS_AUDIT_ENABLED=true
```
### Programmatic Configuration
```python
from hacs_pinecone import PineconeVectorStore
# Full configuration
vector_store = PineconeVectorStore(
api_key="your-api-key",
environment="us-west1-gcp",
index_name="clinical-embeddings",
dimension=1536,
metric="cosine",
pod_type="p1.x1",
replicas=1,
shards=1,
metadata_config={
"indexed": ["resource_type", "clinical_context", "actor_id"]
}
)
```
## Usage Examples
### Clinical Data Storage
```python
from hacs_pinecone import PineconeVectorStore
from hacs_models import Observation
import openai
# Initialize vector store
vector_store = PineconeVectorStore(index_name="clinical-data")
# Create clinical observation
observation = Observation(
status="final",
code={
"coding": [{
"system": "http://loinc.org",
"code": "8480-6",
"display": "Systolic blood pressure"
}]
},
value_quantity={"value": 120, "unit": "mmHg"}
)
# Generate embedding for clinical text
clinical_text = f"{observation.code.coding[0].display}: {observation.value_quantity.value} {observation.value_quantity.unit}"
embedding = openai.Embedding.create(
input=clinical_text,
model="text-embedding-ada-002"
)["data"][0]["embedding"]
# Store with clinical metadata
vector_store.store_embedding(
embedding=embedding,
resource_id=observation.id,
resource_type="Observation",
metadata={
"loinc_code": "8480-6",
"value": 120,
"unit": "mmHg",
"clinical_significance": "normal",
"fhir_resource": observation.model_dump()
}
)
```
### Semantic Clinical Search
```python
# Search for similar blood pressure readings
query_text = "high blood pressure hypertension"
query_embedding = openai.Embedding.create(
input=query_text,
model="text-embedding-ada-002"
)["data"][0]["embedding"]
# Find similar clinical observations
results = vector_store.similarity_search(
query_embedding=query_embedding,
top_k=10,
filter_metadata={
"resource_type": "Observation",
"loinc_code": "8480-6" # Blood pressure observations only
},
include_metadata=True
)
# Process results
for result in results:
print(f"Similarity: {result.score:.3f}")
print(f"Value: {result.metadata['value']} {result.metadata['unit']}")
print(f"Clinical significance: {result.metadata['clinical_significance']}")
print("---")
```
### Batch Operations
```python
# Store multiple embeddings efficiently
embeddings_batch = [
{
"embedding": embedding1,
"resource_id": "patient-001",
"resource_type": "Patient",
"metadata": {"age": 35, "condition": "diabetes"}
},
{
"embedding": embedding2,
"resource_id": "patient-002",
"resource_type": "Patient",
"metadata": {"age": 42, "condition": "hypertension"}
}
]
vector_store.store_embeddings_batch(embeddings_batch)
# Batch similarity search
query_embeddings = [embedding1, embedding2]
batch_results = vector_store.similarity_search_batch(
query_embeddings=query_embeddings,
top_k=5
)
```
## API Reference
### PineconeVectorStore
#### Constructor
```python
PineconeVectorStore(
api_key: str = None,
environment: str = None,
index_name: str = "hacs-embeddings",
dimension: int = 1536,
metric: str = "cosine",
pod_type: str = "p1.x1",
replicas: int = 1,
shards: int = 1,
metadata_config: dict = None
)
```
#### Methods
- `store_embedding(embedding, resource_id, resource_type, metadata, actor)`: Store a single embedding
- `store_embeddings_batch(embeddings_batch)`: Store multiple embeddings efficiently
- `similarity_search(query_embedding, top_k, filter_metadata, include_metadata)`: Search for similar embeddings
- `similarity_search_batch(query_embeddings, top_k, filter_metadata)`: Batch similarity search
- `delete_embedding(resource_id)`: Delete an embedding by resource ID
- `get_embedding(resource_id)`: Retrieve an embedding by resource ID
