Redis

Insert a PDF into a Redis knowledge base, query it with an agent, and delete content by name.

Code

redis_db.py
import os

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.redis import RedisDB, SearchType

# Configure Redis connection
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379/0")
INDEX_NAME = os.getenv("REDIS_INDEX", "agno_cookbook_vectors")

# Initialize Redis Vector DB
vector_db = RedisDB(
    index_name=INDEX_NAME,
    redis_url=REDIS_URL,
    search_type=SearchType.vector,  # try SearchType.hybrid for hybrid search
)

contents_db = PostgresDb(
    db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    knowledge_table="knowledge_contents",
)

knowledge = Knowledge(
    name="My Redis Vector Knowledge Base",
    description="This is a knowledge base that uses a Redis Vector DB",
    vector_db=vector_db,
    contents_db=contents_db,
)

knowledge.insert(
    name="Recipes",
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
    metadata={"doc_type": "recipe_book"},
)

agent = Agent(knowledge=knowledge)
agent.print_response("List down the ingredients to make Massaman Gai", markdown=True)

vector_db.delete_by_name("Recipes")

Redis metadata deletion requires tag fields that are both stored on each vector document and indexed. The adapter does not index doc_type, and this URL-ingestion path does not merge the caller metadata into each stored vector document. Use the demonstrated delete_by_name for these recipe chunks.

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Install dependencies

uv pip install -U redis redisvl sqlalchemy psycopg pypdf openai agno

Run Redis

docker run -d --name my-redis -p 6379:6379 -p 8001:8001 redis/redis-stack:latest

Run PgVector

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql \
  -v pgvolume:/var/lib/postgresql \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:18

Set environment variables

export OPENAI_API_KEY=xxx

Run Agent

python redis_db.py