txtai-llamacpp-turbovec.py

# MINIMAL=1 pip install git+https://github.com/neuml/txtai
# pip install llama-cpp-python turbovec
# pip freeze
# diskcache==5.6.3
# Jinja2==3.1.6
# llama_cpp_python==0.3.28
# MarkupSafe==3.0.3
# numpy==2.2.6
# turbovec==0.7.1
# txtai_minimal @ git+https...
# typing_extensions==4.15.0

from txtai import Embeddings
embeddings = Embeddings(
  path="all-MiniLM-L6-v2-Q4_K_M.gguf",
  backend="turbovec",
  content=True
)
embeddings.index([
  "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"
])
embeddings.search("dishonest junk", 1)
# [{
#   'id': '5',
#   'text': 'Make huge profits without work, earn up to $100,000 a day',
#   'score': 0.17288534343242645
# }]