txtai-content-storage.py

from txtai.embeddings import Embeddings

data = ["US tops 5 million confirmed virus cases",
        "Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg",
        "Beijing mobilises invasion craft along coast as Taiwan tensions escalate",
        "The National Park Service warns against sacrificing slower friends in a bear attack",
        "Maine man wins $1M from $25 lottery ticket",
        "Make huge profits without work, earn up to $100,000 a day"]

# Create embeddings index with content enabled. The default behavior is to only store indexed vectors.
embeddings = Embeddings({"path": "sentence-transformers/nli-mpnet-base-v2", "content": True, "objects": True})

# Create an index for the list of text
embeddings.index([(uid, text, None) for uid, text in enumerate(data)])

print("%-20s %s" % ("Query", "Best Match"))
print("-" * 50)

# Run an embeddings search for each query
for query in ("feel good story", "climate change", "public health story", "war", "wildlife", "asia", "lucky", "dishonest junk"):
    # Extract text field from result
    text = embeddings.search(query, 1)[0]["text"]

    # Print text
    print("%-20s %s" % (query, text))