langchainrb 0.17.1 → 0.19.0

data/lib/langchain/llm/anthropic.rb

@@ -5,16 +5,16 @@ module Langchain::LLM
   # Wrapper around Anthropic APIs.
   #
   # Gem requirements:
-  #   gem "anthropic", "~> 0.3.0"
+  #   gem "anthropic", "~> 0.3.2"
   #
   # Usage:
-  #     anthropic = Langchain::LLM::Anthropic.new(api_key: ENV["ANTHROPIC_API_KEY"])
+  #     llm = Langchain::LLM::Anthropic.new(api_key: ENV["ANTHROPIC_API_KEY"])
   #
   class Anthropic < Base
     DEFAULTS = {
       temperature: 0.0,
-      completion_model_name: "claude-2.1",
-      chat_completion_model_name: "claude-3-5-sonnet-20240620",
+      completion_model: "claude-2.1",
+      chat_model: "claude-3-5-sonnet-20240620",
       max_tokens_to_sample: 256
     }.freeze
 
@@ -22,7 +22,7 @@ module Langchain::LLM
     #
     # @param api_key [String] The API key to use
     # @param llm_options [Hash] Options to pass to the Anthropic client
-    # @param default_options [Hash] Default options to use on every call to LLM, e.g.: { temperature:, completion_model_name:, chat_completion_model_name:, max_tokens_to_sample: }
+    # @param default_options [Hash] Default options to use on every call to LLM, e.g.: { temperature:, completion_model:, chat_model:, max_tokens_to_sample: }
     # @return [Langchain::LLM::Anthropic] Langchain::LLM::Anthropic instance
     def initialize(api_key:, llm_options: {}, default_options: {})
       depends_on "anthropic"
@@ -30,7 +30,7 @@ module Langchain::LLM
       @client = ::Anthropic::Client.new(access_token: api_key, **llm_options)
       @defaults = DEFAULTS.merge(default_options)
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         temperature: {default: @defaults[:temperature]},
         max_tokens: {default: @defaults[:max_tokens_to_sample]},
         metadata: {},
@@ -54,7 +54,7 @@ module Langchain::LLM
     # @return [Langchain::LLM::AnthropicResponse] The completion
     def complete(
       prompt:,
-      model: @defaults[:completion_model_name],
+      model: @defaults[:completion_model],
       max_tokens_to_sample: @defaults[:max_tokens_to_sample],
       stop_sequences: nil,
       temperature: @defaults[:temperature],
@@ -100,7 +100,7 @@ module Langchain::LLM
     # @option params [Integer] :top_k Only sample from the top K options for each subsequent token
     # @option params [Float] :top_p Use nucleus sampling.
     # @return [Langchain::LLM::AnthropicResponse] The chat completion
-    def chat(params = {})
+    def chat(params = {}, &block)
       set_extra_headers! if params[:tools]
 
       parameters = chat_parameters.to_params(params)
@@ -109,9 +109,19 @@ module Langchain::LLM
       raise ArgumentError.new("model argument is required") if parameters[:model].empty?
       raise ArgumentError.new("max_tokens argument is required") if parameters[:max_tokens].nil?
 
-      binding.pry
+      if block
+        @response_chunks = []
+        parameters[:stream] = proc do |chunk|
+          @response_chunks << chunk
+          yield chunk
+        end
+      end
+
       response = client.messages(parameters: parameters)
 
+      response = response_from_chunks if block
+      reset_response_chunks
+
       Langchain::LLM::AnthropicResponse.new(response)
     end
 
