informers 1.0.2 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4ea317272c5054b01616643e7e0f0b2b2fe0c4a87fe8399350a6b8d0a279c5a1
-  data.tar.gz: 530f8aaab9a5ca71811a82adca0272e2ca84525bcf1f60f2209c394cbd0f9c2a
+  metadata.gz: ab4f19adb4d6ca0289784cee6c6cb5235b73a5184abffbeaf44391768be1f0ac
+  data.tar.gz: '0880ce4dced5ce47ceaaa5fee8d10e6324b3fc0a23e05c3da3728414dcc273d9'
 SHA512:
-  metadata.gz: 76059b486e6f6c0b0054450f76813dd4bf12845da6f46e8089585cd1a69be7db86a0acf446cc5a18e48108393403324626f6656d09bdb69083f2651abc0d2448
-  data.tar.gz: f466f5382edd76a7092dc6ada349a3e58fe7eedcd481726ca765f8ddfb4543b7269dab96c00a93d10b0fd67f800afd70a619cfb15d78dde494b29cc13d21ef1a
+  metadata.gz: eb3ee6d16e4e20eca6fae3fae8f97d78ba6bb655d48e2012640d64538785e2a9ff2afb10269cf01db928553438e8fbd08584774ba3f3d08bc25f36cbb971a99a
+  data.tar.gz: '0008441293f2605ec8599135d715093053e21f67f56ba59b730a3bc1f46f04f4a7fabb7fef039f156cd4183011c93b7fc9cab6ba731bf78627244bc4dedcf18d'

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## 1.1.0 (2024-09-17)
+
+- Added more pipelines
+
+## 1.0.3 (2024-08-29)
+
+- Added `model_output` option
+- Improved `model_file_name` option
+
 ## 1.0.2 (2024-08-28)
 
 - Added `embedding` pipeline

data/README.md

@@ -30,10 +30,15 @@ Embedding
 - [intfloat/e5-base-v2](#intfloate5-base-v2)
 - [nomic-ai/nomic-embed-text-v1](#nomic-ainomic-embed-text-v1)
 - [BAAI/bge-base-en-v1.5](#baaibge-base-en-v15)
+- [jinaai/jina-embeddings-v2-base-en](#jinaaijina-embeddings-v2-base-en)
+- [Snowflake/snowflake-arctic-embed-m-v1.5](#snowflakesnowflake-arctic-embed-m-v15)
+- [Xenova/all-mpnet-base-v2](#xenovaall-mpnet-base-v2)
 
-Reranking (experimental)
+Reranking
 
 - [mixedbread-ai/mxbai-rerank-base-v1](#mixedbread-aimxbai-rerank-base-v1)
+- [jinaai/jina-reranker-v1-turbo-en](#jinaaijina-reranker-v1-turbo-en)
+- [BAAI/bge-reranker-base](#baaibge-reranker-base)
 
 ### sentence-transformers/all-MiniLM-L6-v2
 
@@ -72,18 +77,16 @@ doc_score_pairs = docs.zip(scores).sort_by { |d, s| -s }
 [Docs](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1)
 
 ```ruby
-def transform_query(query)
-  "Represent this sentence for searching relevant passages: #{query}"
-end
+query_prefix = "Represent this sentence for searching relevant passages: "
 
-docs = [
-  transform_query("puppy"),
+input = [
   "The dog is barking",
-  "The cat is purring"
+  "The cat is purring",
+  query_prefix + "puppy"
 ]
 
 model = Informers.pipeline("embedding", "mixedbread-ai/mxbai-embed-large-v1")
-embeddings = model.(docs)
+embeddings = model.(input)
 ```
 
 ### Supabase/gte-small
@@ -102,9 +105,12 @@ embeddings = model.(sentences)
 [Docs](https://huggingface.co/intfloat/e5-base-v2)
 
 ```ruby
+doc_prefix = "passage: "
+query_prefix = "query: "
+
 input = [
-  "passage: Ruby is a programming language created by Matz",
-  "query: Ruby creator"
+  doc_prefix + "Ruby is a programming language created by Matz",
+  query_prefix + "Ruby creator"
 ]
 
 model = Informers.pipeline("embedding", "intfloat/e5-base-v2")
@@ -116,9 +122,13 @@ embeddings = model.(input)
 [Docs](https://huggingface.co/nomic-ai/nomic-embed-text-v1)
 