- `list_embeddings(filter_metadata)`: List embeddings with optional filtering
## Healthcare Compliance
### PHI Protection
The HACS Pinecone integration includes built-in safeguards:
```python
# Automatic PHI detection
try:
vector_store.store_embedding(
embedding=embedding,
metadata={"patient_ssn": "123-45-6789"} # This will be blocked
)
except ValueError as e:
print("PHI detected and blocked:", e)
```
### Audit Logging
All operations are automatically logged for compliance:
```python
# Enable audit logging
vector_store = PineconeVectorStore(
index_name="clinical-data",
audit_enabled=True,
audit_actor_required=True
)
# All operations will be logged with actor information
vector_store.store_embedding(embedding, metadata, actor=physician)
```
### FHIR Compliance
Store FHIR resources with embeddings:
```python
# FHIR-compliant metadata
metadata = {
"fhir_resource_type": "Patient",
"fhir_resource_id": patient.id,
"fhir_resource": patient.model_dump(),
"fhir_version": "R4"
}
vector_store.store_embedding(embedding, metadata=metadata)
```
## Performance
### Benchmarks
- **Storage**: 10,000 embeddings/minute
- **Search**: Sub-100ms for similarity queries
- **Memory**: <50MB for typical healthcare workloads
- **Scalability**: Tested with 10M+ clinical embeddings
### Optimization Tips
```python
# Use batch operations for better performance
vector_store.store_embeddings_batch(large_batch)
# Enable metadata indexing for faster filtering
vector_store = PineconeVectorStore(
metadata_config={
"indexed": ["resource_type", "loinc_code", "clinical_context"]
}
)
# Use appropriate pod types for your workload
vector_store = PineconeVectorStore(
pod_type="p1.x2", # Higher performance
replicas=2 # Better availability
)
```
## Error Handling
```python
from hacs_pinecone import PineconeVectorStore, PineconeError
try:
vector_store = PineconeVectorStore(api_key="invalid-key")
except PineconeError as e:
print(f"Pinecone configuration error: {e}")
try:
vector_store.store_embedding(invalid_embedding)
except ValueError as e:
print(f"Validation error: {e}")
```
## Contributing
We welcome contributions! Please see our [Contributing Guidelines](../../CONTRIBUTING.md) for details.
### Development Setup
```bash
# Clone the repository
git clone https://github.com/solanovisitor/hacs.git
cd hacs
# Install development dependencies
pip install -e packages/hacs-pinecone[dev]
# Run tests
pytest packages/hacs-pinecone/tests/
```
### Running Tests
```bash
# Unit tests
pytest packages/hacs-pinecone/tests/unit/
# Integration tests (requires Pinecone API key)
export PINECONE_API_KEY="your-test-api-key"
pytest packages/hacs-pinecone/tests/integration/
# Performance tests
pytest packages/hacs-pinecone/tests/performance/
```
## License
This project is licensed under the Apache License 2.0 - see the [LICENSE](../../LICENSE) file for details.
## Support
- **Documentation**: [HACS Documentation](../../docs/README.md)
- **Issues**: [GitHub Issues](https://github.com/solanovisitor/hacs/issues)
- **Discussions**: [GitHub Discussions](https://github.com/solanovisitor/hacs/discussions)
- **Security**: security@hacs-project.org
---
**Part of the HACS (Healthcare Agent Communication Standard) ecosystem**
[HACS Core](../hacs-core/) | [HACS Models](../hacs-models/) | [HACS Tools](../hacs-tools/) | [All Packages](../../README.md#package-structure)
Raw data
{
"_id": null,
"home_page": null,
"name": "hacs-pinecone",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "agents, ai, clinical, communication, embeddings, fhir, healthcare, pinecone, semantic-search, standard, vector-store, vectorization",
"author": null,