@@ -124,8 +134,53 @@ module Langchain::LLM
       response
     end
 
+    def response_from_chunks
+      grouped_chunks = @response_chunks.group_by { |chunk| chunk["index"] }.except(nil)
+
+      usage = @response_chunks.find { |chunk| chunk["type"] == "message_delta" }&.dig("usage")
+      stop_reason = @response_chunks.find { |chunk| chunk["type"] == "message_delta" }&.dig("delta", "stop_reason")
+
+      content = grouped_chunks.map do |_index, chunks|
+        text = chunks.map { |chunk| chunk.dig("delta", "text") }.join
+        if !text.nil? && !text.empty?
+          {"type" => "text", "text" => text}
+        else
+          tool_calls_from_choice_chunks(chunks)
+        end
+      end.flatten
+
+      @response_chunks.first&.slice("id", "object", "created", "model")
+        &.merge!(
+          {
+            "content" => content,
+            "usage" => usage,
+            "role" => "assistant",
+            "stop_reason" => stop_reason
+          }
+        )
+    end
+
+    def tool_calls_from_choice_chunks(chunks)
+      return unless (first_block = chunks.find { |chunk| chunk.dig("content_block", "type") == "tool_use" })
+
+      chunks.group_by { |chunk| chunk["index"] }.map do |index, chunks|
+        input = chunks.select { |chunk| chunk.dig("delta", "partial_json") }
+          .map! { |chunk| chunk.dig("delta", "partial_json") }.join
+        {
+          "id" => first_block.dig("content_block", "id"),
+          "type" => "tool_use",
+          "name" => first_block.dig("content_block", "name"),
+          "input" => JSON.parse(input).transform_keys(&:to_sym)
+        }
+      end.compact
+    end
+
     private
 
+    def reset_response_chunks
+      @response_chunks = []
+    end
+
     def set_extra_headers!
       ::Anthropic.configuration.extra_headers = {"anthropic-beta": "tools-2024-05-16"}
     end

data/lib/langchain/llm/aws_bedrock.rb

@@ -7,12 +7,13 @@ module Langchain::LLM
   #    gem 'aws-sdk-bedrockruntime', '~> 1.1'
   #
   # Usage:
-  #    bedrock = Langchain::LLM::AwsBedrock.new(llm_options: {})
+  #    llm = Langchain::LLM::AwsBedrock.new(llm_options: {})
   #
   class AwsBedrock < Base
     DEFAULTS = {
-      completion_model_name: "anthropic.claude-v2",
-      embedding_model_name: "amazon.titan-embed-text-v1",
+      chat_model: "anthropic.claude-v2",
+      completion_model: "anthropic.claude-v2",
+      embedding_model: "amazon.titan-embed-text-v1",
       max_tokens_to_sample: 300,
       temperature: 1,
       top_k: 250,
@@ -52,16 +53,14 @@ module Langchain::LLM
     SUPPORTED_CHAT_COMPLETION_PROVIDERS = %i[anthropic].freeze
     SUPPORTED_EMBEDDING_PROVIDERS = %i[amazon cohere].freeze
 
-    def initialize(completion_model: DEFAULTS[:completion_model_name], embedding_model: DEFAULTS[:embedding_model_name], aws_client_options: {}, default_options: {})
+    def initialize(aws_client_options: {}, default_options: {})
       depends_on "aws-sdk-bedrockruntime", req: "aws-sdk-bedrockruntime"
 
       @client = ::Aws::BedrockRuntime::Client.new(**aws_client_options)
       @defaults = DEFAULTS.merge(default_options)
-        .merge(completion_model_name: completion_model)
-        .merge(embedding_model_name: embedding_model)
 
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         temperature: {},
         max_tokens: {default: @defaults[:max_tokens_to_sample]},
         metadata: {},
@@ -85,7 +84,7 @@ module Langchain::LLM
       parameters = compose_embedding_parameters params.merge(text:)
 
       response = client.invoke_model({
-        model_id: @defaults[:embedding_model_name],
+        model_id: @defaults[:embedding_model],
         body: parameters.to_json,
         content_type: "application/json",
         accept: "application/json"
@@ -104,14 +103,14 @@ module Langchain::LLM
     def complete(prompt:, **params)
       raise "Completion provider #{completion_provider} is not supported." unless SUPPORTED_COMPLETION_PROVIDERS.include?(completion_provider)
 
