Jina Embedder

1from kern.knowledge.knowledge import Knowledge
2from kern.vectordb.pgvector import PgVector
3from kern.knowledge.embedder.jina import JinaEmbedder
4
5# Add embedding to database
6embeddings = JinaEmbedder(id="jina-embeddings-v3").get_embedding("The quick brown fox jumps over the lazy dog.")
7# Print the embeddings and their dimensions
8print(f"Embeddings: {embeddings[:5]}")
9print(f"Dimensions: {len(embeddings)}")
10
11# Use an embedder in a knowledge base
12knowledge = Knowledge(
13    vector_db=PgVector(
14        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
15        table_name="jina_embeddings",
16        embedder=JinaEmbedder(id="jina-embeddings-v3"),
17    ),
18    max_results=2,
19)

1# Configure embedder with custom settings
2embedder = JinaEmbedder(
3    id="jina-embeddings-v3",
4    dimensions=1024,
5    embedding_type="float",
6    late_chunking=True,
7    batch_size=50,
8    timeout=30.0
9)
10
11# Use async methods for better performance
12import asyncio
13
14async def embed_texts():
15    embedder = JinaEmbedder()
16    texts = ["First text", "Second text", "Third text"]
17    
18    # Get embeddings in batches
19    embeddings, usage = await embedder.async_get_embeddings_batch_and_usage(texts)
20    print(f"Generated {len(embeddings)} embeddings")
21    print(f"Usage info: {usage[0]}")
22
23# Run async example
24asyncio.run(embed_texts())