Usage

Weaviate

Insert a PDF, search it with an agent, and delete Weaviate records by name or metadata.

Code

weaviate_db.py
from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.search import SearchType
from agno.vectordb.weaviate import Distance, VectorIndex, Weaviate

vector_db = Weaviate(
    collection="vectors",
    search_type=SearchType.vector,
    vector_index=VectorIndex.HNSW,
    distance=Distance.COSINE,
    local=False,  # Set to True if using Weaviate locally
)

# Create Knowledge Instance with Weaviate
knowledge = Knowledge(
    name="Basic SDK Knowledge Base",
    description="Agno 2.0 Knowledge Implementation with Weaviate",
    vector_db=vector_db,
)

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

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

# Delete operations
vector_db.delete_by_name("Recipes")
# or
vector_db.delete_by_metadata({"doc_type": "recipe_book"})

Usage

Set up your virtual environment

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

Install dependencies

uv pip install -U weaviate-client pypdf openai agno

Setup Weaviate

# 1. Create account at https://console.weaviate.cloud/
# 2. Create a cluster and copy the "REST endpoint" and "Admin" API Key
# 3. Set environment variables:
export WCD_URL="your-cluster-url"
export WCD_API_KEY="your-api-key"
# 4. Set local=False in the code

Set environment variables

export OPENAI_API_KEY=xxx

Run Agent

python weaviate_db.py

Overview

Use Weaviate as a vector database for your Knowledge Base.

Weaviate Async

Insert knowledge and run an agent with Agno's async methods and a Weaviate backend.