langchainrb 0.9.5 → 0.10.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 833d4dafdf55e45852261e1c86b8121fd3ed1b61766a7fb121589e6549b255e0
-  data.tar.gz: d3834e7a5d15cf1ddd45bfc2db69b73afb5cf60b6b43004a398a688b5d5932e1
+  metadata.gz: 19b23746583868d1a5eca30d5e8f30bf548cfc253d8cf20fa13c27bb4e03b967
+  data.tar.gz: 6de6bea0a348b812d09745af6f14c03def1f8d7a4fb7a246ab328de4992b9e8e
 SHA512:
-  metadata.gz: 98dbc07b39f956d7425c562451d9eced8162cd7d7e181ac6188d029090275f5485376db3afeb826e730c168f6d64a7cd6af90503974f8b2696b1555f3d18b589
-  data.tar.gz: 3e641d27e3ccdedfa363c7bfecb7f6a1293c1f866421db3ac5e74dcd4615934a132345f9c7912fec0200d2fe626747faaefa592592066e336d33c4db5d3fd050
+  metadata.gz: 12e39b5c0c523d7ea798f4fc0729fc53f0e0754db43261ec9c464369a4a01fea18ef7c30bee9d26b45a08add746cd45b0550f1a741dda0f84ae4cd72be9481d1
+  data.tar.gz: abf235f4d1dffd76d4a73a45a8e3e3af81ed358eadb43189ccef6cd8d3ff7739c8e1fcb38287c786dd56de6edf8944efc16270936cd6d4e4763e2ec4f7c84eea

data/CHANGELOG.md

@@ -1,5 +1,15 @@
 ## [Unreleased]
 
+## [0.10.2]
+- New Langchain::LLM::Mistral
+- Drop Ruby 3.0 support
+- Fixes Zeitwerk::NameError
+
+## [0.10.1] - GEM VERSION YANKED
+
+## [0.10.0]
+- Delete `Langchain::Conversation` class
+
 ## [0.9.5]
 - Now using OpenAI's "text-embedding-3-small" model to generate embeddings
 - Added `remove_texts(ids:)` method to Qdrant and Chroma

data/lib/langchain/llm/mistral_ai.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  # Gem requirements:
+  #    gem "mistral-ai"
+  #
+  # Usage:
+  #    llm = Langchain::LLM::MistralAI.new(api_key: ENV["OPENAI_API_KEY"])
+  class MistralAI < Base
+    DEFAULTS = {
+      chat_completion_model_name: "mistral-medium",
+      embeddings_model_name: "mistral-embed"
+    }.freeze
+
+    attr_reader :defaults
+
+    def initialize(api_key:, default_options: {})
+      depends_on "mistral-ai"
+
+      @client = Mistral.new(
+        credentials: {api_key: ENV["MISTRAL_AI_API_KEY"]},
+        options: {server_sent_events: true}
+      )
+
+      @defaults = DEFAULTS.merge(default_options)
+    end
+
+    def chat(
+      messages:,
+      model: defaults[:chat_completion_model_name],
+      temperature: nil,
+      top_p: nil,
+      max_tokens: nil,
+      safe_prompt: nil,
+      random_seed: nil
+    )
+      params = {
+        messages: messages,
+        model: model
+      }
+      params[:temperature] = temperature if temperature
+      params[:top_p] = top_p if top_p
+      params[:max_tokens] = max_tokens if max_tokens
+      params[:safe_prompt] = safe_prompt if safe_prompt
+      params[:random_seed] = random_seed if random_seed
+
+      response = client.chat_completions(params)
+
+      Langchain::LLM::MistralAIResponse.new(response.to_h)
+    end
+
+    def embed(
+      text:,
+      model: defaults[:embeddings_model_name],
+      encoding_format: nil
+    )
+      params = {
+        input: text,
+        model: model
+      }
+      params[:encoding_format] = encoding_format if encoding_format
+
+      response = client.embeddings(params)
+
+      Langchain::LLM::MistralAIResponse.new(response.to_h)
+    end
+  end
+end

data/lib/langchain/llm/response/mistral_ai_response.rb

@@ -0,0 +1,39 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  class MistralAIResponse < BaseResponse
+    def model
+      raw_response["model"]
+    end
+
+    def chat_completion
+      raw_response.dig("choices", 0, "message", "content")
+    end
+
+    def role
+      raw_response.dig("choices", 0, "message", "role")
+    end
+
+    def embedding
+      raw_response.dig("data", 0, "embedding")
+    end
+
+    def prompt_tokens
+      raw_response.dig("usage", "prompt_tokens")
+    end
+
+    def total_tokens
+      raw_response.dig("usage", "total_tokens")
+    end
+
+    def completion_tokens
+      raw_response.dig("usage", "completion_tokens")
+    end
+
+    def created_at
+      if raw_response.dig("created_at")
+        Time.at(raw_response.dig("created_at"))
+      end
+    end
+  end
+end

