cloudflare-ai 0.9.0 → 0.9.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '08feb777620d0767e6ab08f5366c9a207facc25783f9fe497f381e894e02876c'
-  data.tar.gz: cacc6945ed2914fa62280e5afd8a0695f7c108139737e3785cbc74a24d26b79b
+  metadata.gz: c0dbb7a703cef587e4c132ced954abc6be79bb903fe6e2b1d531ae8a1bd22ad9
+  data.tar.gz: f59a67ae6ff4785994269a65bce16f3bc22d284dfc3fcdac5d4d846b70e5e2b7
 SHA512:
-  metadata.gz: 31b20441f2791a3c93a8ccde7d5674e2daaf8190cd348b2c941849b84edc6f04fcef9bfd2a3ef6de8e4c39c3a9d2f03e3388a0f8efd6fc6391ca83fafee111d5
-  data.tar.gz: b695c2971236bb8aa182fe8c36bd63fd9c7303dfda70aee767a098532fbb274e720ed165e73515800b3b64a6a77d5e124b3048dcc2100bff7e039b0245577bbf
+  metadata.gz: 55ab260777dfdfb4427f20e06c2a3522226db63bd869a627ed0abbd7c83948d33f37585f2249c1417ae590b0267934b5ce9e7444df03df95fad8b4d1334c0a12
+  data.tar.gz: 1716e968bf8f7694de57eadf3b003a5e4cd76cb25b240112a8561830c2fe16cd17a769af02662024edb32efc860675520356431cd2dd8cfc132db58ae7c8a165

data/README.md

@@ -194,6 +194,36 @@ result = client.transcribe(audio: File.open("/path/to/audio.wav"))
 #### Result object
 All invocations of the `transcribe` method returns a `Cloudflare::AI::Results::Transcribe`.
 
+### Summarization
+```ruby
+result = client.summarize(text: "This text should be a lot longer.")
+p result.summary # => {"result":{"summary":"Short text"},"success":true,"errors":[],"messages":[]}
+```
+#### Result object
+All invocations of the `summarize` method returns a `Cloudflare::AI::Results::Summarization` object.
+
+### Object detection
+The object detection endpoint accepts either a path to a file or a file stream.
+
+```ruby
+result = client.detect_objects(image: "/path/to/cat.jpg")
+result = client.classify(image: File.open("/path/to/cat.jpg"))
+```
+
+#### Result object
+All invocations of the `detect_objects` method returns a `Cloudflare::AI::Results::ObjectDetection` object.
+
+### Image-to-text
+The captioning endpoint accepts either a path to a file or a file stream.
+
+```ruby
+client.caption(image: "/path/to/cat.jpg").description # => "a cat sitting on a couch"
+client.caption(image: File.open("/path/to/cat.jpg")).description # => "a cat sitting on a couch"
+```
+
+#### Result object
+All invocations of the `caption` method returns a `Cloudflare::AI::Results::ImageToText` object.
+
 # Logging
 
 This gem uses standard logging mechanisms and defaults to `:warn` level. Most messages are at info level, but we will add debug or warn statements as needed.

data/lib/cloudflare/ai/client.rb

@@ -12,6 +12,13 @@ class Cloudflare::AI::Client
     @api_token = api_token
   end
 
+  def caption(image: nil, model_name: Cloudflare::AI::Models.image_to_text.first)
+    url = service_url_for(account_id: account_id, model_name: model_name)
+
+    image = File.open(image) if image.is_a?(String)
+    Cloudflare::AI::Results::ImageToText.new(post_request_with_binary_file(url, image).body)
+  end
+
   def chat(messages:, model_name: default_text_generation_model_name, max_tokens: default_max_tokens, &block)
     url = service_url_for(account_id: account_id, model_name: model_name)
     stream = block ? true : false
@@ -41,6 +48,13 @@ class Cloudflare::AI::Client
     post_streamable_request(url, payload, &block)
   end
 
