Qdrant is an open-source vector search engine. It is designed to work with large-scale datasets and provides a high-performance search engine for vector data.

​
Usage

import os
from Zentry import Memory

os.environ["OPENAI_API_KEY"] = "sk-xx"

config = {
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "collection_name": "test",
            "host": "localhost",
            "port": 6333,
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="alice", metadata={"category": "movies"})

​
Config

Let’s see the available parameters for the qdrant config:
ParameterDescriptionDefault Value
collection_nameThe name of the collection to store the vectorsZentry
embedding_model_dimsDimensions of the embedding model1536
clientCustom client for qdrantNone
hostThe host where the qdrant server is runningNone
portThe port where the qdrant server is runningNone
pathPath for the qdrant database/tmp/qdrant
urlFull URL for the qdrant serverNone
api_keyAPI key for the qdrant serverNone
on_diskFor enabling persistent storageFalse