data/lib/langchain/tool/ruby_code_interpreter/ruby_code_interpreter.rb

@@ -1,45 +1,41 @@
 # frozen_string_literal: true
 
-# RubyCodeInterpreter does not work with Ruby 3.3;
-# https://github.com/ukutaht/safe_ruby/issues/4
-if RUBY_VERSION <= "3.2"
-  module Langchain::Tool
-    class RubyCodeInterpreter < Base
-      #
-      # A tool that execute Ruby code in a sandboxed environment.
-      #
-      # Gem requirements:
-      #     gem "safe_ruby", "~> 1.0.4"
-      #
-      # Usage:
-      #    interpreter = Langchain::Tool::RubyCodeInterpreter.new
-      #
-      NAME = "ruby_code_interpreter"
-      ANNOTATIONS_PATH = Langchain.root.join("./langchain/tool/#{NAME}/#{NAME}.json").to_path
+module Langchain::Tool
+  class RubyCodeInterpreter < Base
+    #
+    # A tool that execute Ruby code in a sandboxed environment.
+    #
+    # Gem requirements:
+    #     gem "safe_ruby", "~> 1.0.4"
+    #
+    # Usage:
+    #    interpreter = Langchain::Tool::RubyCodeInterpreter.new
+    #
+    NAME = "ruby_code_interpreter"
+    ANNOTATIONS_PATH = Langchain.root.join("./langchain/tool/#{NAME}/#{NAME}.json").to_path
 
-      description <<~DESC
-        A Ruby code interpreter. Use this to execute ruby expressions. Input should be a valid ruby expression. If you want to see the output of the tool, make sure to return a value.
-      DESC
+    description <<~DESC
+      A Ruby code interpreter. Use this to execute ruby expressions. Input should be a valid ruby expression. If you want to see the output of the tool, make sure to return a value.
+    DESC
 
-      def initialize(timeout: 30)
-        depends_on "safe_ruby"
+    def initialize(timeout: 30)
+      depends_on "safe_ruby"
 
-        @timeout = timeout
-      end
+      @timeout = timeout
+    end
 
-      # Executes Ruby code in a sandboxes environment.
-      #
-      # @param input [String] ruby code expression
-      # @return [String] Answer
-      def execute(input:)
-        Langchain.logger.info("Executing \"#{input}\"", for: self.class)
+    # Executes Ruby code in a sandboxes environment.
+    #
+    # @param input [String] ruby code expression
+    # @return [String] Answer
+    def execute(input:)
+      Langchain.logger.info("Executing \"#{input}\"", for: self.class)
 
-        safe_eval(input)
-      end
+      safe_eval(input)
+    end
 
-      def safe_eval(code)
-        SafeRuby.eval(code, timeout: @timeout)
-      end
+    def safe_eval(code)
+      SafeRuby.eval(code, timeout: @timeout)
     end
   end
 end

data/lib/langchain/vectorsearch/base.rb

@@ -124,6 +124,11 @@ module Langchain::Vectorsearch
       raise NotImplementedError, "#{self.class.name} does not support updating texts"
     end
 
+    # Method supported by Vectorsearch DB to delete a list of texts from the index
+    def remove_texts(...)
+      raise NotImplementedError, "#{self.class.name} does not support deleting texts"
+    end
+
     # Method supported by Vectorsearch DB to search for similar texts in the index
     def similarity_search(...)
       raise NotImplementedError, "#{self.class.name} does not support similarity search"

data/lib/langchain/vectorsearch/elasticsearch.rb

@@ -75,6 +75,17 @@ module Langchain::Vectorsearch
       es_client.bulk(body: body)
     end
 
+    # Remove a list of texts from the index
+    # @param ids [Array<Integer>] The list of ids to delete
+    # @return [Elasticsearch::Response] from the Elasticsearch server
+    def remove_texts(ids: [])
+      body = ids.map do |id|
+        {delete: {_index: index_name, _id: id}}
+      end
+
+      es_client.bulk(body: body)
+    end
+
     # Create the index with the default schema
     # @return [Elasticsearch::Response] Index creation
     def create_default_schema

