💎 ruby-spacy

gem 'ruby-spacy'

py_nlp = PyCall.import_module("spacy_stanza").load_pipeline("ar")
nlp = Spacy::Language.new(py_nlp: py_nlp)
nlp.read("...").tokens # works like any other nlp

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("en_core_web_sm")

doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")

row = []

doc.each do |token|
  row << token.text
end

headings = [1,2,3,4,5,6,7,8,9,10]
table = Terminal::Table.new rows: [row], headings: headings

puts table

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")

headings = ["text", "lemma", "pos", "tag", "dep"]
rows = []

doc.each do |token|
  rows << [token.text, token.lemma, token.pos, token.tag, token.dep]
end

table = Terminal::Table.new rows: rows, headings: headings
puts table

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("ja_core_news_lg")
doc = nlp.read("任天堂は1983年にファミコンを14,800円で発売した。")

headings = ["text", "lemma", "pos", "tag", "dep"]
rows = []

doc.each do |token|
  rows << [token.text, token.lemma, token.pos, token.tag, token.dep]
end

table = Terminal::Table.new rows: rows, headings: headings
puts table

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("Apple is looking at buying U.K. startup for $1 billion")

headings = ["text", "shape", "is_alpha", "is_stop", "morphology"]
rows = []

doc.each do |token|
  morph = token.morphology.map do |k, v|
    "#{k} = #{v}"
  end.join("\n")
  rows << [token.text, token.shape, token.is_alpha, token.is_stop, morph]
end

table = Terminal::Table.new rows: rows, headings: headings
puts table

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")

sentence = "Autonomous cars shift insurance liability toward manufacturers"
doc = nlp.read(sentence)

dep_svg = doc.displacy(style: "dep", compact: false)

File.open(File.join("test_dep.svg"), "w") do |file|
  file.write(dep_svg)
end

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")

sentence = "Autonomous cars shift insurance liability toward manufacturers"
doc = nlp.read(sentence)

dep_svg = doc.displacy(style: "dep", compact: true)

File.open(File.join("test_dep_compact.svg"), "w") do |file|
  file.write(dep_svg)
end

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("The quick brown fox jumped over the lazy dog near the river.")

doc.syntax_tree                          # => "[S [%NP [DET The] [ADJ quick] ...] ...]"
File.binwrite("tree.png", doc.syntax_tree(format: :png))
doc.syntax_tree(style: :chunks)          # shallow tree with noun chunks
doc.syntax_tree(morphology: true)        # attach morphology tables to the leaves

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("en_core_web_sm")
doc =nlp.read("Apple is looking at buying U.K. startup for $1 billion")

rows = []

doc.ents.each do |ent|
  rows << [ent.text, ent.start_char, ent.end_char, ent.label]
end

headings = ["text", "start_char", "end_char", "label"]
table = Terminal::Table.new rows: rows, headings: headings
puts table

require( "ruby-spacy")
require "terminal-table"

nlp = Spacy::Language.new("ja_core_news_lg")

sentence = "任天堂は1983年にファミコンを14,800円で発売した。"
doc = nlp.read(sentence)

rows = []

doc.ents.each do |ent|
  rows << [ent.text, ent.start_char, ent.end_char, ent.label]
end

headings = ["text", "start", "end", "label"]
table = Terminal::Table.new rows: rows, headings: headings
print table

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("en_core_web_lg")
doc = nlp.read("dog cat banana afskfsd")

rows = []

doc.each do |token|
  rows << [token.text, token.has_vector, token.vector_norm, token.is_oov]
end

headings = ["text", "has_vector", "vector_norm", "is_oov"]
table = Terminal::Table.new rows: rows, headings: headings
puts table

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_lg")
doc1 = nlp.read("I like salty fries and hamburgers.")
doc2 = nlp.read("Fast food tastes very good.")

puts "Doc 1: " + doc1.text
puts "Doc 2: " + doc2.text
puts "Similarity: #{doc1.similarity(doc2)}"

require "ruby-spacy"

nlp = Spacy::Language.new("ja_core_news_lg")
ja_doc1 = nlp.read("今日は雨ばっかり降って、嫌な天気ですね。")
puts "doc1: #{ja_doc1.text}"
ja_doc2 = nlp.read("あいにくの悪天候で残念です。")
puts "doc2: #{ja_doc2.text}"
puts "Similarity: #{ja_doc1.similarity(ja_doc2)}"