-      raise "Model #{@defaults[:completion_model_name]} only supports #chat." if @defaults[:completion_model_name].include?("claude-3")
+      raise "Model #{@defaults[:completion_model]} only supports #chat." if @defaults[:completion_model].include?("claude-3")
 
       parameters = compose_parameters params
 
       parameters[:prompt] = wrap_prompt prompt
 
       response = client.invoke_model({
-        model_id: @defaults[:completion_model_name],
+        model_id: @defaults[:completion_model],
         body: parameters.to_json,
         content_type: "application/json",
         accept: "application/json"
@@ -127,7 +126,7 @@ module Langchain::LLM
     # @param [Hash] params unified chat parmeters from [Langchain::LLM::Parameters::Chat::SCHEMA]
     # @option params [Array<String>] :messages The messages to generate a completion for
     # @option params [String] :system The system prompt to provide instructions
-    # @option params [String] :model The model to use for completion defaults to @defaults[:chat_completion_model_name]
+    # @option params [String] :model The model to use for completion defaults to @defaults[:chat_model]
     # @option params [Integer] :max_tokens The maximum number of tokens to generate defaults to @defaults[:max_tokens_to_sample]
     # @option params [Array<String>] :stop The stop sequences to use for completion
     # @option params [Array<String>] :stop_sequences The stop sequences to use for completion
@@ -176,11 +175,11 @@ module Langchain::LLM
     private
 
     def completion_provider
-      @defaults[:completion_model_name].split(".").first.to_sym
+      @defaults[:completion_model].split(".").first.to_sym
     end
 
     def embedding_provider
-      @defaults[:embedding_model_name].split(".").first.to_sym
+      @defaults[:embedding_model].split(".").first.to_sym
     end
 
     def wrap_prompt(prompt)

data/lib/langchain/llm/azure.rb

@@ -7,7 +7,7 @@ module Langchain::LLM
   #    gem "ruby-openai", "~> 6.3.0"
   #
   # Usage:
-  #    openai = Langchain::LLM::Azure.new(api_key:, llm_options: {}, embedding_deployment_url: chat_deployment_url:)
+  #    llm = Langchain::LLM::Azure.new(api_key:, llm_options: {}, embedding_deployment_url: chat_deployment_url:)
   #
   class Azure < OpenAI
     attr_reader :embed_client
@@ -33,7 +33,7 @@ module Langchain::LLM
       )
       @defaults = DEFAULTS.merge(default_options)
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         logprobs: {},
         top_logprobs: {},
         n: {default: @defaults[:n]},

data/lib/langchain/llm/base.rb

@@ -34,7 +34,7 @@ module Langchain::LLM
       default_dimensions
     end
 
-    # Returns the number of vector dimensions used by DEFAULTS[:chat_completion_model_name]
+    # Returns the number of vector dimensions used by DEFAULTS[:chat_model]
     #
     # @return [Integer] Vector dimensions
     def default_dimensions

data/lib/langchain/llm/cohere.rb

@@ -13,9 +13,9 @@ module Langchain::LLM
   class Cohere < Base
     DEFAULTS = {
       temperature: 0.0,
-      completion_model_name: "command",
-      chat_completion_model_name: "command-r-plus",
-      embeddings_model_name: "small",
+      completion_model: "command",
+      chat_model: "command-r-plus",
+      embedding_model: "small",
       dimensions: 1024,
       truncate: "START"
     }.freeze
@@ -26,7 +26,7 @@ module Langchain::LLM
       @client = ::Cohere::Client.new(api_key: api_key)
       @defaults = DEFAULTS.merge(default_options)
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         temperature: {default: @defaults[:temperature]},
         response_format: {default: @defaults[:response_format]}
       )
@@ -48,10 +48,10 @@ module Langchain::LLM
     def embed(text:)
       response = client.embed(
         texts: [text],
-        model: @defaults[:embeddings_model_name]
+        model: @defaults[:embedding_model]
       )
 