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.9.5"
+  VERSION = "0.10.2"
 end

data/lib/langchain.rb

@@ -16,6 +16,8 @@ loader.inflector.inflect(
   "json" => "JSON",
   "jsonl" => "JSONL",
   "llm" => "LLM",
+  "mistral_ai" => "MistralAI",
+  "mistral_ai_response" => "MistralAIResponse",
   "openai" => "OpenAI",
   "openai_validator" => "OpenAIValidator",
   "openai_response" => "OpenAIResponse",
@@ -32,6 +34,11 @@ loader.collapse("#{__dir__}/langchain/tool/google_search")
 loader.collapse("#{__dir__}/langchain/tool/ruby_code_interpreter")
 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
+loader.ignore("#{__dir__}/langchain/tool/ruby_code_interpreter") if RUBY_VERSION >= "3.3.0"
+
 loader.setup
 
 # Langchain.rb a is library for building LLM-backed Ruby applications. It is an abstraction layer that sits on top of the emerging AI-related tools that makes it easy for developers to consume and string those services together.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.9.5
+  version: 0.10.2
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-03-15 00:00:00.000000000 Z
+date: 2024-03-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -472,6 +472,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.8'
+- !ruby/object:Gem::Dependency
+  name: mistral-ai
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: open-weather-ruby-client
   requirement: !ruby/object:Gem::Requirement
@@ -698,12 +712,6 @@ files:
 - lib/langchain/chunker/sentence.rb
 - lib/langchain/chunker/text.rb
 - lib/langchain/contextual_logger.rb
-- lib/langchain/conversation.rb
-- lib/langchain/conversation/context.rb
-- lib/langchain/conversation/memory.rb
-- lib/langchain/conversation/message.rb
-- lib/langchain/conversation/prompt.rb
-- lib/langchain/conversation/response.rb
 - lib/langchain/data.rb
 - lib/langchain/dependency_helper.rb
 - lib/langchain/evals/ragas/answer_relevance.rb
@@ -724,6 +732,7 @@ files:
 - lib/langchain/llm/google_vertex_ai.rb
 - lib/langchain/llm/hugging_face.rb
 - lib/langchain/llm/llama_cpp.rb
+- lib/langchain/llm/mistral_ai.rb
 - lib/langchain/llm/ollama.rb
 - lib/langchain/llm/openai.rb
 - lib/langchain/llm/prompts/ollama/summarize_template.yaml
@@ -738,6 +747,7 @@ files:
 - lib/langchain/llm/response/google_vertex_ai_response.rb
 - lib/langchain/llm/response/hugging_face_response.rb
 - lib/langchain/llm/response/llama_cpp_response.rb
+- lib/langchain/llm/response/mistral_ai_response.rb
 - lib/langchain/llm/response/ollama_response.rb
 - lib/langchain/llm/response/openai_response.rb
 - lib/langchain/llm/response/replicate_response.rb
@@ -812,7 +822,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.0.0
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="

data/lib/langchain/conversation/context.rb

@@ -1,8 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain
-  class Conversation
-    class Context < Message
-    end
-  end
-end

data/lib/langchain/conversation/memory.rb

@@ -1,83 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain
-  class Conversation
-    class Memory
-      attr_reader :messages
-
-      # The least number of tokens we want to be under the limit by
-      TOKEN_LEEWAY = 20
-
-      def initialize(llm:, messages: [], **options)
-        warn "[DEPRECATION] `Langchain::Conversation::Memory` is deprecated. Please use `Langchain::Assistant` instead."
-
-        @llm = llm
-        @context = nil
-        @summary = nil
-        @messages = messages
-        @strategy = options.delete(:strategy) || :truncate
-        @options = options
-      end
-
-      def set_context(message)
-        @context = message
-      end
-
-      def append_message(message)
-        @messages.append(message)
-      end
-
-      def reduce_messages(exception)
-        case @strategy
-        when :truncate
-          truncate_messages(exception)
-        when :summarize
-          summarize_messages
-        else
-          raise "Unknown strategy: #{@options[:strategy]}"
-        end
-      end
-
-      def context
-        return if @context.nil? && @summary.nil?
-
-        Context.new([@context, @summary].compact.join("\n"))
-      end
-
-      private
-
-      def truncate_messages(exception)
-        raise exception if @messages.size == 1
-
-        token_overflow = exception.token_overflow
-
-        @messages = @messages.drop_while do |message|
-          proceed = token_overflow > -TOKEN_LEEWAY
-          token_overflow -= token_length(message.to_json, model_name, llm: @llm)
-
-          proceed
-        end
-      end
-
-      def summarize_messages
-        history = [@summary, @messages.to_json].compact.join("\n")
-        partitions = [history[0, history.size / 2], history[history.size / 2, history.size]]
-
-        @summary = partitions.map { |messages| @llm.summarize(text: messages.to_json) }.join("\n")
-
-        @messages = [@messages.last]
-      end
-
-      def partition_messages
-      end
-
-      def model_name
-        @llm.class::DEFAULTS[:chat_completion_model_name]
-      end
-
-      def token_length(content, model_name, options)
-        @llm.class::LENGTH_VALIDATOR.token_length(content, model_name, options)
-      end
-    end
-  end
-end