"author_email": "Solano Todeschini <solano.todeschini@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/a5/32/30555589e33d67df71d7e7c5abfc6bfc74c421bb95d994cff3ddb52728fb/hacs_pinecone-0.3.3.tar.gz",
"platform": null,
"description": "# HACS Pinecone Integration\n\n[](https://badge.fury.io/py/hacs-pinecone)\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/Apache-2.0)\n\n**Pinecone vector database integration for HACS (Healthcare Agent Communication Standard)**\n\nThis package provides seamless integration between HACS and Pinecone, enabling healthcare AI agents to store and retrieve vector embeddings for clinical data with enterprise-grade performance and scalability.\n\n## Table of Contents\n\n- [Introduction](#introduction)\n- [Features](#features)\n- [Installation](#installation)\n- [Quick Start](#quick-start)\n- [Configuration](#configuration)\n- [Usage Examples](#usage-examples)\n- [API Reference](#api-reference)\n- [Healthcare Compliance](#healthcare-compliance)\n- [Performance](#performance)\n- [Contributing](#contributing)\n- [License](#license)\n\n## Introduction\n\nThe HACS Pinecone integration enables healthcare AI systems to leverage Pinecone's high-performance vector database for storing and retrieving clinical embeddings. This integration is designed specifically for healthcare applications with built-in support for:\n\n- **Clinical Data Embeddings**: Store vector representations of patient data, observations, and clinical notes\n- **Semantic Search**: Find similar patients, conditions, or treatments using vector similarity\n- **FHIR Compliance**: Maintain healthcare interoperability standards\n- **Privacy Protection**: Built-in safeguards against PHI exposure\n- **Audit Trails**: Comprehensive logging for healthcare compliance\n\n## Features\n\n### \ud83c\udfe5 Healthcare-First Design\n- **FHIR-Compliant Metadata**: Store FHIR resource references with embeddings\n- **PHI Protection**: Automatic detection and prevention of sensitive data storage\n- **Clinical Terminology**: Support for LOINC, SNOMED CT, and ICD-10 codes\n- **Audit Logging**: Complete audit trails for regulatory compliance\n\n### \ud83d\ude80 High Performance\n- **Lazy Loading**: Import Pinecone only when needed\n- **Batch Operations**: Efficient bulk embedding storage and retrieval\n- **Automatic Indexing**: Smart index creation and management\n- **Scalable Architecture**: Handle millions of clinical embeddings\n\n### \ud83d\udd27 Easy Integration\n- **HACS Native**: Seamless integration with HACS models and tools\n- **Multiple Embeddings**: Support for OpenAI, Hugging Face, and custom models\n- **Flexible Configuration**: Environment-based and programmatic configuration\n- **Error Handling**: Robust error handling with healthcare-specific messaging\n\n## Installation\n\n### Prerequisites\n\n- Python 3.10 or higher\n- Pinecone account and API key\n- HACS core packages\n\n### Install from PyPI\n\n```bash\n# Install hacs-pinecone\npip install hacs-pinecone\n\n# Or install with HACS suite\npip install healthcare-hacs[vectorization]\n```\n\n### Development Installation\n\n```bash\n# Clone the HACS repository\ngit clone https://github.com/solanovisitor/hacs.git\ncd hacs\n\n# Install in development mode\npip install -e packages/hacs-pinecone\n```\n\n## Quick Start\n\n### 1. Set Up Pinecone Credentials\n\n```bash\n# Set environment variables\nexport PINECONE_API_KEY=\"your-api-key\"\nexport PINECONE_ENVIRONMENT=\"your-environment\" # e.g., \"us-west1-gcp\"\n```\n\n### 2. Basic Usage\n\n```python\nfrom hacs_pinecone import PineconeVectorStore\nfrom hacs_models import Patient, Observation\nfrom hacs_core import Actor\n\n# Initialize the vector store\nvector_store = PineconeVectorStore(\n index_name=\"healthcare-embeddings\",\n