Types

from cyborgdb import IndexIVFSQ

config = IndexIVFSQ(
    sq_bits=16,       # optional, default: 16
    dimension=768     # optional, defaults to auto-detect
)

from cyborgdb import IndexIVFFlat

config = IndexIVFFlat(
    dimension=512 # optional, defaults to auto-detect
)

from cyborgdb import IndexIVFPQ

config = IndexIVFPQ(
    pq_dim=64,        # required: product quantization dimension
    pq_bits=8,        # required: bits per quantization code
    dimension=1536    # optional, defaults to auto-detect
)

vector_item = {
    "id": "unique_identifier",           # Required: string
    "vector": [0.1, 0.2, 0.3, ...],    # Optional: List[float]
    "contents": "text content",          # Optional: string or bytes
    "metadata": {                        # Optional: Dict[str, Any]
        "category": "research",
        "author": "Dr. Smith",
        "tags": ["ai", "ml"]
    }
}

# Single query result format (flat list)
single_query_results = [
    {
        "id": "doc1",                    # string (always included)
        "distance": 0.125,               # float (if included, lower = more similar)
        "metadata": {                    # Dict (if included in query)
            "category": "research"
        },
        "contents": "text content",      # string (if included in query)
        "vector": [0.1, 0.2, ...]      # List[float] (if included in query)
    },
    # ... more results
]

# Batch query result format (nested list)
batch_query_results = [
    [  # Results for first query vector
        {"id": "doc1", "distance": 0.125, ...},
        {"id": "doc2", "distance": 0.234, ...}
    ],
    [  # Results for second query vector
        {"id": "doc3", "distance": 0.156, ...},
        {"id": "doc4", "distance": 0.278, ...}
    ]
]

# Simple equality filter
simple_filter = {"category": "research"}

# Range filter
range_filter = {
    "published_year": {"$gte": 2020, "$lte": 2024}
}

# Complex compound filter
complex_filter = {
    "$and": [
        {"category": "research"},
        {"confidence": {"$gte": 0.9}},
        {"$or": [
            {"language": "en"},
            {"translated": True}
        ]}
    ]
}

# Include only metadata (efficient for existence checks)
metadata_only = ["metadata"]

# Include vectors and distances (for similarity analysis)
vectors_and_distances = ["vector", "distance"]

# Include all available fields
all_fields = ["vector", "contents", "metadata", "distance"]