langchainrb 0.9.4 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 62c459d5dc2f716eaeb81697bdf45ad42ae168784d28ff8a80a89d1b3e14eadd
-  data.tar.gz: 8bb1f94373c54619235cb24ea705179626e398d517739b93014a514283068468
+  metadata.gz: 81783847d8152dbcff9e1ea0b51afee5619fb863b1cf3bf2f66912a52e96e797
+  data.tar.gz: 877bf77b04771a9a898d478967a0df5ef8ab2d62371f7e71c67e76daf39cffb9
 SHA512:
-  metadata.gz: 4b6bd3fb3a983458dd0ff83573e268c4ab8ae26fcffbab93826d3f3143a648b3fa2fcb9e93ba1139551cf8b6d8641da74ea78d098e42ecd672245ca41610c137
-  data.tar.gz: a40d5bfb0301e7e9e4d66a708fc6bc048272da772bad21473f88be219caf139c86f8cbcf9ea73a3454642042872e796595518a75eb5e9ad3ba5288adf823bfc7
+  metadata.gz: 8a3c6e98399f8d76d10c0ccdd6af2650c77962662490a9541daf1bcb76f693c19637b8bdd140800dd920f116753178bdda7e7a2dd0649c9fdafaad837df3a3db
+  data.tar.gz: 8f0a18c9c3c25c2bea9041e5884aa2a29e79549fbbd73255f27bc2a6053e4524b4f3d0a4896d002291cf6f2b74c277462aa85d3933a2a3c4ab7499901d9aa89b

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 ## [Unreleased]
-- `Langchain::LLM::Ollama` can now `#summarize`
+
+## [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
+- Add Ruby 3.3 support
 
 ## [0.9.4]
 - New `Ollama#summarize()` method

data/lib/langchain/llm/openai.rb

@@ -17,7 +17,7 @@ module Langchain::LLM
       n: 1,
       temperature: 0.0,
       chat_completion_model_name: "gpt-3.5-turbo",
-      embeddings_model_name: "text-embedding-ada-002"
+      embeddings_model_name: "text-embedding-3-small"
     }.freeze
 
     EMBEDDING_SIZES = {
@@ -53,7 +53,8 @@ module Langchain::LLM
       text:,
       model: defaults[:embeddings_model_name],
       encoding_format: nil,
-      user: nil
+      user: nil,
+      dimensions: EMBEDDING_SIZES.fetch(model.to_sym, nil)
     )
       raise ArgumentError.new("text argument is required") if text.empty?
       raise ArgumentError.new("model argument is required") if model.empty?
@@ -61,12 +62,15 @@ module Langchain::LLM
 
       parameters = {
         input: text,
-        model: model,
-        dimensions: default_dimension
+        model: model
       }
       parameters[:encoding_format] = encoding_format if encoding_format
       parameters[:user] = user if user
 
+      if ["text-embedding-3-small", "text-embedding-3-large"].include?(model)
+        parameters[:dimensions] = EMBEDDING_SIZES[model.to_sym] if EMBEDDING_SIZES.key?(model.to_sym)
+      end
+
       validate_max_tokens(text, parameters[:model])
 
       response = with_api_error_handling do

data/lib/langchain/processors/eml.rb

@@ -1,4 +1,3 @@
-require "mail"
 require "uri"
 
 module Langchain

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

@@ -1,41 +1,45 @@
 # frozen_string_literal: true
 
-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
+# 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
 
-    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)
+      def safe_eval(code)
+        SafeRuby.eval(code, timeout: @timeout)
+      end
     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/chroma.rb

@@ -60,6 +60,13 @@ module Langchain::Vectorsearch
       collection.update(embeddings)
     end
 
+    # Remove a list of texts from the index
+    # @param ids [Array<String>] The list of ids to remove
+    # @return [Hash] The response from the server
+    def remove_texts(ids:)
+      collection.delete(ids)
+    end
+
     # Create the collection with the default schema
     # @return [::Chroma::Resources::Collection] Created collection
     def create_default_schema

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/vectorsearch/qdrant.rb

@@ -64,6 +64,16 @@ module Langchain::Vectorsearch
       add_texts(texts: texts, ids: ids)
     end
 
+    # Remove a list of texts from the index
+    # @param ids [Array<Integer>] The ids to remove
+    # @return [Hash] The response from the server
+    def remove_texts(ids:)
+      client.points.delete(
+        collection_name: index_name,
+        points: ids
+      )
+    end
+
     # Get the default schema
     # @return [Hash] The response from the server
     def get_default_schema

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.9.4"
+  VERSION = "0.10.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.9.4
+  version: 0.10.0
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-02-28 00:00:00.000000000 Z
+date: 2024-03-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -698,12 +698,6 @@ 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
@@ -819,7 +813,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.1
+rubygems_version: 3.5.3
 signing_key:
 specification_version: 4
 summary: Build LLM-backed Ruby applications with Ruby's Langchain.rb

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