vector-database-ops

# Docker (single node)
docker run -d \
  --name qdrant \
  -p 6333:6333 \
  -p 6334:6334 \
  -v $(pwd)/qdrant-data:/qdrant/storage \
  qdrant/qdrant:latest

# With custom config
docker run -d \
  --name qdrant \
  -p 6333:6333 \
  -v $(pwd)/qdrant-data:/qdrant/storage \
  -v $(pwd)/qdrant-config.yaml:/qdrant/config/production.yaml \
  qdrant/qdrant:latest

# qdrant-config.yaml
storage:
  storage_path: /qdrant/storage
  on_disk_payload: true          # store payload on disk (saves RAM)

service:
  max_request_size_mb: 32

hnsw_index:
  m: 16                          # graph connections per node
  ef_construct: 100              # accuracy vs build time trade-off
  full_scan_threshold: 10000     # switch to brute force below this

quantization:
  scalar:
    type: int8
    quantile: 0.99
    always_ram: true             # keep quantized index in RAM

telemetry_disabled: true

from qdrant_client import QdrantClient
from qdrant_client.models import (
    Distance, VectorParams, HnswConfigDiff,
    ScalarQuantizationConfig, ScalarType, QuantizationConfig
)

client = QdrantClient("http://localhost:6333")

# Create optimized collection
client.create_collection(
    collection_name="documents",
    vectors_config=VectorParams(
        size=1536,                         # OpenAI ada-002 / text-embedding-3-small
        distance=Distance.COSINE,
        on_disk=True,                      # save RAM — vectors stored on disk
    ),
    hnsw_config=HnswConfigDiff(
        m=32,                              # higher = better recall, more RAM
        ef_construct=200,
        on_disk=False,                     # keep HNSW graph in RAM for speed
    ),
    quantization_config=QuantizationConfig(
        scalar=ScalarQuantizationConfig(
            type=ScalarType.INT8,
            quantile=0.99,
            always_ram=True,
        )
    ),
)

# Create payload index for fast filtering
client.create_payload_index(
    collection_name="documents",
    field_name="tenant_id",
    field_schema="keyword",
)
client.create_payload_index(
    collection_name="documents",
    field_name="created_at",
    field_schema="datetime",
)

# Collection info
info = client.get_collection("documents")
print(f"Vectors: {info.vectors_count}, Status: {info.status}")

from qdrant_client.models import Filter, FieldCondition, MatchValue, Range

# Tenant-isolated search (multi-tenant RAG)
results = client.query_points(
    collection_name="documents",
    query=query_embedding,
    query_filter=Filter(
        must=[
            FieldCondition(key="tenant_id", match=MatchValue(value="acme-corp")),
            FieldCondition(key="doc_type", match=MatchValue(value="contract")),
        ],
        should=[
            FieldCondition(key="created_at", range=Range(gte="2024-01-01")),
        ],
    ),