dimension=1536, # OpenAI embedding dimension\n api_key=\"your-api-key\",\n environment=\"us-west1-gcp\"\n)\n\n# Create a healthcare actor\nactor = Actor(\n id=\"physician-001\",\n name=\"Dr. Sarah Johnson\",\n role=\"physician\"\n)\n\n# Store patient embedding\npatient = Patient(\n id=\"patient-001\",\n given=[\"John\"],\n family=\"Doe\",\n birth_date=\"1985-03-15\"\n)\n\n# Store embedding with clinical metadata\nembedding = [0.1, 0.2, 0.3, ...] # Your embedding vector\nvector_store.store_embedding(\n embedding=embedding,\n resource_id=patient.id,\n resource_type=\"Patient\",\n metadata={\n \"fhir_resource\": patient.model_dump(),\n \"clinical_context\": \"routine_checkup\",\n \"actor_id\": actor.id\n },\n actor=actor\n)\n\n# Search for similar patients\nsimilar_patients = vector_store.similarity_search(\n query_embedding=embedding,\n top_k=5,\n filter_metadata={\"resource_type\": \"Patient\"}\n)\n\nprint(f\"Found {len(similar_patients)} similar patients\")\n```\n\n## Configuration\n\n### Environment Variables\n\n```bash\n# Required\nPINECONE_API_KEY=your-api-key\nPINECONE_ENVIRONMENT=your-environment\n\n# Optional\nPINECONE_INDEX_NAME=healthcare-embeddings\nPINECONE_DIMENSION=1536\nPINECONE_METRIC=cosine\nHACS_AUDIT_ENABLED=true\n```\n\n### Programmatic Configuration\n\n```python\nfrom hacs_pinecone import PineconeVectorStore\n\n# Full configuration\nvector_store = PineconeVectorStore(\n api_key=\"your-api-key\",\n environment=\"us-west1-gcp\",\n index_name=\"clinical-embeddings\",\n dimension=1536,\n metric=\"cosine\",\n pod_type=\"p1.x1\",\n replicas=1,\n shards=1,\n metadata_config={\n \"indexed\": [\"resource_type\", \"clinical_context\", \"actor_id\"]\n }\n)\n```\n\n## Usage Examples\n\n### Clinical Data Storage\n\n```python\nfrom hacs_pinecone import PineconeVectorStore\nfrom hacs_models import Observation\nimport openai\n\n# Initialize vector store\nvector_store = PineconeVectorStore(index_name=\"clinical-data\")\n\n# Create clinical observation\nobservation = Observation(\n status=\"final\",\n code={\n \"coding\": [{\n \"system\": \"http://loinc.org\",\n \"code\": \"8480-6\",\n \"display\": \"Systolic blood pressure\"\n }]\n },\n value_quantity={\"value\": 120, \"unit\": \"mmHg\"}\n)\n\n# Generate embedding for clinical text\nclinical_text = f\"{observation.code.coding[0].display}: {observation.value_quantity.value} {observation.value_quantity.unit}\"\nembedding = openai.Embedding.create(\n input=clinical_text,\n model=\"text-embedding-ada-002\"\n)[\"data\"][0][\"embedding\"]\n\n# Store with clinical metadata\nvector_store.store_embedding(\n embedding=embedding,\n resource_id=observation.id,\n resource_type=\"Observation\",\n metadata={\n \"loinc_code\": \"8480-6\",\n \"value\": 120,\n \"unit\": \"mmHg\",\n \"clinical_significance\": \"normal\",\n \"fhir_resource\": observation.model_dump()\n }\n)\n```\n\n### Semantic Clinical Search\n\n```python\n# Search for similar blood pressure readings\nquery_text = \"high blood pressure hypertension\"\nquery_embedding = openai.Embedding.create(\n input=query_text,\n model=\"text-embedding-ada-002\"\n)[\"data\"][0][\"embedding\"]\n\n# Find similar clinical observations\nresults = vector_store.similarity_search(\n query_embedding=query_embedding,\n top_k=10,\n filter_metadata={\n \"resource_type\": \"Observation\",\n \"loinc_code\": \"8480-6\" # Blood pressure observations only\n },\n include_metadata=True\n)\n\n# Process results\nfor result in results:\n print(f\"Similarity: {result.score:.3f}\")\n print(f\"Value: {result.metadata['value']} {result.metadata['unit']}\")\n print(f\"Clinical significance: {result.metadata['clinical_significance']}\")\n print(\"---\")\n```\n\n### Batch