langchainrb 0.14.0 → 0.15.1

data/lib/langchain/tool/base.rb

@@ -1,107 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain::Tool
-  # = Tools
-  #
-  # Tools are used by Agents to perform specific tasks. A 'Tool' is a collection of functions ("methods").
-  #
-  # == Available Tools
-  #
-  # - {Langchain::Tool::Calculator}: calculate the result of a math expression
-  # - {Langchain::Tool::Database}: executes SQL queries
-  # - {Langchain::Tool::FileSystem}: interacts with the file system
-  # - {Langchain::Tool::GoogleSearch}: search on Google (via SerpAPI)
-  # - {Langchain::Tool::RubyCodeInterpreter}: runs ruby code
-  # - {Langchain::Tool::Weather}: gets current weather data
-  # - {Langchain::Tool::Wikipedia}: search on Wikipedia
-  #
-  # == Usage
-  #
-  # 1. Pick the tools you'd like to pass to an Agent and install the gems listed under **Gem Requirements**
-  #
-  #     # For example to use the Calculator, GoogleSearch, and Wikipedia:
-  #     gem install eqn
-  #     gem install google_search_results
-  #     gem install wikipedia-client
-  #
-  # 2. Set the environment variables listed under **ENV Requirements**
-  #
-  #     export SERPAPI_API_KEY=paste-your-serpapi-api-key-here
-  #
-  # 3. Pass the tools when Agent is instantiated.
-  #
-  #     agent = Langchain::Assistant.new(
-  #       llm: Langchain::LLM::OpenAI.new(api_key: "YOUR_API_KEY"), # or other LLM that supports function calling (coming soon)
-  #       thread: Langchain::Thread.new,
-  #       tools: [
-  #         Langchain::Tool::GoogleSearch.new(api_key: "YOUR_API_KEY"),
-  #         Langchain::Tool::Calculator.new,
-  #         Langchain::Tool::Wikipedia.new
-  #       ]
-  #     )
-  #
-  # == Adding Tools
-  #
-  # 1. Create a new folder in lib/langchain/tool/your_tool_name/
-  # 2. Inside of this folder create a file with a class YourToolName that inherits from {Langchain::Tool::Base}
-  # 3. Add `NAME=` and `ANNOTATIONS_PATH=` constants in your Tool class
-  # 4. Implement various public methods in your tool class
-  # 5. Create a sidecar .json file in the same directory as your tool file annotating the methods in the Open API format
-  # 6. Add your tool to the {file:README.md}
-  class Base
-    include Langchain::DependencyHelper
-
-    # Returns the NAME constant of the tool
-    #
-    # @return [String] tool name
-    def name
-      self.class.const_get(:NAME)
-    end
-
-    def self.logger_options
-      {
-        color: :light_blue
-      }
-    end
-
-    # Returns the tool as a list of OpenAI formatted functions
-    #
-    # @return [Array<Hash>] List of hashes representing the tool as OpenAI formatted functions
-    def to_openai_tools
-      method_annotations
-    end
-
-    # Returns the tool as a list of Anthropic formatted functions
-    #
-    # @return [Array<Hash>] List of hashes representing the tool as Anthropic formatted functions
-    def to_anthropic_tools
-      method_annotations.map do |annotation|
-        # Slice out only the content of the "function" key
-        annotation["function"]
-          # Rename "parameters" to "input_schema" key
-          .transform_keys("parameters" => "input_schema")
-      end
-    end
-
-    # Returns the tool as a list of Google Gemini formatted functions
-    #
-    # @return [Array<Hash>] List of hashes representing the tool as Google Gemini formatted functions
-    def to_google_gemini_tools
-      method_annotations.map do |annotation|
-        # Slice out only the content of the "function" key
-        annotation["function"]
-      end
-    end
-
-    # Return tool's method annotations as JSON
-    #
-    # @return [Hash] Tool's method annotations
-    def method_annotations
-      JSON.parse(
-        File.read(
-          self.class.const_get(:ANNOTATIONS_PATH)
-        )
-      )
-    end
-  end
-end

data/lib/langchain/tool/calculator/calculator.json

@@ -1,19 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "calculator__execute",
-      "description": "Evaluates a pure math expression or if equation contains non-math characters (e.g.: \"12F in Celsius\") then it uses the google search calculator to evaluate the expression",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "input": {
-            "type": "string",
-            "description": "math expression"
-          }
-        },
-        "required": ["input"]
-      }
-    }
-  }
-]

