Ollama Embedder

Code

1from kern.knowledge.embedder.ollama import OllamaEmbedder
2from kern.knowledge.knowledge import Knowledge
3from kern.vectordb.pgvector import PgVector
4
5embeddings = OllamaEmbedder().get_embedding(
6    "The quick brown fox jumps over the lazy dog."
7)
8
9# Print the embeddings and their dimensions
10print(f"Embeddings: {embeddings[:5]}")
11print(f"Dimensions: {len(embeddings)}")
12
13# Example usage:
14knowledge = Knowledge(
15    vector_db=PgVector(
16        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
17        table_name="ollama_embeddings",
18        embedder=OllamaEmbedder(),
19    ),
20    max_results=2,
21)

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Install Ollama

Follow the installation instructions at Ollama's website

Install dependencies

1uv pip install -U sqlalchemy psycopg pgvector kern-ai

Run PgVector

1docker run -d \
2  -e POSTGRES_DB=ai \
3  -e POSTGRES_USER=ai \
4  -e POSTGRES_PASSWORD=ai \
5  -e PGDATA=/var/lib/postgresql/data/pgdata \
6  -v pgvolume:/var/lib/postgresql/data \
7  -p 5532:5432 \
8  --name pgvector \
9  agnohq/pgvector:16

Run Agent

1python cookbook/08_knowledge/embedders/ollama_embedder.py

1python cookbook/08_knowledge/embedders/ollama_embedder.py