-      Langchain::LLM::CohereResponse.new response, model: @defaults[:embeddings_model_name]
+      Langchain::LLM::CohereResponse.new response, model: @defaults[:embedding_model]
     end
 
     #
@@ -65,7 +65,7 @@ module Langchain::LLM
       default_params = {
         prompt: prompt,
         temperature: @defaults[:temperature],
-        model: @defaults[:completion_model_name],
+        model: @defaults[:completion_model],
         truncate: @defaults[:truncate]
       }
 
@@ -76,7 +76,7 @@ module Langchain::LLM
       default_params.merge!(params)
 
       response = client.generate(**default_params)
-      Langchain::LLM::CohereResponse.new response, model: @defaults[:completion_model_name]
+      Langchain::LLM::CohereResponse.new response, model: @defaults[:completion_model]
     end
 
     # Generate a chat completion for given messages

data/lib/langchain/llm/google_gemini.rb

@@ -5,8 +5,8 @@ module Langchain::LLM
   #     llm = Langchain::LLM::GoogleGemini.new(api_key: ENV['GOOGLE_GEMINI_API_KEY'])
   class GoogleGemini < Base
     DEFAULTS = {
-      chat_completion_model_name: "gemini-1.5-pro-latest",
-      embeddings_model_name: "text-embedding-004",
+      chat_model: "gemini-1.5-pro-latest",
+      embedding_model: "text-embedding-004",
       temperature: 0.0
     }
 
@@ -17,10 +17,10 @@ module Langchain::LLM
       @defaults = DEFAULTS.merge(default_options)
 
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         temperature: {default: @defaults[:temperature]},
         generation_config: {default: nil},
-        safety_settings: {default: nil}
+        safety_settings: {default: @defaults[:safety_settings]}
       )
       chat_parameters.remap(
         messages: :contents,
@@ -72,9 +72,8 @@ module Langchain::LLM
 
     def embed(
       text:,
-      model: @defaults[:embeddings_model_name]
+      model: @defaults[:embedding_model]
     )
-
       params = {
         content: {
           parts: [

data/lib/langchain/llm/google_vertex_ai.rb

@@ -17,8 +17,8 @@ module Langchain::LLM
       top_p: 0.8,
       top_k: 40,
       dimensions: 768,
-      embeddings_model_name: "textembedding-gecko",
-      chat_completion_model_name: "gemini-1.0-pro"
+      embedding_model: "textembedding-gecko",
+      chat_model: "gemini-1.0-pro"
     }.freeze
 
     # Google Cloud has a project id and a specific region of deployment.
@@ -38,8 +38,9 @@ module Langchain::LLM
       @defaults = DEFAULTS.merge(default_options)
 
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
-        temperature: {default: @defaults[:temperature]}
+        model: {default: @defaults[:chat_model]},
+        temperature: {default: @defaults[:temperature]},
+        safety_settings: {default: @defaults[:safety_settings]}
       )
       chat_parameters.remap(
         messages: :contents,
@@ -57,7 +58,7 @@ module Langchain::LLM
     #
     def embed(
       text:,
-      model: @defaults[:embeddings_model_name]
+      model: @defaults[:embedding_model]
     )
       params = {instances: [{content: text}]}
 

data/lib/langchain/llm/hugging_face.rb

@@ -8,11 +8,11 @@ module Langchain::LLM
   #     gem "hugging-face", "~> 0.3.4"
   #
   # Usage:
-  #     hf = Langchain::LLM::HuggingFace.new(api_key: ENV["HUGGING_FACE_API_KEY"])
+  #     llm = Langchain::LLM::HuggingFace.new(api_key: ENV["HUGGING_FACE_API_KEY"])
   #
   class HuggingFace < Base
     DEFAULTS = {
-      embeddings_model_name: "sentence-transformers/all-MiniLM-L6-v2"
+      embedding_model: "sentence-transformers/all-MiniLM-L6-v2"
     }.freeze
 