data/lib/langchain/tool/calculator/calculator.rb

@@ -1,34 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain::Tool
-  class Calculator < Base
-    #
-    # A calculator tool that falls back to the Google calculator widget
-    #
-    # Gem requirements:
-    #     gem "eqn", "~> 1.6.5"
-    #     gem "google_search_results", "~> 2.0.0"
-    #
-    # Usage:
-    #     calculator = Langchain::Tool::Calculator.new
-    #
-    NAME = "calculator"
-    ANNOTATIONS_PATH = Langchain.root.join("./langchain/tool/#{NAME}/#{NAME}.json").to_path
-
-    def initialize
-      depends_on "eqn"
-    end
-
-    # Evaluates a pure math expression or if equation contains non-math characters (e.g.: "12F in Celsius") then it uses the google search calculator to evaluate the expression
-    #
-    # @param input [String] math expression
-    # @return [String] Answer
-    def execute(input:)
-      Langchain.logger.info("Executing \"#{input}\"", for: self.class)
-
-      Eqn::Calculator.calc(input)
-    rescue Eqn::ParseError, Eqn::NoVariableValueError
-      "\"#{input}\" is an invalid mathematical expression"
-    end
-  end
-end

data/lib/langchain/tool/database/database.json

@@ -1,46 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "database__describe_tables",
-      "description": "Database Tool: Returns the schema for a list of tables",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "tables": {
-            "type": "string",
-            "description": "The tables to describe."
-          }
-        },
-        "required": ["tables"]
-      }
-    }
-  }, {
-    "type": "function",
-    "function": {
-      "name": "database__list_tables",
-      "description": "Database Tool: Returns a list of tables in the database",
-      "parameters": {
-        "type": "object",
-        "properties": {},
-        "required": []
-      }
-    }
-  }, {
-    "type": "function",
-    "function": {
-      "name": "database__execute",
-      "description": "Database Tool: Executes a SQL query and returns the results",
-      "parameters": { 
-        "type": "object",
-        "properties": {
-          "input": {
-            "type": "string",
-            "description": "SQL query to be executed"
-          }
-        },
-        "required": ["input"]
-      }
-    }
-  }
-]

data/lib/langchain/tool/file_system/file_system.json

@@ -1,57 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "file_system__list_directory",
-      "description": "File System Tool: Lists out the content of a specified directory",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "directory_path": {
-            "type": "string",
-            "description": "Directory path to list"
-          }
-        },
-        "required": ["directory_path"]
-      }
-    }
-  },
-  {
-    "type": "function",
-    "function": {
-      "name": "file_system__read_file",
-      "description": "File System Tool: Reads the contents of a file",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "file_path": {
-            "type": "string",
-            "description": "Path to the file to read from"
-          }
-        },
-        "required": ["file_path"]
-      }
-    }
-  },
-  {
-    "type": "function",
-    "function": {
-      "name": "file_system__write_to_file",
-      "description": "File System Tool: Write content to a file",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "file_path": {
-            "type": "string",
-            "description": "Path to the file to write"
-          },
-          "content": {
-            "type": "string",
-            "description": "Content to write to the file"
-          }
-        },
-        "required": ["file_path", "content"]
-      }
-    }
-  }    
-]

data/lib/langchain/tool/file_system/file_system.rb

@@ -1,32 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain::Tool
-  class FileSystem < Base
-    #
-    # A tool that wraps the Ruby file system classes.
-    #
-    # Usage:
-    #    file_system = Langchain::Tool::FileSystem.new
-    #
-    NAME = "file_system"
-    ANNOTATIONS_PATH = Langchain.root.join("./langchain/tool/#{NAME}/#{NAME}.json").to_path
-
-    def list_directory(directory_path:)
-      Dir.entries(directory_path)
-    rescue Errno::ENOENT
-      "No such directory: #{directory_path}"
-    end
-
-    def read_file(file_path:)
-      File.read(file_path)
-    rescue Errno::ENOENT
-      "No such file: #{file_path}"
-    end
-
-    def write_to_file(file_path:, content:)
-      File.write(file_path, content)
-    rescue Errno::EACCES
-      "Permission denied: #{file_path}"
-    end
-  end
-end

data/lib/langchain/tool/google_search/google_search.json

@@ -1,19 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "google_search-execute",
-      "description": "Executes Google Search and returns the result",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "input": {
-            "type": "string",
-            "description": "search query"
-          }
-        },
-        "required": ["input"]
-      }
-    }
-  }
-]