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("en_core_web_lg")

tokyo = nlp.get_lexeme("Tokyo")
japan = nlp.get_lexeme("Japan")
france = nlp.get_lexeme("France")

query = tokyo.vector - japan.vector + france.vector

headings = ["rank", "text", "score"]
rows = []

results = nlp.most_similar(query, 10)
results.each_with_index do |lexeme, i|
  index = (i + 1).to_s
  rows << [index, lexeme.text, lexeme.score]
end

table = Terminal::Table.new rows: rows, headings: headings
puts table

require "ruby-spacy"
require "terminal-table"

nlp = Spacy::Language.new("ja_core_news_lg")

tokyo = nlp.get_lexeme("東京")
japan = nlp.get_lexeme("日本")
france = nlp.get_lexeme("フランス")

query = tokyo.vector - japan.vector + france.vector

headings = ["rank", "text", "score"]
rows = []

results = nlp.most_similar(query, 10)
results.each_with_index do |lexeme, i|
  index = (i + 1).to_s
  rows << [index, lexeme.text, lexeme.score]
end

table = Terminal::Table.new rows: rows, headings: headings
puts table

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")

matcher = nlp.matcher
matcher.add("GREETING", [[{ LOWER: "hello" }, { IS_PUNCT: true }, { LOWER: "world" }]])

doc = nlp.read("Hello, world!")
matcher.match(doc).each do |match|
  span = doc.span(match[:start_index]..match[:end_index])
  puts "#{match[:label]}: #{span.text}"
end
# => GREETING: Hello, world

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")

# Create a phrase matcher
matcher = nlp.phrase_matcher
matcher.add("PRODUCT", ["iPhone", "MacBook Pro", "iPad"])

doc = nlp.read("I bought an iPhone and a MacBook Pro yesterday.")
matches = matcher.match(doc)

matches.each do |span|
  puts "#{span.text} => #{span.label}"
end
# => iPhone => PRODUCT
# => MacBook Pro => PRODUCT

# Use attr: "LOWER" for case-insensitive matching
matcher = nlp.phrase_matcher(attr: "LOWER")
matcher.add("COMPANY", ["apple", "google", "microsoft"])

doc = nlp.read("Apple and GOOGLE are competitors of Microsoft.")
matches = matcher.match(doc)

matches.each do |span|
  puts span.text
end
# => Apple
# => GOOGLE
# => Microsoft

matcher = nlp.phrase_matcher(attr: "LOWER")
matcher.add("TECH_COMPANY", ["apple", "google", "microsoft", "amazon"])
matcher.add("PRODUCT", ["iphone", "pixel", "surface", "kindle"])

doc = nlp.read("Apple released the new iPhone while Google announced Pixel updates.")
matches = matcher.match(doc)

matches.each do |span|
  puts "#{span.text}: #{span.label}"
end
# => Apple: TECH_COMPANY
# => iPhone: PRODUCT
# => Google: TECH_COMPANY
# => Pixel: PRODUCT

require "ruby-spacy"

api_key = ENV["OPENAI_API_KEY"]
nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("The Beatles released 12 studio albums")

# default parameter values
# max_completion_tokens: 1000
# model: "gpt-5-mini"
res1 = doc.openai_query(
  access_token: api_key,
  prompt: "Translate the text to Japanese."
)
puts res1

require "ruby-spacy"

api_key = ENV["OPENAI_API_KEY"]
nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("The Beatles were an English rock band formed in Liverpool in 1960.")

# default parameter values
# max_completion_tokens: 1000
# model: "gpt-5-mini"
res = doc.openai_query(
  access_token: api_key,
  prompt: "Extract the topic of the document and list 10 entities (names, concepts, locations, etc.) that are relevant to the topic."
)

require "ruby-spacy"

api_key = ENV["OPENAI_API_KEY"]
nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("The Beatles released 12 studio albums")

# default parameter values
# max_completion_tokens: 1000
# model: "gpt-5-mini"
res = doc.openai_query(
  access_token: api_key,
  prompt: "List token data of each of the words used in the sentence. Add 'meaning' property and value (brief semantic definition) to each token data. Output as a JSON object."
)

require "ruby-spacy"

api_key = ENV["OPENAI_API_KEY"]
nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("The Beatles released 12 studio albums")