+  def detect_objects(image: nil, model_name: Cloudflare::AI::Models.object_detection.first)
+    url = service_url_for(account_id: account_id, model_name: model_name)
+
+    image = File.open(image) if image.is_a?(String)
+    Cloudflare::AI::Results::ObjectDetection.new(post_request_with_binary_file(url, image).body)
+  end
+
   def draw(prompt:, num_steps: 20, model_name: Cloudflare::AI::Models.text_to_image.first)
     url = service_url_for(account_id: account_id, model_name: model_name)
     payload = {prompt: prompt, num_steps: num_steps}.to_json
@@ -59,6 +73,13 @@ class Cloudflare::AI::Client
     Cloudflare::AI::Results::TextEmbedding.new(connection.post(url, payload).body)
   end
 
+  def summarize(text:, model_name: Cloudflare::AI::Models.summarization.first, max_tokens: 1024)
+    url = service_url_for(account_id: account_id, model_name: model_name)
+    payload = {input_text: text, max_tokens: max_tokens}.to_json
+
+    Cloudflare::AI::Results::Summarization.new(connection.post(url, payload).body)
+  end
+
   def transcribe(source_url: nil, audio: nil, model_name: Cloudflare::AI::Models.automatic_speech_recognition.first)
     raise ArgumentError, "Must provide either audio_url or audio" if [source_url, audio].compact.size != 1
 

data/lib/cloudflare/ai/models.rb

@@ -1,43 +1,90 @@
 class Cloudflare::AI::Models
   class << self
-    def text_generation
-      %w[@hf/thebloke/llamaguard-7b-awq @hf/thebloke/neural-chat-7b-v3-1-awq @cf/meta/llama-2-7b-chat-fp16 @cf/mistral/mistral-7b-instruct-v0.1 @hf/thebloke/codellama-7b-instruct-awq @cf/meta/llama-2-7b-chat-int8 @hf/thebloke/mistral-7b-instruct-v0.1-awq @hf/thebloke/deepseek-coder-6.7b-base-awq @hf/thebloke/openhermes-2.5-mistral-7b-awq @hf/thebloke/deepseek-coder-6.7b-instruct-awq @hf/thebloke/zephyr-7b-beta-awq]
+    def all
+      {
+        automatic_speech_recognition: automatic_speech_recognition,
+        image_classification: image_classification,
+        image_to_text: image_to_text,
+        object_detection: object_detection,
+        summarization: summarization,
+        text_classification: text_classification,
+        text_embeddings: text_embedding,
+        text_generation: text_generation,
+        text_to_image: text_to_image,
+        translation: translation
+      }
     end
 
     def automatic_speech_recognition
       %w[@cf/openai/whisper]
     end
 
-    def translation
-      %w[@cf/meta/m2m100-1.2b]
+    def image_classification
+      %w[@cf/microsoft/resnet-50]
     end
 
-    def text_classification
-      %w[@cf/huggingface/distilbert-sst-2-int8]
+    def image_to_text
+      %w[@cf/unum/uform-gen2-qwen-500m]
     end
 
-    def image_classification
-      %w[@cf/microsoft/resnet-50]
+    def object_detection
+      %w[@cf/meta/detr-resnet-50]
     end
 
-    def text_to_image
-      %w[@cf/stabilityai/stable-diffusion-xl-base-1.0]
+    def summarization
+      %w[@cf/facebook/bart-large-cnn]
+    end
+
+    def text_classification
+      %w[@cf/huggingface/distilbert-sst-2-int8]
     end
 
     def text_embedding
       %w[@cf/baai/bge-base-en-v1.5 @cf/baai/bge-large-en-v1.5 @cf/baai/bge-small-en-v1.5]
     end
 