data/lib/langchain/tool/news_retriever/news_retriever.json

@@ -1,122 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "news_retriever__get_everything",
-      "description": "News Retriever: Search through millions of articles from over 150,000 large and small news sources and blogs.",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "q": {
-            "type": "string",
-            "description": "Keywords or phrases to search for in the article title and body. Surround phrases with quotes (\") for exact match. Alternatively you can use the AND / OR / NOT keywords, and optionally group these with parenthesis. Must be URL-encoded."
-          },
-          "search_in": {
-            "type": "string",
-            "description": "The fields to restrict your q search to.",
-            "enum": ["title", "description", "content"]
-          },
-          "sources": {
-            "type": "string",
-            "description": "A comma-seperated string of identifiers (maximum 20) for the news sources or blogs you want headlines from. Use the /sources endpoint to locate these programmatically or look at the sources index."
-          },
-          "domains": {
-            "type": "string",
-            "description": "A comma-seperated string of domains (eg bbc.co.uk, techcrunch.com, engadget.com) to restrict the search to."
-          },
-          "exclude_domains": {
-            "type": "string",
-            "description": "A comma-seperated string of domains (eg bbc.co.uk, techcrunch.com, engadget.com) to remove from the results."
-          },
-          "from": {
-            "type": "string",
-            "description": "A date and optional time for the oldest article allowed. This should be in ISO 8601 format."
-          },
-          "to": {
-            "type": "string",
-            "description": "A date and optional time for the newest article allowed. This should be in ISO 8601 format."
-          },
-          "language": {
-            "type": "string",
-            "description": "The 2-letter ISO-639-1 code of the language you want to get headlines for.",
-            "enum": ["ar", "de", "en", "es", "fr", "he", "it", "nl", "no", "pt", "ru", "sv", "ud", "zh"]
-          },
-          "sort_by": {
-            "type": "string",
-            "description": "The order to sort the articles in.",
-            "enum": ["relevancy", "popularity", "publishedAt"]
-          },
-          "page_size": {
-            "type": "integer",
-            "description": "The number of results to return per page (request). 5 is the default, 100 is the maximum."
-          },
-          "page": {
-            "type": "integer",
-            "description": "Use this to page through the results if the total results found is greater than the page size."
-          } 
-        }
-      }
-    }
-  },
-  {
-    "type": "function",
-    "function": {
-      "name": "news_retriever__get_top_headlines",
-      "description": "News Retriever: Provides live top and breaking headlines for a country, specific category in a country, single source, or multiple sources. You can also search with keywords. Articles are sorted by the earliest date published first.",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "country": {
-            "type": "string",
-            "description": "The 2-letter ISO 3166-1 code of the country you want to get headlines for.",
-            "enum": ["ae", "ar", "at", "au", "be", "bg", "br", "ca", "ch", "cn", "co", "cu", "cz", "de", "eg", "fr", "gb", "gr", "hk", "hu", "id", "ie", "il", "in", "it", "jp", "kr", "lt", "lv", "ma", "mx", "my", "ng", "nl", "no", "nz", "ph", "pl", "pt", "ro", "rs", "ru", "sa", "se", "sg", "si", "sk", "th", "tr", "tw", "ua", "us", "ve", "za"]
-          },
-          "category": {
-            "type": "string",
-            "description": "The category you want to get headlines for.",
-            "enum": ["business", "entertainment", "general", "health", "science", "sports", "technology"]
-          },
-          "q": {
-            "type": "string",
-            "description": "Keywords or a phrase to search for."
-          },
-          "page_size": {
-            "type": "integer",
-            "description": "The number of results to return per page (request). 5 is the default, 100 is the maximum."
-          },
-          "page": {
-            "type": "integer",
-            "description": "Use this to page through the results if the total results found is greater than the page size."
-          } 
-        }
-      }
-    }
-  },
-  {
-    "type": "function",
-    "function": {
-      "name": "news_retriever__get_sources",
-      "description": "News Retriever: This endpoint returns the subset of news publishers that top headlines (/v2/top-headlines) are available from. It's mainly a convenience endpoint that you can use to keep track of the publishers available on the API, and you can pipe it straight through to your users.",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "country": {
-            "type": "string",
-            "description": "The 2-letter ISO 3166-1 code of the country you want to get headlines for. Default: all countries.",
-            "enum": ["ae", "ar", "at", "au", "be", "bg", "br", "ca", "ch", "cn", "co", "cu", "cz", "de", "eg", "fr", "gb", "gr", "hk", "hu", "id", "ie", "il", "in", "it", "jp", "kr", "lt", "lv", "ma", "mx", "my", "ng", "nl", "no", "nz", "ph", "pl", "pt", "ro", "rs", "ru", "sa", "se", "sg", "si", "sk", "th", "tr", "tw", "ua", "us", "ve", "za"]
-          },
-          "category": {
-            "type": "string",
-            "description": "The category you want to get headlines for. Default: all categories.",
-            "enum": ["business", "entertainment", "general", "health", "science", "sports", "technology"]
-          },
-          "language": {
-            "type": "string",
-            "description": "The 2-letter ISO-639-1 code of the language you want to get headlines for.",
-            "enum": ["ar", "de", "en", "es", "fr", "he", "it", "nl", "no", "pt", "ru", "sv", "ud", "zh"]
-          }
-        }
-      }
-    }
-  }
-]

data/lib/langchain/tool/ruby_code_interpreter/ruby_code_interpreter.json

@@ -1,19 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "ruby_code_interpreter__execute",
-      "description": "Executes Ruby code in a sandboxes environment.",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "input": {
-            "type": "string",
-            "description": "ruby code expression"
-          }
-        },
-        "required": ["input"]
-      }
-    }
-  }
-]

