Ollama を使用したベクトル検索の実装部分

services:
  db:
    # ... (existing db service)

  ollama:
    image: ollama/ollama
    container_name: ollama-service
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama

  data_loader:
    # ... (existing data_loader service)
    environment:
      - OLLAMA_HOST=ollama
    depends_on:
      - db
      - ollama

volumes:
  pgdata:
  ollama_data:

docker compose up -d

# Pull the embedding model
docker compose exec ollama ollama pull nomic-embed-text

# Test embedding generation
curl http://localhost:11434/api/embed -d '{
  "model": "nomic-embed-text",
  "input": "Hello World"
}'

-- Connect to the database
docker compose exec db psql -U postgres -d example_db

-- Add a column for Ollama embeddings
ALTER TABLE items
ADD COLUMN embedding_ollama vector(768);

CREATE TABLE items (
    id SERIAL PRIMARY KEY,
    name VARCHAR(255) NOT NULL,
    item_data JSONB,
    embedding vector(1536),        # OpenAI
    embedding_ollama vector(768)   # Ollama
);

ollama==0.3.3

import ollama  # New import

def get_embedding_ollama(text: str):
    """Generate embedding using Ollama API"""
    response = ollama.embed(
        model='nomic-embed-text',
        input=text
    )
    return response["embeddings"][0]

def load_books_to_db():
    """Load books with embeddings into PostgreSQL"""
    books = fetch_books()

    for book in books:
        description = (
            f"Book titled '{book['title']}' by {', '.join(book['authors'])}. "
            f"Published in {book['first_publish_year']}. "
            f"This is a book about {book['subject']}."
        )

        # Generate embeddings with both OpenAI and Ollama
        embedding = get_embedding(description)                # OpenAI
        embedding_ollama = get_embedding_ollama(description)  # Ollama

        # Store in the database
        store_book(book["title"], json.dumps(book), embedding, embedding_ollama)

-- View first 5 dimensions of an embedding
SELECT
    name,
    (replace(replace(embedding_ollama::text, '[', '{'), ']', '}')::float[])[1:5] as first_dimensions
FROM items;

-- Search for books about web development:
WITH web_book AS (
    SELECT embedding_ollama FROM items WHERE name LIKE '%Web%' LIMIT 1
)
SELECT
    item_data->>'title' as title,
    item_data->>'authors' as authors,
    embedding_ollama <=> (SELECT embedding_ollama FROM web_book) as similarity
FROM items
ORDER BY similarity
LIMIT 3;

CREATE INDEX ON items
USING ivfflat (embedding_ollama vector_cosine_ops)
WITH (lists = 100);

data_loader:
  environment:
    - OLLAMA_HOST=ollama

docker compose exec ollama ollama pull nomic-embed-text