Pinecone Vector Protocol Documentation¶

This directory contains consolidated documentation for HeliosDB's Pinecone vector database protocol support.

Quick Start¶

Connect to HeliosDB using the Pinecone client:

from pinecone import Pinecone

# Connect to HeliosDB (Pinecone-compatible)
pc = Pinecone(api_key="your-api-key", host="http://localhost:8080")

# Access index
index = pc.Index("my-vectors")

# Upsert vectors
index.upsert(vectors=[
    {"id": "vec1", "values": [0.1, 0.2, 0.3, ...], "metadata": {"category": "A"}},
    {"id": "vec2", "values": [0.4, 0.5, 0.6, ...], "metadata": {"category": "B"}}
])

# Query similar vectors
results = index.query(vector=[0.1, 0.2, 0.3, ...], top_k=10)

Contents¶

File	Description
README.md	Overview and quick start (this file)
CONFIGURATION.md	Connection and API configuration
COMPATIBILITY.md	Pinecone API compatibility
EXAMPLES.md	Vector search examples

Feature Overview¶

API Compatibility¶

Operation	Status	Notes
Upsert	Supported	Batch operations
Query	Supported	Top-K search
Fetch	Supported	By ID
Delete	Supported	By ID or filter
Update	Supported	Metadata update
List	Supported	Pagination
Describe Index	Supported	Index stats

Vector Search Features¶

Similarity Metrics: Cosine, Euclidean, Dot product
Filtering: Metadata-based filtering
Namespaces: Logical partitioning
Sparse Vectors: Hybrid search support
Batching: Bulk operations

Connection Parameters¶

Parameter	Default	Description
`host`	localhost	Server hostname
`port`	8080	Vector API port
`api_key`	-	API authentication
`index`	-	Index name

Use Cases¶

Semantic Search: Natural language queries
Recommendations: Similar item lookup
Image Search: Visual similarity
RAG Applications: Retrieval-augmented generation
Anomaly Detection: Outlier identification

CONFIGURATION.md - API configuration
COMPATIBILITY.md - API compatibility
EXAMPLES.md - Usage examples
Parent Directory - Protocol overview

Last Updated: December 2025 Consolidation Status: Complete