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

@@ -1,37 +0,0 @@
-# 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
-
-    def initialize(timeout: 30)
-      depends_on "safe_ruby"
-
-      @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)
-
-      safe_eval(input)
-    end
-
-    def safe_eval(code)
-      SafeRuby.eval(code, timeout: @timeout)
-    end
-  end
-end

data/lib/langchain/tool/tavily/tavily.json

@@ -1,54 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "tavily__search",
-      "description": "Tavily Tool: Robust search API",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "query": {
-            "type": "string",
-            "description": "The search query string"
-          },
-          "search_depth": {
-            "type": "string",
-            "description": "The depth of the search: basic for quick results and advanced for indepth high quality results but longer response time",
-            "enum": ["basic", "advanced"]
-          },
-          "include_images": {
-            "type": "boolean",
-            "description": "Include a list of query related images in the response"
-          },
-          "include_answer": {
-            "type": "boolean",
-            "description": "Include answers in the search results"
-          },
-          "include_raw_content": {
-            "type": "boolean",
-            "description": "Include raw content in the search results"
-          },
-          "max_results": {
-            "type": "integer",
-            "description": "The number of maximum search results to return"
-          },
-          "include_domains": {
-            "type": "array",
-            "items": {
-              "type": "string"
-            },
-            "description": "A list of domains to specifically include in the search results"
-          },
-          "exclude_domains": {
-            "type": "array",
-            "items": {
-              "type": "string"
-            },
-            "description": "A list of domains to specifically exclude from the search results"
-          }
-        },
-        "required": ["query"]
-      }
-    }
-  }
-]

data/lib/langchain/tool/vectorsearch/vectorsearch.json

@@ -1,24 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "vectorsearch__similarity_search",
-      "description": "Vectorsearch: Retrieves relevant document for the query",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "query": {
-            "type": "string",
-            "description": "Query to find similar documents for"
-          },
-          "k": {
-            "type": "integer",
-            "description": "Number of similar documents to retrieve",
-            "default": 4
-          }
-        },
-        "required": ["query"]
-      }
-    }
-  }
-]

data/lib/langchain/tool/vectorsearch/vectorsearch.rb

@@ -1,36 +0,0 @@
-# frozen_string_literal: true
-
-module Langchain::Tool
-  class Vectorsearch < Base
-    #
-    # A tool wraps vectorsearch classes
-    #
-    # Usage:
-    #    # Initialize the LLM that will be used to generate embeddings
-    #    ollama = Langchain::LLM::Ollama.new(url: ENV["OLLAMA_URL"]
-    #    chroma = Langchain::Vectorsearch::Chroma.new(url: ENV["CHROMA_URL"], index_name: "my_index", llm: ollama)
-    #
-    #    # This tool can now be used by the Assistant
-    #    vectorsearch_tool = Langchain::Tool::Vectorsearch.new(vectorsearch: chroma)
-    #
-    NAME = "vectorsearch"
-    ANNOTATIONS_PATH = Langchain.root.join("./langchain/tool/#{NAME}/#{NAME}.json").to_path
-
-    attr_reader :vectorsearch
-
-    # Initializes the Vectorsearch tool
-    #
-    # @param vectorsearch [Langchain::Vectorsearch::Base] Vectorsearch instance to use
-    def initialize(vectorsearch:)
-      @vectorsearch = vectorsearch
-    end
-
-    # Executes the vector search and returns the results
-    #
-    # @param query [String] The query to search for
-    # @param k [Integer] The number of results to return
-    def similarity_search(query:, k: 4)
-      vectorsearch.similarity_search(query:, k: 4)
-    end
-  end
-end

data/lib/langchain/tool/weather/weather.json

@@ -1,19 +0,0 @@
-[
-  {
-    "type": "function",
-    "function": {
-      "name": "weather__execute",
-      "description": "Returns current weather for a city",
-      "parameters": {
-        "type": "object",
-        "properties": {
-          "input": {
-            "type": "string",
-            "description": "comma separated city and unit (optional: imperial, metric, or standard)"
-          }
-        },
-        "required": ["input"]
-      }
-    }
-  }
-]