# default parameter values
# max_completion_tokens: 1000
# model: "gpt-5-mini"
res = doc.openai_query(
  access_token: api_key,
  prompt: "Generate a tree diagram from the text using given token data. Use the following bracketing style: [S [NP [Det the] [N cat]] [VP [V sat] [PP [P on] [NP the mat]]]"
)
puts res

require "ruby-spacy"

api_key = ENV["OPENAI_API_KEY"]
nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("Vladimir Nabokov was a")

# default parameter values
# max_completion_tokens: 1000
# model: "gpt-5-mini"
res = doc.openai_completion(access_token: api_key)
puts res

require "ruby-spacy"

api_key = ENV["OPENAI_API_KEY"]
nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("Vladimir Nabokov was a Russian-American novelist, poet, translator and entomologist.")

# default model: text-embedding-3-small
res = doc.openai_embeddings(access_token: api_key)

puts res

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("Apple Inc. was founded by Steve Jobs in California.")

nlp.with_openai(model: "gpt-5-mini") do |ai|
  result = ai.chat(
    system: "You are a linguistic analyst. Analyze the given linguistic data.",
    user: doc.linguistic_summary
  )
  puts result
end

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")
texts = ["The bank approved the loan.", "I sat on the river bank."]

nlp.with_openai(model: "gpt-5-mini") do |ai|
  nlp.pipe(texts).each do |doc|
    result = ai.chat(
      system: "Identify the meaning of 'bank' in one word based on the linguistic context.",
      user: doc.linguistic_summary
    )
    puts "#{doc.text} => #{result}"
  end
end

# Include sentences and morphology, exclude noun chunks
summary = doc.linguistic_summary(
  sections: [:text, :tokens, :entities, :sentences],
  token_attributes: [:text, :lemma, :pos, :dep, :head, :morphology]
)

nlp.with_openai do |ai|
  vector = ai.embeddings("Hello world")
  puts vector.length  # => 1536
end

# Requires the ANTHROPIC_API_KEY environment variable
# Default model: claude-sonnet-5 (override with model: "...")
nlp.with_llm(provider: :anthropic) do |ai|
  result = ai.chat(
    system: "You are a linguistic analyst.",
    user: doc.linguistic_summary
  )
  puts result
end

# Requires a running Ollama server: https://ollama.com
nlp.with_llm(provider: :ollama, model: "llama3.2") do |ai|
  puts ai.chat(user: doc.linguistic_summary)
end

nlp.with_llm(provider: :openai, base_url: "http://localhost:1234/v1",
             access_token: "not-needed", model: "your-model") do |ai|
  puts ai.chat(user: "Hello!")
end

schema = {
  type: "object",
  properties: {
    entities: {
      type: "array",
      items: {
        type: "object",
        properties: { text: { type: "string" }, label: { type: "string" } },
        required: %w[text label],
        additionalProperties: false
      }
    }
  },
  required: ["entities"],
  additionalProperties: false
}

result = nlp.with_llm(provider: :openai) do |ai|
  ai.chat(system: "Extract named entities.", user: doc.text, schema: schema)
end
result["entities"].each { |ent| puts "#{ent["text"]} (#{ent["label"]})" }

nlp = Spacy::Language.new("en_core_web_sm", timeout: 120) # Set timeout to 120 seconds

require "ruby-spacy"

nlp = Spacy::Language.new("en_core_web_sm")
doc = nlp.read("Apple Inc. was founded by Steve Jobs in California.")

# Serialize to binary
bytes = doc.to_bytes

# Save to file
File.binwrite("doc_cache.bin", bytes)

nlp = Spacy::Language.new("en_core_web_sm")

# Load from file
bytes = File.binread("doc_cache.bin")

# Restore the document (all annotations are preserved)
restored_doc = Spacy::Doc.from_bytes(nlp, bytes)

puts restored_doc.text
# => "Apple Inc. was founded by Steve Jobs in California."

restored_doc.ents.each do |ent|
  puts "#{ent.text} (#{ent.label})"
end
# => Apple Inc. (ORG)
# => Steve Jobs (PERSON)
# => California (GPE)