vectordb

Quick Start using Docker

1. Run Backend in Docker

docker pull epsilla/vectordb
docker run --pull=always -d -p 8888:8888 -v /data:/data epsilla/vectordb

2. Interact with Python Client

pip install pyepsilla

from pyepsilla import vectordb

client = vectordb.Client(host='localhost', port='8888')
client.load_db(db_name="MyDB", db_path="/data/epsilla")
client.use_db(db_name="MyDB")

client.create_table(
    table_name="MyTable",
    table_fields=[
        {"name": "ID", "dataType": "INT", "primaryKey": True},
        {"name": "Doc", "dataType": "STRING"},
    ],
    indices=[
      {"name": "Index", "field": "Doc"},
    ]
)

client.insert(
    table_name="MyTable",
    records=[
        {"ID": 1, "Doc": "Jupiter is the largest planet in our solar system."},
        {"ID": 2, "Doc": "Cheetahs are the fastest land animals, reaching speeds over 60 mph."},
        {"ID": 3, "Doc": "Vincent van Gogh painted the famous work \"Starry Night.\""},
        {"ID": 4, "Doc": "The Amazon River is the longest river in the world."},
        {"ID": 5, "Doc": "The Moon completes one orbit around Earth every 27 days."},
    ],
)

client.query(
    table_name="MyTable",
    query_text="Celestial bodies and their characteristics",
    limit=2
)

---

## (Experimental) Use Epsilla as a python library without starting a docker image

**1. Build Epsilla Python Bindings lib package**
```shell
cd engine/scripts
(If on Ubuntu, run this first: bash setup-dev.sh)
bash install_oatpp_modules.sh
cd ..
bash build.sh
ls -lh build/*.so

2. Run test with python bindings lib "epsilla.so" "libvectordb_dylib.so in the folder "build" built in the previous step

cd engine
export PYTHONPATH=./build/
export DB_PATH=/tmp/db33
python3 test/bindings/python/test.py

Here are some sample code:

import epsilla

epsilla.load_db(db_name="db", db_path="/data/epsilla")
epsilla.use_db(db_name="db")
epsilla.create_table(
    table_name="MyTable",
    table_fields=[
        {"name": "ID", "dataType": "INT", "primaryKey": True},
        {"name": "Doc", "dataType": "STRING"},
        {"name": "EmbeddingEuclidean", "dataType": "VECTOR_FLOAT", "dimensions": 4, "metricType": "EUCLIDEAN"}
    ]
)
epsilla.insert(
    table_name="MyTable",
    records=[
        {"ID": 1, "Doc": "Berlin", "EmbeddingEuclidean": [0.05, 0.61, 0.76, 0.74]},
        {"ID": 2, "Doc": "London", "EmbeddingEuclidean": [0.19, 0.81, 0.75, 0.11]},
        {"ID": 3, "Doc": "Moscow", "EmbeddingEuclidean": [0.36, 0.55, 0.47, 0.94]}
    ]
)
(code, response) = epsilla.query(
    table_name="MyTable",
    query_field="EmbeddingEuclidean",
    response_fields=["ID", "Doc", "EmbeddingEuclidean"],
    query_vector=[0.35, 0.55, 0.47, 0.94],
    filter="ID < 6",
    limit=10,
    with_distance=True
)
print(code, response)