     EMBEDDING_SIZES = {
@@ -36,7 +36,7 @@ module Langchain::LLM
     def default_dimensions
       # since Huggin Face can run multiple models, look it up or generate an embedding and return the size
       @default_dimensions ||= @defaults[:dimensions] ||
-        EMBEDDING_SIZES.fetch(@defaults[:embeddings_model_name].to_sym) do
+        EMBEDDING_SIZES.fetch(@defaults[:embedding_model].to_sym) do
           embed(text: "test").embedding.size
         end
     end
@@ -50,9 +50,9 @@ module Langchain::LLM
     def embed(text:)
       response = client.embedding(
         input: text,
-        model: @defaults[:embeddings_model_name]
+        model: @defaults[:embedding_model]
       )
-      Langchain::LLM::HuggingFaceResponse.new(response, model: @defaults[:embeddings_model_name])
+      Langchain::LLM::HuggingFaceResponse.new(response, model: @defaults[:embedding_model])
     end
   end
 end

data/lib/langchain/llm/mistral_ai.rb

@@ -8,8 +8,8 @@ module Langchain::LLM
   #    llm = Langchain::LLM::MistralAI.new(api_key: ENV["MISTRAL_AI_API_KEY"])
   class MistralAI < Base
     DEFAULTS = {
-      chat_completion_model_name: "mistral-large-latest",
-      embeddings_model_name: "mistral-embed"
+      chat_model: "mistral-large-latest",
+      embedding_model: "mistral-embed"
     }.freeze
 
     attr_reader :defaults
@@ -24,7 +24,7 @@ module Langchain::LLM
 
       @defaults = DEFAULTS.merge(default_options)
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         n: {default: @defaults[:n]},
         safe_prompt: {},
         temperature: {default: @defaults[:temperature]},
@@ -44,7 +44,7 @@ module Langchain::LLM
 
     def embed(
       text:,
-      model: defaults[:embeddings_model_name],
+      model: defaults[:embedding_model],
       encoding_format: nil
     )
       params = {

data/lib/langchain/llm/ollama.rb

@@ -5,7 +5,6 @@ module Langchain::LLM
   # Available models: https://ollama.ai/library
   #
   # Usage:
-  #    llm = Langchain::LLM::Ollama.new
   #    llm = Langchain::LLM::Ollama.new(url: ENV["OLLAMA_URL"], default_options: {})
   #
   class Ollama < Base
@@ -13,9 +12,9 @@ module Langchain::LLM
 
     DEFAULTS = {
       temperature: 0.0,
-      completion_model_name: "llama3.1",
-      embeddings_model_name: "llama3.1",
-      chat_completion_model_name: "llama3.1"
+      completion_model: "llama3.1",
+      embedding_model: "llama3.1",
+      chat_model: "llama3.1"
     }.freeze
 
     EMBEDDING_SIZES = {
@@ -42,7 +41,7 @@ module Langchain::LLM
       @api_key = api_key
       @defaults = DEFAULTS.merge(default_options)
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         temperature: {default: @defaults[:temperature]},
         template: {},
         stream: {default: false},
@@ -56,7 +55,7 @@ module Langchain::LLM
     def default_dimensions
       # since Ollama can run multiple models, look it up or generate an embedding and return the size
       @default_dimensions ||=
-        EMBEDDING_SIZES.fetch(defaults[:embeddings_model_name].to_sym) do
+        EMBEDDING_SIZES.fetch(defaults[:embedding_model].to_sym) do
           embed(text: "test").embedding.size
         end
     end
@@ -78,7 +77,7 @@ module Langchain::LLM
     #
     def complete(
       prompt:,
-      model: defaults[:completion_model_name],
+      model: defaults[:completion_model],
       images: nil,
       format: nil,
       system: nil,
@@ -200,7 +199,7 @@ module Langchain::LLM
     #
     def embed(
       text:,
-      model: defaults[:embeddings_model_name],
+      model: defaults[:embedding_model],
       mirostat: nil,
       mirostat_eta: nil,
       mirostat_tau: nil,

