davidmezzetti

from txtai import Embeddings

# SQLite + NumPy
embeddings = Embeddings(content=True, backend="numpy")
embeddings.index(["test"])
embeddings.save("test")

# SQLite File
# sqlite3 test/documents "SELECT * FROM sections"
# 0|0|test||2026-01-16 16:12:03.410194+00:00

davidmezzetti

# Install TxtAI with Torch CPU
pip install txtai torch==2.9.1+cpu -f https://download.pytorch.org/whl/torch

# Disk usage is much less
# Torch CPU  = 1.1G
# Torch CUDA = 6.9G

# Number of installed packages is also less
# Torch CPU  = 27
# Torch CUDA = 43

davidmezzetti

#
# pip install ai-edge-torch txtai
#
# See https://github.com/google-ai-edge/ai-edge-torch

import torch
import ai_edge_torch

import numpy as np

davidmezzetti

from txtai import Embeddings
from txtai.pipeline import HFOnnx

# Export as quantized onnx model
# Model Size = 1.1 MB!
path = HFOnnx()( 
  "neuml/biomedbert-hash-nano-embeddings",
  "pooling", "model.onnx", True
)

davidmezzetti

from txtai import Embeddings

# Load the 100K most viewed Wikipedia articles
embeddings = Embeddings()
embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia-slim")

# Show a random article
embeddings.search("""
  SELECT id, text, 'https://en.wikipedia.org/wiki/' || replace(id, ' ', '_') url 
  FROM txtai

davidmezzetti

from txtai import Agent

# Define tools
tools = [
    "websearch",  # Runs a websearch using default engine
    "webview",  # Loads a web page
]

# Define LLM
model = "Qwen/Qwen3-4B-Instruct-2507"

davidmezzetti

import numpy as np
from txtai.ann import ANNFactory

# Index 10M vectors using llama.cpp style quants
ann = None
for _ in range(1000):
  # Generate batch of vectors
  batch = np.random.rand(10000, 768).astype(np.float32)

  if not ann:

davidmezzetti

# RAG Quick Start
# Easy to use way to get started with RAG using YOUR data
#
# For a complete application see this: https://github.com/neuml/rag
#
# TxtAI has 70+ example notebooks covering everything the framework provides
# Examples: https://neuml.github.io/txtai/examples
#
# Install TxtAI
# pip install txtai[pipeline-data]

davidmezzetti

import soundfile as sf

from txtai.pipeline import TextToAudio

# Create and run pipeline (Note that model is CC-BY-NC)
tta = TextToAudio("facebook/musicgen-stereo-medium")
speech, rate = tta("Happy 80s rock and synth for a fun startup company")

# Write to file
sf.write("out.wav", speech.T, rate)

davidmezzetti

import soundfile as sf

from txtai.pipeline import TextToSpeech

# Build pipeline
tts = TextToSpeech("neuml/kokoro-int8-onnx")

# Generate speech
speech, rate = tts(
    """Have you ever considered having a snooty British accent?