Why txtai?

why why

New vector databases, LLM frameworks and everything in between are sprouting up daily. Why build with txtai?

  • Up and running in minutes with pip or Docker

    1. # Get started in a couple lines
    2. import txtai
    4. embeddings = txtai.Embeddings()
    5. embeddings.index(["Correct", "Not what we hoped"])
    6. embeddings.search("positive", 1)
    7. #[(0, 0.29862046241760254)]

  • Built-in API makes it easy to develop applications using your programming language of choice

    1. # app.yml
    2. embeddings:
    3.     path: sentence-transformers/all-MiniLM-L6-v2
    1. CONFIG=app.yml uvicorn "txtai.api:app"
    2. curl -X GET "http://localhost:8000/search?query=positive"

  • Run local - no need to ship data off to disparate remote services

  • Work with micromodels all the way up to large language models (LLMs)
  • Low footprint - install additional dependencies and scale up when needed
  • Learn by example - notebooks cover all available functionality