 ```ruby
+doc_prefix = "search_document: "
+query_prefix = "search_query: "
+
 input = [
-  "search_document: The dog is barking",
-  "search_query: puppy"
+  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")
@@ -130,20 +140,57 @@ embeddings = model.(input)
 [Docs](https://huggingface.co/BAAI/bge-base-en-v1.5)
 
 ```ruby
-def transform_query(query)
-  "Represent this sentence for searching relevant passages: #{query}"
-end
+query_prefix = "Represent this sentence for searching relevant passages: "
 
 input = [
-  transform_query("puppy"),
   "The dog is barking",
-  "The cat is purring"
+  "The cat is purring",
+  query_prefix + "puppy"
 ]
 
 model = Informers.pipeline("embedding", "BAAI/bge-base-en-v1.5")
 embeddings = model.(input)
 ```
 
+### jinaai/jina-embeddings-v2-base-en
+
+[Docs](https://huggingface.co/jinaai/jina-embeddings-v2-base-en)
+
+```ruby
+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)
+```
+
+### Snowflake/snowflake-arctic-embed-m-v1.5
+
+[Docs](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5)
+
+```ruby
+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")
+```
+
+### Xenova/all-mpnet-base-v2
+
+[Docs](https://huggingface.co/Xenova/all-mpnet-base-v2)
+
+```ruby
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = Informers.pipeline("embedding", "Xenova/all-mpnet-base-v2")
+embeddings = model.(sentences)
+```
+
 ### mixedbread-ai/mxbai-rerank-base-v1
 
 [Docs](https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v1)
@@ -156,6 +203,30 @@ model = Informers.pipeline("reranking", "mixedbread-ai/mxbai-rerank-base-v1")
 result = model.(query, docs)
 ```
 
+### jinaai/jina-reranker-v1-turbo-en
+
+[Docs](https://huggingface.co/jinaai/jina-reranker-v1-turbo-en)
+
+```ruby
+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)
+```
+
+### BAAI/bge-reranker-base
+
+[Docs](https://huggingface.co/BAAI/bge-reranker-base)
+
+```ruby
+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)
+```
+
 ### Other
 
 You can use the feature extraction pipeline directly.
@@ -165,10 +236,16 @@ model = Informers.pipeline("feature-extraction", "Xenova/all-MiniLM-L6-v2", quan
 embeddings = model.(sentences, pooling: "mean", normalize: true)
 ```
 
-The model files must include `onnx/model.onnx` or `onnx/model_quantized.onnx` ([example](https://huggingface.co/Xenova/all-MiniLM-L6-v2/tree/main/onnx)).
+The model must include a `.onnx` file ([example](https://huggingface.co/Xenova/all-MiniLM-L6-v2/tree/main/onnx)). If the file is not at `onnx/model.onnx` or `onnx/model_quantized.onnx`, use the `model_file_name` option to specify the location.
 
 ## Pipelines
 
+- [Text](#text)
+- [Vision](#vision)
+- [Multimodel](#multimodal)
+
+### Text
+
 Embedding
 
 ```ruby
@@ -176,7 +253,7 @@ embed = Informers.pipeline("embedding")
 embed.("We are very happy to show you the 🤗 Transformers library.")
 ```
 
-Reranking (experimental)
+Reranking
 
 ```ruby
 rerank = Informers.pipeline("reranking")
@@ -204,6 +281,48 @@ qa = Informers.pipeline("question-answering")
 qa.("Who invented Ruby?", "Ruby is a programming language created by Matz")
 ```
 
+Zero-shot classification
+
+```ruby
+classifier = Informers.pipeline("zero-shot-classification")
+classifier.("text", ["label1", "label2", "label3"])
+```
+
+Text generation
+
+```ruby
+generator = Informers.pipeline("text-generation")
+generator.("I enjoy walking with my cute dog,")
+```
+
+Text-to-text generation
+
+```ruby
+text2text = Informers.pipeline("text2text-generation")
+text2text.("translate from English to French: I'm very happy")
+```
+
+Translation
+
+```ruby
+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")
+```
+
+Summarization
+
+```ruby
+summarizer = Informers.pipeline("summarization")
+summarizer.("Many paragraphs of text")
+```
+
+Fill mask
+
+```ruby
+unmasker = Informers.pipeline("fill-mask")
+unmasker.("Paris is the [MASK] of France.")
+```
+
 Feature extraction
 
 ```ruby
@@ -211,6 +330,80 @@ extractor = Informers.pipeline("feature-extraction")
 extractor.("We are very happy to show you the 🤗 Transformers library.")
 ```
 
