davidmezzetti

data = ["Giants hit 3 HRs to down Dodgers",
        "Giants 5 Dodgers 4 final",
        "Dodgers drop Game 2 against the Giants, 5-4",
        "Blue Jays beat Red Sox final score 2-1",
        "Red Sox lost to the Blue Jays, 2-1",
        "Blue Jays at Red Sox is over. Score: 2-1",
        "Phillies win over the Braves, 5-0",
        "Phillies 5 Braves 0 final",
        "Final: Braves lose to the Phillies in the series opener, 5-0",
        "Lightning goaltender pulled, lose to Flyers 4-1",

davidmezzetti

embeddings.save("index")

embeddings = Embeddings()
embeddings.load("index")

uid = embeddings.search("climate change", 1)[0][0]
print(data[uid])

davidmezzetti

from tldrstory.source.source import Source

class Neuspo(Source):
    """
    Articles have the following schema:
        uid - unique id
        source - source name
        date - article date
        title - article title
        url - reference url for data

davidmezzetti

# GitHub Actions build workflow
name: build

on: ["push", "pull_request"]

jobs:
  build:
    runs-on: ubuntu-latest

    steps:

davidmezzetti

# GitHub Actions build workflow
name: build

on: ["push", "pull_request"]

jobs:
  build:
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:

davidmezzetti

from txtai.pipeline import Summary

# Create summary model
summary = Summary()

text = ("Search is the base of many applications. Once data starts to pile up, users want to be able to find it. It’s the foundation "
       "of the internet and an ever-growing challenge that is never solved or done. The field of Natural Language Processing (NLP) is "
       "rapidly evolving with a number of new developments. Large-scale general language models are an exciting new capability "
       "allowing us to add amazing functionality quickly with limited compute and people. Innovation continues with new models "
       "and advancements coming in at what seems a weekly basis. This article introduces txtai, an AI-powered search engine "

davidmezzetti

from txtai.pipeline import Textractor

# Create textractor model
textractor = Textractor()

textractor("txtai/article.pdf")

davidmezzetti

from txtai.pipeline import Transcription

# Create transcription model
transcribe = Transcription("facebook/wav2vec2-large-960h")

transcribe("Make_huge_profits.wav")

davidmezzetti

from txtai.pipeline import Translation

# Create translation model
translate = Translation()

translate("This is a test translation into Spanish", "es")

davidmezzetti

from txtai.embeddings import Embeddings
    
embeddings = Embeddings({"method": "sentence-transformers", "path": "clip-ViT-B-32"})
embeddings.index(images(directory))
    
embeddings.search(query, 1)