data/lib/langchain/llm/openai.rb

@@ -7,7 +7,7 @@ module Langchain::LLM
   #    gem "ruby-openai", "~> 6.3.0"
   #
   # Usage:
-  #    openai = Langchain::LLM::OpenAI.new(
+  #    llm = Langchain::LLM::OpenAI.new(
   #      api_key: ENV["OPENAI_API_KEY"],
   #      llm_options: {}, # Available options: https://github.com/alexrudall/ruby-openai/blob/main/lib/openai/client.rb#L5-L13
   #      default_options: {}
@@ -16,8 +16,8 @@ module Langchain::LLM
     DEFAULTS = {
       n: 1,
       temperature: 0.0,
-      chat_completion_model_name: "gpt-4o-mini",
-      embeddings_model_name: "text-embedding-3-small"
+      chat_model: "gpt-4o-mini",
+      embedding_model: "text-embedding-3-small"
     }.freeze
 
     EMBEDDING_SIZES = {
@@ -41,7 +41,7 @@ module Langchain::LLM
 
       @defaults = DEFAULTS.merge(default_options)
       chat_parameters.update(
-        model: {default: @defaults[:chat_completion_model_name]},
+        model: {default: @defaults[:chat_model]},
         logprobs: {},
         top_logprobs: {},
         n: {default: @defaults[:n]},
@@ -61,7 +61,7 @@ module Langchain::LLM
     # @return [Langchain::LLM::OpenAIResponse] Response object
     def embed(
       text:,
-      model: defaults[:embeddings_model_name],
+      model: defaults[:embedding_model],
       encoding_format: nil,
       user: nil,
       dimensions: @defaults[:dimensions]
@@ -100,7 +100,7 @@ module Langchain::LLM
     # @param params [Hash] The parameters to pass to the `chat()` method
     # @return [Langchain::LLM::OpenAIResponse] Response object
     def complete(prompt:, **params)
-      warn "DEPRECATED: `Langchain::LLM::OpenAI#complete` is deprecated, and will be removed in the next major version. Use `Langchain::LLM::OpenAI#chat` instead."
+      Langchain.logger.warn "DEPRECATED: `Langchain::LLM::OpenAI#complete` is deprecated, and will be removed in the next major version. Use `Langchain::LLM::OpenAI#chat` instead."
 
       if params[:stop_sequences]
         params[:stop] = params.delete(:stop_sequences)
@@ -109,6 +109,7 @@ module Langchain::LLM
       messages = [{role: "user", content: prompt}]
       chat(messages: messages, **params)
     end
+
     # rubocop:enable Style/ArgumentsForwarding
 
     # Generate a chat completion for given messages.
@@ -159,7 +160,7 @@ module Langchain::LLM
     end
 
     def default_dimensions
-      @defaults[:dimensions] || EMBEDDING_SIZES.fetch(defaults[:embeddings_model_name])
+      @defaults[:dimensions] || EMBEDDING_SIZES.fetch(defaults[:embedding_model])
     end
 
     private

data/lib/langchain/llm/parameters/chat.rb

@@ -34,6 +34,7 @@ module Langchain::LLM::Parameters
       # Function-calling
       tools: {default: []},
       tool_choice: {},
+      parallel_tool_calls: {},
 