Operations\n\n```python\n# Store multiple embeddings efficiently\nembeddings_batch = [\n {\n \"embedding\": embedding1,\n \"resource_id\": \"patient-001\",\n \"resource_type\": \"Patient\",\n \"metadata\": {\"age\": 35, \"condition\": \"diabetes\"}\n },\n {\n \"embedding\": embedding2,\n \"resource_id\": \"patient-002\", \n \"resource_type\": \"Patient\",\n \"metadata\": {\"age\": 42, \"condition\": \"hypertension\"}\n }\n]\n\nvector_store.store_embeddings_batch(embeddings_batch)\n\n# Batch similarity search\nquery_embeddings = [embedding1, embedding2]\nbatch_results = vector_store.similarity_search_batch(\n query_embeddings=query_embeddings,\n top_k=5\n)\n```\n\n## API Reference\n\n### PineconeVectorStore\n\n#### Constructor\n\n```python\nPineconeVectorStore(\n api_key: str = None,\n environment: str = None,\n index_name: str = \"hacs-embeddings\",\n dimension: int = 1536,\n metric: str = \"cosine\",\n pod_type: str = \"p1.x1\",\n replicas: int = 1,\n shards: int = 1,\n metadata_config: dict = None\n)\n```\n\n#### Methods\n\n- `store_embedding(embedding, resource_id, resource_type, metadata, actor)`: Store a single embedding\n- `store_embeddings_batch(embeddings_batch)`: Store multiple embeddings efficiently\n- `similarity_search(query_embedding, top_k, filter_metadata, include_metadata)`: Search for similar embeddings\n- `similarity_search_batch(query_embeddings, top_k, filter_metadata)`: Batch similarity search\n- `delete_embedding(resource_id)`: Delete an embedding by resource ID\n- `get_embedding(resource_id)`: Retrieve an embedding by resource ID\n- `list_embeddings(filter_metadata)`: List embeddings with optional filtering\n\n## Healthcare Compliance\n\n### PHI Protection\n\nThe HACS Pinecone integration includes built-in safeguards:\n\n```python\n# Automatic PHI detection\ntry:\n vector_store.store_embedding(\n embedding=embedding,\n metadata={\"patient_ssn\": \"123-45-6789\"} # This will be blocked\n )\nexcept ValueError as e:\n print(\"PHI detected and blocked:\", e)\n```\n\n### Audit Logging\n\nAll operations are automatically logged for compliance:\n\n```python\n# Enable audit logging\nvector_store = PineconeVectorStore(\n index_name=\"clinical-data\",\n audit_enabled=True,\n audit_actor_required=True\n)\n\n# All operations will be logged with actor information\nvector_store.store_embedding(embedding, metadata, actor=physician)\n```\n\n### FHIR Compliance\n\nStore FHIR resources with embeddings:\n\n```python\n# FHIR-compliant metadata\nmetadata = {\n \"fhir_resource_type\": \"Patient\",\n \"fhir_resource_id\": patient.id,\n \"fhir_resource\": patient.model_dump(),\n \"fhir_version\": \"R4\"\n}\n\nvector_store.store_embedding(embedding, metadata=metadata)\n```\n\n## Performance\n\n### Benchmarks\n\n- **Storage**: 10,000 embeddings/minute\n- **Search**: Sub-100ms for similarity queries\n- **Memory**: <50MB for typical healthcare workloads\n- **Scalability**: Tested with 10M+ clinical embeddings\n\n### Optimization Tips\n\n```python\n# Use batch operations for better performance\nvector_store.store_embeddings_batch(large_batch)\n\n# Enable metadata indexing for faster filtering\nvector_store = PineconeVectorStore(\n metadata_config={\n \"indexed\": [\"resource_type\", \"loinc_code\", \"clinical_context\"]\n }\n)\n\n# Use appropriate pod types for your workload\nvector_store = PineconeVectorStore(\n pod_type=\"p1.x2\", # Higher performance\n replicas=2 # Better availability\n)\n```\n\n## Error Handling\n\n```python\nfrom hacs_pinecone import PineconeVectorStore, PineconeError\n\ntry:\n vector_store = PineconeVectorStore(api_key=\"invalid-key\")\nexcept PineconeError as e:\n print(f\"Pinecone configuration error: {e}\")\n\ntry:\n vector_store.store_embedding(invalid_embedding)\nexcept ValueError as e:\n print(f\"Validation error: {e}\")\n```\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guidelines](../../CONTRIBUTING.md) for details.