Shortcuts

Docs

• https://api.qdrant.tech/api-reference/points/upsert-points

Fundamental Concepts

• points
  • https://qdrant.tech/documentation/concepts/points/
• payload
  • https://qdrant.tech/documentation/concepts/payload/
• vector
  • https://qdrant.tech/documentation/concepts/vectors/

Qdrant

Vector representations of data to perform search and retrieval based on the semantic meaning of the content rather than just keywords or exact matches.

Vector search finds what users mean, without requiring an exact keyword match.

Embeddings represent data in the form of numerical vectors in higher dimensional space.

• embeddings are generated through deep learning models.

Vector databases are optimized for storing and querying these high-dimensional vectors efficiently.

• These databases enable fast similarity and semantic search.
• These databases use distance metrics like Euclidean Distance, Cosine Similarity, and Dot Product.

Basic Concepts

Point = fundamental unit of data.

• Vector
  • Vectors define the similarity between objects in the vector space
• Payload
  • Payload is additional data associated with the point

Qdrant Commands

Upsert

from qdrant_client import QdrantClient, models

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

client.upsert(
    collection_name="{collection_name}",
    points=[
        models.PointStruct(
            id=1,
            payload={
                "color": "red",
            },
            vector=[0.9, 0.1, 0.1],
        ),
        models.PointStruct(
            id=2,
            payload={
                "color": "green",
            },
            vector=[0.1, 0.9, 0.1],
        ),
        models.PointStruct(
            id=3,
            payload={
                "color": "blue",
            },
            vector=[0.1, 0.1, 0.9],
        ),
    ],
)