Demo Redis with SQL

1.txt

$docker container run -d -p 6379:6379 redis:8.8
$docker container ps
CONTAINER ID   IMAGE       COMMAND                  CREATED          STATUS          PORTS                                         NAMES
89bdbf4df9c9   redis:8.8   "docker-entrypoint.s…"   15 seconds ago   Up 15 seconds   0.0.0.0:6379->6379/tcp, [::]:6379->6379/tcp   pensive_mendel

2.txt

$pip install sentence-transformers
$pip install "redisvl[sql-redis]"
$pip list                        
Package           Version
----------------- -------
annotated-types   0.7.0
jsonpath-ng       1.8.0
ml_dtypes         0.5.4
numpy             2.4.6
pip               24.3.1
pydantic          2.13.4
pydantic_core     2.46.4
python-ulid       3.1.0
PyYAML            6.0.3
redis             7.4.1
redisvl           0.20.0
sql-redis         0.6.0
sqlglot           30.9.0
tenacity          9.1.4
typing_extensions 4.15.0
typing-inspection 0.4.2

step1.py

from redisvl.utils.vectorize import HFTextVectorizer
from redisvl.index import SearchIndex
from redis import Redis

# 1. Design schema of data

hf = HFTextVectorizer()
schema = {
    "index": {
        "name": "user_simple",
        "prefix": "user_simple_docs",
        "storage_type": "json",
    },
    "fields": [
        {"name": "user", "type": "tag"},
        {"name": "region", "type": "tag"},
        {"name": "job", "type": "tag"},
        {"name": "job_description", "type": "text"},
        {"name": "age", "type": "numeric"},
        {"name": "office_location", "type": "geo"},
        {
            "name": "job_embedding",
            "type": "vector",
            "attrs": {
                "dims": len(hf.embed("get embed length")),
                "distance_metric": "cosine",
                "algorithm": "flat",
                "datatype": "float32"
            }
        }
    ]
}

# 2. Sample data
data = [
    {
        'user': 'john',
        'age': 34,
        'job': 'software engineer',
        'region': 'us-west',
        'job_description': 'Designs, develops, and maintains software applications and systems.',
        'office_location': '-122.4194,37.7749'  # San Francisco
    },
    {
        'user': 'bill',
        'age': 54,
        'job': 'engineer',
        'region': 'us-central',
        'job_description': 'Applies scientific and mathematical principles to solve technical problems.',
        'office_location': '-87.6298,41.8781'  # Chicago
    }
]

# 3. Create index and insert data
client = Redis.from_url("redis://localhost:6379")
index = SearchIndex.from_dict(schema, redis_client=client)
index.create(overwrite=True, drop=True)
index.load(data)

# Close the connection
client.close()

step2.py

from redisvl.query import SQLQuery
from redisvl.index import SearchIndex
from redis import Redis
from redisvl.utils.vectorize import HFTextVectorizer

hf = HFTextVectorizer()
schema = {
    "index": {
        "name": "user_simple",
        "prefix": "user_simple_docs",
        "storage_type": "json",
    },
    "fields": [
        {"name": "user", "type": "tag"},
        {"name": "region", "type": "tag"},
        {"name": "job", "type": "tag"},
        {"name": "job_description", "type": "text"},
        {"name": "age", "type": "numeric"},
        {"name": "office_location", "type": "geo"},
        {
            "name": "job_embedding",
            "type": "vector",
            "attrs": {
                "dims": len(hf.embed("get embed length")),
                "distance_metric": "cosine",
                "algorithm": "flat",
                "datatype": "float32"
            }
        }
    ]
}

sql_str = """
    SELECT user, region, job, age
    FROM user_simple
    WHERE age > 40
    """
sql_query = SQLQuery(sql_str)

client = Redis.from_url("redis://localhost:6379")
index = SearchIndex.from_dict(schema, redis_client=client)
results = index.query(sql_query)
print(results)