       # Additional optional parameters
       logit_bias: {}

data/lib/langchain/llm/replicate.rb

@@ -7,23 +7,15 @@ module Langchain::LLM
   # Gem requirements:
   #     gem "replicate-ruby", "~> 0.2.2"
   #
-  # Use it directly:
-  #     replicate = Langchain::LLM::Replicate.new(api_key: ENV["REPLICATE_API_KEY"])
-  #
-  # Or pass it to be used by a vector search DB:
-  #     chroma = Langchain::Vectorsearch::Chroma.new(
-  #       url: ENV["CHROMA_URL"],
-  #       index_name: "...",
-  #       llm: replicate
-  #     )
-  #
+  # Usage:
+  #     llm = Langchain::LLM::Replicate.new(api_key: ENV["REPLICATE_API_KEY"])
   class Replicate < Base
     DEFAULTS = {
       # TODO: Figure out how to send the temperature to the API
       temperature: 0.01, # Minimum accepted value
       # TODO: Design the interface to pass and use different models
-      completion_model_name: "replicate/vicuna-13b",
-      embeddings_model_name: "creatorrr/all-mpnet-base-v2",
+      completion_model: "replicate/vicuna-13b",
+      embedding_model: "creatorrr/all-mpnet-base-v2",
       dimensions: 384
     }.freeze
 
@@ -57,7 +49,7 @@ module Langchain::LLM
         sleep(0.1)
       end
 
-      Langchain::LLM::ReplicateResponse.new(response, model: @defaults[:embeddings_model_name])
+      Langchain::LLM::ReplicateResponse.new(response, model: @defaults[:embedding_model])
     end
 
     #
@@ -74,7 +66,7 @@ module Langchain::LLM
         sleep(0.1)
       end
 
-      Langchain::LLM::ReplicateResponse.new(response, model: @defaults[:completion_model_name])
+      Langchain::LLM::ReplicateResponse.new(response, model: @defaults[:completion_model])
     end
 
     #
@@ -102,11 +94,11 @@ module Langchain::LLM
     private
 
     def completion_model
-      @completion_model ||= client.retrieve_model(@defaults[:completion_model_name]).latest_version
+      @completion_model ||= client.retrieve_model(@defaults[:completion_model]).latest_version
     end
 
     def embeddings_model
-      @embeddings_model ||= client.retrieve_model(@defaults[:embeddings_model_name]).latest_version
+      @embeddings_model ||= client.retrieve_model(@defaults[:embedding_model]).latest_version
     end
   end
 end

data/lib/langchain/tool_definition.rb

@@ -103,6 +103,13 @@ module Langchain::ToolDefinition
     # @return [String] JSON string of schemas in Anthropic format
     def to_anthropic_format
       @schemas.values.map do |schema|
+        # Adds a default input_schema if no parameters are present
+        schema[:function][:parameters] ||= {
+          type: "object",
+          properties: {},
+          required: []
+        }
+
         schema[:function].transform_keys(parameters: :input_schema)
       end
     end

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.17.1"
+  VERSION = "0.19.0"
 end

data/lib/langchain.rb

@@ -22,25 +22,12 @@ loader.inflector.inflect(
   "mistral_ai_response" => "MistralAIResponse",
   "mistral_ai_message" => "MistralAIMessage",
   "openai" => "OpenAI",
-  "openai_validator" => "OpenAIValidator",
   "openai_response" => "OpenAIResponse",
   "openai_message" => "OpenAIMessage",
   "pdf" => "PDF"
 )
+
 loader.collapse("#{__dir__}/langchain/llm/response")
-loader.collapse("#{__dir__}/langchain/assistants")
-
-loader.collapse("#{__dir__}/langchain/tool/calculator")
-loader.collapse("#{__dir__}/langchain/tool/database")
-loader.collapse("#{__dir__}/langchain/tool/docs_tool")
-loader.collapse("#{__dir__}/langchain/tool/file_system")
-loader.collapse("#{__dir__}/langchain/tool/google_search")
-loader.collapse("#{__dir__}/langchain/tool/ruby_code_interpreter")
-loader.collapse("#{__dir__}/langchain/tool/news_retriever")
-loader.collapse("#{__dir__}/langchain/tool/tavily")
-loader.collapse("#{__dir__}/langchain/tool/vectorsearch")
-loader.collapse("#{__dir__}/langchain/tool/weather")
-loader.collapse("#{__dir__}/langchain/tool/wikipedia")
 
 # RubyCodeInterpreter does not work with Ruby 3.3;
 # https://github.com/ukutaht/safe_ruby/issues/4