+### Vision
+
+Image classification
+
+```ruby
+classifier = Informers.pipeline("image-classification")
+classifier.("image.jpg")
+```
+
+Zero-shot image classification
+
+```ruby
+classifier = Informers.pipeline("zero-shot-image-classification")
+classifier.("image.jpg", ["label1", "label2", "label3"])
+```
+
+Image segmentation
+
+```ruby
+segmenter = Informers.pipeline("image-segmentation")
+segmenter.("image.jpg")
+```
+
+Object detection
+
+```ruby
+detector = Informers.pipeline("object-detection")
+detector.("image.jpg")
+```
+
+Zero-shot object detection
+
+```ruby
+detector = Informers.pipeline("zero-shot-object-detection")
+detector.("image.jpg", ["label1", "label2", "label3"])
+```
+
+Depth estimation
+
+```ruby
+estimator = Informers.pipeline("depth-estimation")
+estimator.("image.jpg")
+```
+
+Image-to-image
+
+```ruby
+upscaler = Informers.pipeline("image-to-image")
+upscaler.("image.jpg")
+```
+
+Image feature extraction
+
+```ruby
+extractor = Informers.pipeline("image-feature-extraction")
+extractor.("image.jpg")
+```
+
+### Multimodal
+
+Image captioning
+
+```ruby
+captioner = Informers.pipeline("image-to-text")
+captioner.("image.jpg")
+```
+
+Document question answering
+
+```ruby
+qa = Informers.pipeline("document-question-answering")
+qa.("image.jpg", "What is the invoice number?")
+```
+
 ## Credits
 
 This library was ported from [Transformers.js](https://github.com/xenova/transformers.js) and is available under the same license.
@@ -250,5 +443,6 @@ To get started with development:
 git clone https://github.com/ankane/informers.git
 cd informers
 bundle install
+bundle exec rake download:files
 bundle exec rake test
 ```

data/lib/informers/configs.rb

@@ -1,17 +1,19 @@
 module Informers
   class PretrainedConfig
-    attr_reader :model_type, :problem_type, :id2label
-
     def initialize(config_json)
-      @is_encoder_decoder = false
-
-      @model_type = config_json["model_type"]
-      @problem_type = config_json["problem_type"]
-      @id2label = config_json["id2label"]
+      @config_json = config_json.to_h
     end
 
     def [](key)
-      instance_variable_get("@#{key}")
+      @config_json[key.to_s]
+    end
+
+    def []=(key, value)
+      @config_json[key.to_s] = value
+    end
+
+    def to_h
+      @config_json.to_h
     end
 
     def self.from_pretrained(

data/lib/informers/model.rb

@@ -1,24 +1,12 @@
 module Informers
   class Model
     def initialize(model_id, quantized: false)
-      @model_id = model_id
       @model = Informers.pipeline("embedding", model_id, quantized: quantized)
+      @options = model_id == "mixedbread-ai/mxbai-embed-large-v1" ? {pooling: "cls", normalize: false} : {}
     end
 
     def embed(texts)
-      is_batched = texts.is_a?(Array)
-      texts = [texts] unless is_batched
-
-      case @model_id
-      when "sentence-transformers/all-MiniLM-L6-v2", "Xenova/all-MiniLM-L6-v2", "Xenova/multi-qa-MiniLM-L6-cos-v1", "Supabase/gte-small"
-        output = @model.(texts)
-      when "mixedbread-ai/mxbai-embed-large-v1"
-        output = @model.(texts, pooling: "cls", normalize: false)
-      else
-        raise Error, "Use the embedding pipeline for this model: #{@model_id}"
-      end
-
-      is_batched ? output : output[0]
+      @model.(texts, **@options)
     end
   end
 end