gem "informers"

sentences = ["This is an example sentence", "Each sentence is converted"]

model = Informers.pipeline("embedding", "sentence-transformers/all-MiniLM-L6-v2")
embeddings = model.(sentences)

query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]

model = Informers.pipeline("embedding", "sentence-transformers/multi-qa-MiniLM-L6-cos-v1")
query_embedding = model.(query)
doc_embeddings = model.(docs)
scores = doc_embeddings.map { |e| e.zip(query_embedding).sum { |d, q| d * q } }
doc_score_pairs = docs.zip(scores).sort_by { |d, s| -s }

sentences = ["This is an example sentence", "Each sentence is converted"]

model = Informers.pipeline("embedding", "sentence-transformers/all-mpnet-base-v2")
embeddings = model.(sentences)

sentences = ["This is an example sentence", "Each sentence is converted"]

model = Informers.pipeline("embedding", "sentence-transformers/paraphrase-MiniLM-L6-v2")
embeddings = model.(sentences, normalize: false)

query_prefix = "Represent this sentence for searching relevant passages: "

input = [
  "The dog is barking",
  "The cat is purring",
  query_prefix + "puppy"
]

model = Informers.pipeline("embedding", "mixedbread-ai/mxbai-embed-large-v1")
embeddings = model.(input)

sentences = ["That is a happy person", "That is a very happy person"]

model = Informers.pipeline("embedding", "Supabase/gte-small")
embeddings = model.(sentences)

doc_prefix = "passage: "
query_prefix = "query: "

input = [
  doc_prefix + "Ruby is a programming language created by Matz",
  query_prefix + "Ruby creator"
]

model = Informers.pipeline("embedding", "intfloat/e5-base-v2")
embeddings = model.(input)

doc_prefix = "search_document: "
query_prefix = "search_query: "

input = [
  doc_prefix + "The dog is barking",
  doc_prefix + "The cat is purring",
  query_prefix + "puppy"
]

model = Informers.pipeline("embedding", "nomic-ai/nomic-embed-text-v1")
embeddings = model.(input)

query_prefix = "Represent this sentence for searching relevant passages: "

input = [
  "The dog is barking",
  "The cat is purring",
  query_prefix + "puppy"
]

model = Informers.pipeline("embedding", "BAAI/bge-base-en-v1.5")
embeddings = model.(input)

sentences = ["How is the weather today?", "What is the current weather like today?"]

model = Informers.pipeline("embedding", "jinaai/jina-embeddings-v2-base-en", model_file_name: "../model")
embeddings = model.(sentences)

query_prefix = "Represent this sentence for searching relevant passages: "

input = [
  "The dog is barking",
  "The cat is purring",
  query_prefix + "puppy"
]

model = Informers.pipeline("embedding", "Snowflake/snowflake-arctic-embed-m-v1.5")
embeddings = model.(input, model_output: "sentence_embedding", pooling: "none")

query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]

model = Informers.pipeline("reranking", "mixedbread-ai/mxbai-rerank-base-v1")
result = model.(query, docs)

query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]

model = Informers.pipeline("reranking", "jinaai/jina-reranker-v1-turbo-en")
result = model.(query, docs)

query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]

model = Informers.pipeline("reranking", "BAAI/bge-reranker-base")
result = model.(query, docs)

query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]

model = Informers.pipeline("reranking", "Xenova/ms-marco-MiniLM-L-6-v2")
result = model.(query, docs)

embed = Informers.pipeline("embedding")
embed.("We are very happy to show you the 🤗 Transformers library.")

rerank = Informers.pipeline("reranking")
rerank.("Who created Ruby?", ["Matz created Ruby", "Another doc"])

ner = Informers.pipeline("ner")
ner.("Ruby is a programming language created by Matz")

classifier = Informers.pipeline("sentiment-analysis")
classifier.("We are very happy to show you the 🤗 Transformers library.")

qa = Informers.pipeline("question-answering")
qa.("Who invented Ruby?", "Ruby is a programming language created by Matz")

classifier = Informers.pipeline("zero-shot-classification")
classifier.("text", ["label1", "label2", "label3"])

generator = Informers.pipeline("text-generation")
generator.("I enjoy walking with my cute dog,")

text2text = Informers.pipeline("text2text-generation")
text2text.("translate from English to French: I'm very happy")

translator = Informers.pipeline("translation", "Xenova/nllb-200-distilled-600M")
translator.("जीवन एक चॉकलेट बॉक्स की तरह है।", src_lang: "hin_Deva", tgt_lang: "fra_Latn")

summarizer = Informers.pipeline("summarization")
summarizer.("Many paragraphs of text")

unmasker = Informers.pipeline("fill-mask")
unmasker.("Paris is the [MASK] of France.")

extractor = Informers.pipeline("feature-extraction")
extractor.("We are very happy to show you the 🤗 Transformers library.")

classifier = Informers.pipeline("image-classification")
classifier.("image.jpg")

classifier = Informers.pipeline("zero-shot-image-classification")
classifier.("image.jpg", ["label1", "label2", "label3"])

segmenter = Informers.pipeline("image-segmentation")
segmenter.("image.jpg")

detector = Informers.pipeline("object-detection")
detector.("image.jpg")

detector = Informers.pipeline("zero-shot-object-detection")
detector.("image.jpg", ["label1", "label2", "label3"])

estimator = Informers.pipeline("depth-estimation")
estimator.("image.jpg")

upscaler = Informers.pipeline("image-to-image")
upscaler.("image.jpg")

extractor = Informers.pipeline("image-feature-extraction")
extractor.("image.jpg")

classifier = Informers.pipeline("audio-classification")
classifier.("audio.wav")

captioner = Informers.pipeline("image-to-text")
captioner.("image.jpg")

qa = Informers.pipeline("document-question-answering")
qa.("image.jpg", "What is the invoice number?")

Informers.pipeline("embedding", "Xenova/all-MiniLM-L6-v2", dtype: "fp16")

Informers.pipeline("embedding", device: "cuda")

Informers.pipeline("embedding", session_options: {log_severity_level: 2})

# before
model = Informers::SentimentAnalysis.new("sentiment-analysis.onnx")
model.predict("This is super cool")

# after
model = Informers.pipeline("sentiment-analysis")
model.("This is super cool")