-    def all
-      {
-        text_generation: text_generation,
-        automatic_speech_recognition: automatic_speech_recognition,
-        translation: translation,
-        text_classification: text_classification,
-        image_classification: image_classification,
-        text_to_image: text_to_image,
-        text_embeddings: text_embedding
-      }
+    def text_generation
+      %w[
+        @hf/thebloke/codellama-7b-instruct-awq
+        @hf/thebloke/deepseek-coder-6.7b-base-awq
+        @hf/thebloke/deepseek-coder-6.7b-instruct-awq
+        @cf/deepseek-ai/deepseek-math-7b-base
+        @cf/deepseek-ai/deepseek-math-7b-instruct
+        @cf/thebloke/discolm-german-7b-v1-awq
+        @cf/tiiuae/falcon-7b-instruct
+        @hf/thebloke/llama-2-13b-chat-awq
+        @cf/meta/llama-2-7b-chat-fp16
+        @cf/meta/llama-2-7b-chat-int8
+        @hf/thebloke/llamaguard-7b-awq
+        @cf/mistral/mistral-7b-instruct-v0.1
+        @hf/thebloke/mistral-7b-instruct-v0.1-awq
+        @hf/thebloke/neural-chat-7b-v3-1-awq
+        @hf/thebloke/openchat_3.5-awq
+        @cf/openchat/openchat-3.5-0106
+        @hf/thebloke/openhermes-2.5-mistral-7b-awq
+        @cf/microsoft/phi-2
+        @cf/qwen/qwen1.5-0.5b-chat
+        @cf/qwen/qwen1.5-1.8b-chat
+        @cf/qwen/qwen1.5-14b-chat-awq
+        @cf/qwen/qwen1.5-7b-chat-awq
+        @cf/defog/sqlcoder-7b-2
+        @cf/tinyllama/tinyllama-1.1b-chat-v1.0
+        @hf/thebloke/zephyr-7b-beta-awq
+      ]
+    end
+
+    def text_to_image
+      %w[
+        @cf/lykon/dreamshaper-8-lcm
+        @cf/runwayml/stable-diffusion-v1-5-img2img
+        @cf/runwayml/stable-diffusion-v1-5-inpainting
+        @cf/stabilityai/stable-diffusion-xl-base-1.0
+        @cf/bytedance/stable-diffusion-xl-lightning
+      ]
+    end
+
+    def translation
+      %w[@cf/meta/m2m100-1.2b]
     end
   end
 end

data/lib/cloudflare/ai/results/image_to_text.rb

@@ -0,0 +1,5 @@
+class Cloudflare::AI::Results::ImageToText < Cloudflare::AI::Result
+  def description
+    result&.dig(:description) # nil if no shape
+  end
+end

data/lib/cloudflare/ai/results/object_detection.rb

@@ -0,0 +1,3 @@
+class Cloudflare::AI::Results::ObjectDetection < Cloudflare::AI::Result
+  # Empty seam kept for consistency with other result objects that have more complexity.
+end

data/lib/cloudflare/ai/results/summarization.rb

@@ -0,0 +1,5 @@
+class Cloudflare::AI::Results::Summarization < Cloudflare::AI::Result
+  def summary
+    result&.dig(:summary) # nil if no response
+  end
+end

data/lib/cloudflare/ai/version.rb

@@ -2,6 +2,6 @@
 
 module Cloudflare
   module AI
-    VERSION = "0.9.0"
+    VERSION = "0.9.2"
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cloudflare-ai
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.9.2
 platform: ruby
 authors:
 - Ajay Krishnan
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-02-07 00:00:00.000000000 Z
+date: 2024-02-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activemodel
@@ -115,6 +115,9 @@ files:
 - lib/cloudflare/ai/result.rb
 - lib/cloudflare/ai/results/automatic_speech_recognition.rb
 - lib/cloudflare/ai/results/image_classification.rb
+- lib/cloudflare/ai/results/image_to_text.rb
+- lib/cloudflare/ai/results/object_detection.rb
+- lib/cloudflare/ai/results/summarization.rb
 - lib/cloudflare/ai/results/text_classification.rb
 - lib/cloudflare/ai/results/text_embedding.rb
 - lib/cloudflare/ai/results/text_generation.rb