andreibondarev · October 2, 2023 23:26
diff --git a/create_schema.rb b/create_schema.rb
 require "weaviate"

 client = Weaviate::Client.new(
  url:     ENV['WEAVIATE_URL'],
  api_key: ENV['WEAVIATE_API_KEY'],

  # Configure Weaviate to use OpenAI to create vectors and use it for querying
  # You can also use Cohere or Hugging Face and pass their API key here instead
  model_service: :openai,
  model_service_api_key: ENV['OPENAI_API_KEY'] 
 )

 client.schema.create(
  class_name: "Recipes",                  # Name of the collection
  description: "A collection of recipes", # Description of the collection
  vectorizer: "text2vec-openai",          # OpenAI will be used to create vectors
  module_config: {               
    "qna-openai": {              # Weviate's OpenAI's Q&A module
      model: "text-davinci-003", # OpenAI's LLM to be used
      maxTokens: 3500,           # Maximum number of tokens to generate in the completion
      temperature: 0.0,          # How deterministic the output will be
      topP: 1,                   # Nucleus sampling
      frequencyPenalty: 0.0,
      presencePenalty: 0.0
    }
  },
  properties: [
    {
      dataType: ["int"],
      description: "Recipe ID",
      name: "recipe_id"          # Our PostgreSQL's recipes.id
    },
    {
      dataType: ["text"],
      description: "Recipe content",
      name: "content"            # Recipes' concatenated content
    }
  ]
 )
diff --git a/query.rb b/query.rb
 client.query.aggs(
  class_name: "Recipes",
  fields: "meta { count }"
 )

 client.query.get(
  class_name: "Recipes",
  limit: "1",
  fields: """
    recipe_id
    _additional {
      answer {
        result
      }
    }  
  """,
  ask: "{ question: \"What is a vegan dish that could be made for Thanksgiving?\" }"
 )

 client.query.get(
  class_name: "Recipes",
  limit: "1",
  fields: """
    recipe_id
    _additional {
      answer {
        result
      }
    }  
  """,
  ask: "{ question: \"What is a traditional French breakfast?\" }"
 )

 client.query.get(
  class_name: "Recipes",
  limit: "3",
  fields: "recipe_id content",
  near_text: "{ concepts: [\"latin american pescado\"] }"
 )
diff --git a/recipe.rb b/recipe.rb
 # app/models/recipe.rb

 # Table name: recipes
 #
 #  id                :bigint
 #  title             :string
 #  description       :text
 #  total_time        :integer
 #  ingredients       :text
 #  instructions      :text
 #  nutrients         :jsonb
 #  yields            :string

 class Recipe < ActiveRecord::Base
  def text_blob
    [
      "Title: #{title}",
      "Description: #{description}",
      "Total time: #{total_time} minutes",
      "Ingredients: #{ingredients.join(", ")}",
      "Instructions: #{instructions}",
      "Nutrients: #{nutrients}",
      "Serving size: #{yields}"
    ]
  end
 end
diff --git a/weaviate.rake b/weaviate.rake
 namespace :weaviate do
  require "weaviate"

  desc "Importing recipes into Weaviate"

  task import_recipes: :environment do
    Recipe.find_in_batches do |group|
      objects = group.map do |recipe|
        {
          class: "Recipes",            # Each object must contain the schema name
          properties: {
            content: recipe.text_blob, # See below for the formatted data
            recipe_id: recipe.id       # Recipe ID from the recipes PSQL table
          }
        }
      end

      weaviate_client.objects.batch_create(
        objects: objects
      )
    end
  end
 end
	require "weaviate"

	client = Weaviate::Client.new(
	url: ENV['WEAVIATE_URL'],
	api_key: ENV['WEAVIATE_API_KEY'],

	# Configure Weaviate to use OpenAI to create vectors and use it for querying
	# You can also use Cohere or Hugging Face and pass their API key here instead
	model_service: :openai,
	model_service_api_key: ENV['OPENAI_API_KEY']
	)

	client.schema.create(
	class_name: "Recipes", # Name of the collection
	description: "A collection of recipes", # Description of the collection
	vectorizer: "text2vec-openai", # OpenAI will be used to create vectors
	module_config: {
	"qna-openai": { # Weviate's OpenAI's Q&A module
	model: "text-davinci-003", # OpenAI's LLM to be used
	maxTokens: 3500, # Maximum number of tokens to generate in the completion
	temperature: 0.0, # How deterministic the output will be
	topP: 1, # Nucleus sampling
	frequencyPenalty: 0.0,
	presencePenalty: 0.0
	}
	},
	properties: [
	{
	dataType: ["int"],
	description: "Recipe ID",
	name: "recipe_id" # Our PostgreSQL's recipes.id
	},
	{
	dataType: ["text"],
	description: "Recipe content",
	name: "content" # Recipes' concatenated content
	}
	]
	)
	client.query.aggs(
	class_name: "Recipes",
	fields: "meta { count }"
	)

	client.query.get(
	class_name: "Recipes",
	limit: "1",
	fields: """
	recipe_id
	_additional {
	answer {
	result
	}
	}
	""",
	ask: "{ question: \"What is a vegan dish that could be made for Thanksgiving?\" }"
	)

	client.query.get(
	class_name: "Recipes",
	limit: "1",
	fields: """
	recipe_id
	_additional {
	answer {
	result
	}
	}
	""",
	ask: "{ question: \"What is a traditional French breakfast?\" }"
	)

	client.query.get(
	class_name: "Recipes",
	limit: "3",
	fields: "recipe_id content",
	near_text: "{ concepts: [\"latin american pescado\"] }"
	)
	# app/models/recipe.rb

	# Table name: recipes
	#
	# id :bigint
	# title :string
	# description :text
	# total_time :integer
	# ingredients :text
	# instructions :text
	# nutrients :jsonb
	# yields :string

	class Recipe < ActiveRecord::Base
	def text_blob
	[
	"Title: #{title}",
	"Description: #{description}",
	"Total time: #{total_time} minutes",
	"Ingredients: #{ingredients.join(", ")}",
	"Instructions: #{instructions}",
	"Nutrients: #{nutrients}",
	"Serving size: #{yields}"
	]
	end
	end
	namespace :weaviate do
	require "weaviate"

	desc "Importing recipes into Weaviate"

	task import_recipes: :environment do
	Recipe.find_in_batches do \|group\|
	objects = group.map do \|recipe\|
	{
	class: "Recipes", # Each object must contain the schema name
	properties: {
	content: recipe.text_blob, # See below for the formatted data
	recipe_id: recipe.id # Recipe ID from the recipes PSQL table
	}
	}
	end

	weaviate_client.objects.batch_create(
	objects: objects
	)
	end
	end
	end