4. Redis

This is a tutorial on using Redis.

See RedisContextStorage class for storing you users’ contexts in Redis database.

Chatsky uses redis.asyncio library for asynchronous access to Redis DB.

# installing dependencies
%pip install -q chatsky[redis]

Note: you may need to restart the kernel to use updated packages.

import os

from chatsky.context_storages import context_storage_factory

from chatsky import Pipeline
from chatsky.utils.testing.common import (
    check_happy_path,
    is_interactive_mode,
)
from chatsky.utils.testing.toy_script import TOY_SCRIPT_KWARGS, HAPPY_PATH

db_uri = "redis://{}:{}@localhost:6379/{}".format(
    "", os.environ["REDIS_PASSWORD"], "0"
)
db = context_storage_factory(db_uri)


pipeline = Pipeline(**TOY_SCRIPT_KWARGS, context_storage=db)

if __name__ == "__main__":
    check_happy_path(pipeline, HAPPY_PATH, printout=True)
    if is_interactive_mode():
        pipeline.run()

USER: text='Hi'
BOT : text='Hi, how are you?'
USER: text='i'm fine, how are you?'
BOT : text='Good. What do you want to talk about?'
USER: text='Let's talk about music.'
BOT : text='Sorry, I can not talk about music now.'
USER: text='Ok, goodbye.'
BOT : text='bye'
USER: text='Hi'
BOT : text='Hi, how are you?'