data/lib/langchain/conversation/message.rb

@@ -1,50 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain
-  class Conversation
-    class Message
-      attr_reader :content
-
-      ROLE_MAPPING = {
-        context: "system",
-        prompt: "user",
-        response: "assistant"
-      }
-
-      def initialize(content)
-        warn "[DEPRECATION] `Langchain::Conversation::*` is deprecated. Please use `Langchain::Assistant` and `Langchain::Messages` classes instead."
-
-        @content = content
-      end
-
-      def role
-        ROLE_MAPPING[type]
-      end
-
-      def to_s
-        content
-      end
-
-      def to_h
-        {
-          role: role,
-          content: content
-        }
-      end
-
-      def ==(other)
-        to_json == other.to_json
-      end
-
-      def to_json(options = {})
-        to_h.to_json
-      end
-
-      private
-
-      def type
-        self.class.to_s.split("::").last.downcase.to_sym
-      end
-    end
-  end
-end

data/lib/langchain/conversation/prompt.rb

@@ -1,8 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain
-  class Conversation
-    class Prompt < Message
-    end
-  end
-end

data/lib/langchain/conversation/response.rb

@@ -1,8 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain
-  class Conversation
-    class Response < Message
-    end
-  end
-end

data/lib/langchain/conversation.rb

@@ -1,82 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain
-  #
-  # A high-level API for running a conversation with an LLM.
-  # Currently supports: OpenAI and Google PaLM LLMs.
-  #
-  # Usage:
-  #     llm = Langchain::LLM::OpenAI.new(api_key: "YOUR_API_KEY")
-  #     chat = Langchain::Conversation.new(llm: llm)
-  #     chat.set_context("You are a chatbot from the future")
-  #     chat.message("Tell me about future technologies")
-  #
-  # To stream the chat response:
-  #     chat = Langchain::Conversation.new(llm: llm) do |chunk|
-  #       print(chunk)
-  #     end
-  #
-  class Conversation
-    attr_reader :options
-
-    # Intialize Conversation with a LLM
-    #
-    # @param llm [Object] The LLM to use for the conversation
-    # @param options [Hash] Options to pass to the LLM, like temperature, top_k, etc.
-    # @return [Langchain::Conversation] The Langchain::Conversation instance
-    def initialize(llm:, **options, &block)
-      warn "[DEPRECATION] `Langchain::Conversation` is deprecated. Please use `Langchain::Assistant` instead."
-
-      @llm = llm
-      @context = nil
-      @memory = ::Langchain::Conversation::Memory.new(
-        llm: llm,
-        messages: options.delete(:messages) || [],
-        strategy: options.delete(:memory_strategy)
-      )
-      @options = options
-      @block = block
-    end
-
-    # Set the context of the conversation. Usually used to set the model's persona.
-    # @param message [String] The context of the conversation
-    def set_context(message)
-      @memory.set_context ::Langchain::Conversation::Context.new(message)
-    end
-
-    # Message the model with a prompt and return the response.
-    # @param message [String] The prompt to message the model with
-    # @return [Response] The response from the model
-    def message(message)
-      @memory.append_message ::Langchain::Conversation::Prompt.new(message)
-      ai_message = ::Langchain::Conversation::Response.new(llm_response.chat_completion)
-      @memory.append_message(ai_message)
-      ai_message
-    end
-
-    # Messages from conversation memory
-    # @return [Array<Prompt|Response>] The messages from the conversation memory
-    def messages
-      @memory.messages
-    end
-
-    # Context from conversation memory
-    # @return [Context] Context from conversation memory
-    def context
-      @memory.context
-    end
-
-    private
-
-    def llm_response
-      message_history = messages.map(&:to_h)
-      # Prepend the system message as context as the first message
-      message_history.prepend({role: "system", content: @memory.context.to_s}) if @memory.context
-
-      @llm.chat(messages: message_history, **@options, &@block)
-    rescue Langchain::Utils::TokenLength::TokenLimitExceeded => exception
-      @memory.reduce_messages(exception)
-      retry
-    end
-  end
-end