Code
from agno.agent import AgentKnowledge
from agno.embedder.google import GeminiEmbedder
from agno.vectordb.pgvector import PgVector
embeddings = GeminiEmbedder().get_embedding(
"The quick brown fox jumps over the lazy dog."
)
# Print the embeddings and their dimensions
print(f"Embeddings: {embeddings[:5]}")
print(f"Dimensions: {len(embeddings)}")
# Example usage:
knowledge_base = AgentKnowledge(
vector_db=PgVector(
db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
table_name="gemini_embeddings",
embedder=GeminiEmbedder(dimensions=1536),
),
num_documents=2,
)
Usage
1
Create a virtual environment
Open the
Terminal and create a python virtual environment.python3 -m venv .venv
source .venv/bin/activate
python3 -m venv .venv
.venv/scripts/activate
2
Set your API key
export GOOGLE_API_KEY=xxx
3
Install libraries
pip install -U sqlalchemy 'psycopg[binary]' pgvector google-generativeai agno
4
Run PgVector
docker run -d \
-e POSTGRES_DB=ai \
-e POSTGRES_USER=ai \
-e POSTGRES_PASSWORD=ai \
-e PGDATA=/var/lib/postgresql/data/pgdata \
-v pgvolume:/var/lib/postgresql/data \
-p 5532:5432 \
--name pgvector \
agnohq/pgvector:16
5
Run Agent
python cookbook/agent_concepts/knowledge/embedders/gemini_embedder.py
python cookbook/agent_concepts/knowledge/embedders/gemini_embedder.py