Groq::Model.load_models

README.md

@@ -4,7 +4,7 @@ Groq Cloud runs LLM models fast and cheap. Llama 3, Mixtrel, Gemma, and more at
 
 [![speed-pricing](docs/images/groq-speed-price-20240421.png)](https://wow.groq.com/)
 
-Speed and pricing at 2024-04-21.
+Speed and pricing at 2024-04-21. Also see their [changelog](https://console.groq.com/docs/changelog) for new models and features.
 
 ## Groq Cloud API
 
@@ -185,7 +185,7 @@ Assistant reply with model gemma-7b-it:
 
 LLMs are increasingly supporting deferring to tools or functions to fetch data, perform calculations, or store structured data. Groq Cloud in turn then supports their tool implementations through its API.
 
-See the [Using Tools](https://console.groq.com/docs/tool-use) documentation for the list of models that currently support tools.
+See the [Using Tools](https://console.groq.com/docs/tool-use) documentation for the list of models that currently support tools. Others might support it sometimes and raise errors other times.
 
 ```ruby
 @client = Groq::Client.new(model_id: "mixtral-8x7b-32768")

lib/groq/client.rb

@@ -46,6 +46,13 @@ def chat(messages, model_id: nil, tools: nil)
     end
   end
 
+  def get(path:)
+    client.get do |req|
+      req.url path
+      req.headers["Authorization"] = "Bearer #{@api_key}"
+    end
+  end
+
   def post(path:, body:)
     client.post do |req|
       req.url path

lib/groq/model.rb

@@ -49,5 +49,23 @@ def default_model
     def default_model_id
       default_model[:model_id]
     end
+
+    # https://api.groq.com/openai/v1/models
+    # Output:
+    # {"object": "list",
+    # "data": [
+    #     {
+    #         "id": "gemma-7b-it",
+    #         "object": "model",
+    #         "created": 1693721698,
+    #         "owned_by": "Google",
+    #         "active": true,
+    #         "context_window": 8192
+    #     },
+    def load_models(client:)
+      client ||= Groq::Client.new
+      response = client.get(path: "/openai/v1/models")
+      response.body
+    end
   end
 end

test/groq/test_models.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+require "test_helper"
+
+class TestGroqModel < Minitest::Test
+  def test_load_models
+    VCR.use_cassette("api/get_models") do
+      client = Groq::Client.new
+      models = Groq::Model.load_models(client: client)
+      expected = {
+        "object" => "list",
+        "data" => [
+          {"id" => "gemma-7b-it", "object" => "model", "created" => 1693721698, "owned_by" => "Google", "active" => true, "context_window" => 8192},
+          {"id" => "llama2-70b-4096", "object" => "model", "created" => 1693721698, "owned_by" => "Meta", "active" => true, "context_window" => 4096},
+          {"id" => "llama3-70b-8192", "object" => "model", "created" => 1693721698, "owned_by" => "Meta", "active" => true, "context_window" => 8192},
+          {"id" => "llama3-8b-8192", "object" => "model", "created" => 1693721698, "owned_by" => "Meta", "active" => true, "context_window" => 8192},
+          {"id" => "mixtral-8x7b-32768", "object" => "model", "created" => 1693721698, "owned_by" => "Mistral AI", "active" => true, "context_window" => 32768}
+        ]
+      }
+      assert_equal expected, models
+    end
+  end
+end