\n\n### Development Setup\n\n```bash\n# Clone the repository\ngit clone https://github.com/solanovisitor/hacs.git\ncd hacs\n\n# Install development dependencies\npip install -e packages/hacs-pinecone[dev]\n\n# Run tests\npytest packages/hacs-pinecone/tests/\n```\n\n### Running Tests\n\n```bash\n# Unit tests\npytest packages/hacs-pinecone/tests/unit/\n\n# Integration tests (requires Pinecone API key)\nexport PINECONE_API_KEY=\"your-test-api-key\"\npytest packages/hacs-pinecone/tests/integration/\n\n# Performance tests\npytest packages/hacs-pinecone/tests/performance/\n```\n\n## License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](../../LICENSE) file for details.\n\n## Support\n\n- **Documentation**: [HACS Documentation](../../docs/README.md)\n- **Issues**: [GitHub Issues](https://github.com/solanovisitor/hacs/issues)\n- **Discussions**: [GitHub Discussions](https://github.com/solanovisitor/hacs/discussions)\n- **Security**: security@hacs-project.org\n\n---\n\n**Part of the HACS (Healthcare Agent Communication Standard) ecosystem**\n\n[HACS Core](../hacs-core/) | [HACS Models](../hacs-models/) | [HACS Tools](../hacs-tools/) | [All Packages](../../README.md#package-structure) ",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Pinecone vector store integration for HACS (Healthcare Agent Communication Standard)",
"version": "0.3.3",
"project_urls": {
"Bug Tracker": "https://github.com/solanovisitor/hacs/issues",
"Changelog": "https://github.com/solanovisitor/hacs/blob/main/docs/reference/changelog.md",
"Documentation": "https://github.com/solanovisitor/hacs/tree/main/docs",
"Homepage": "https://github.com/solanovisitor/hacs",
"Repository": "https://github.com/solanovisitor/hacs"
},
"split_keywords": [
"agents",
" ai",
" clinical",
" communication",
" embeddings",
" fhir",
" healthcare",
" pinecone",
" semantic-search",
" standard",
" vector-store",
" vectorization"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "faf7ef19a65fc608bd77aeeb40d23e37064bca1e21f161a2e86a454e971985ab",
"md5": "736bb2af9e867fd152a15cb12ed4b4d7",
"sha256": "6e131ed3714ce2ee7eb0d1070311d5387ab6627addc93ea6957b25fbd06c2baf"
},
"downloads": -1,
"filename": "hacs_pinecone-0.3.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "736bb2af9e867fd152a15cb12ed4b4d7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 10551,
"upload_time": "2025-07-10T15:05:19",
"upload_time_iso_8601": "2025-07-10T15:05:19.653621Z",
"url": "https://files.pythonhosted.org/packages/fa/f7/ef19a65fc608bd77aeeb40d23e37064bca1e21f161a2e86a454e971985ab/hacs_pinecone-0.3.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "a53230555589e33d67df71d7e7c5abfc6bfc74c421bb95d994cff3ddb52728fb",
"md5": "87e958551f4f51dc8d03adf1a8576b30",
"sha256": "f72aac67eae0f225e7cd4dd38e21fdfbc3440a55c31a077afc27ea136dedfbb6"
},
"downloads": -1,
"filename": "hacs_pinecone-0.3.3.tar.gz",
"has_sig": false,
"md5_digest": "87e958551f4f51dc8d03adf1a8576b30",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 12556,
"upload_time": "2025-07-10T15:05:20",
"upload_time_iso_8601": "2025-07-10T15:05:20.854234Z",
"url": "https://files.pythonhosted.org/packages/a5/32/30555589e33d67df71d7e7c5abfc6bfc74c421bb95d994cff3ddb52728fb/hacs_pinecone-0.3.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-10 15:05:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "solanovisitor",
"github_project": "hacs",
"github_not_found": true,
"lcname": "hacs-pinecone"
}
JSON
