langchainrb 0.14.0 → 0.15.0

data/lib/langchain/utils/hash_transformer.rb

@@ -1,24 +1,16 @@
 module Langchain
   module Utils
     class HashTransformer
-      # Converts a string to camelCase
-      def self.camelize_lower(str)
-        str.split("_").inject([]) { |buffer, e| buffer.push(buffer.empty? ? e : e.capitalize) }.join
-      end
-
-      # Recursively transforms the keys of a hash to camel case
-      def self.deep_transform_keys(hash, &block)
-        case hash
-        when Hash
-          hash.each_with_object({}) do |(key, value), result|
-            new_key = block.call(key)
-            result[new_key] = deep_transform_keys(value, &block)
+      def self.symbolize_keys(hash)
+        hash.map do |k, v|
+          new_key = begin
+            k.to_sym
+          rescue
+            k
           end
-        when Array
-          hash.map { |item| deep_transform_keys(item, &block) }
-        else
-          hash
-        end
+          new_value = v.is_a?(Hash) ? symbolize_keys(v) : v
+          [new_key, new_value]
+        end.to_h
       end
     end
   end

data/lib/langchain/vectorsearch/chroma.rb

@@ -124,7 +124,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -136,7 +136,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/elasticsearch.rb

@@ -143,7 +143,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -153,7 +153,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/epsilla.rb

@@ -96,7 +96,7 @@ module Langchain::Vectorsearch
 
       status_code, response = @client.database.insert(@table_name, data)
       raise "Failed to insert texts: #{response}" if status_code != 200
-      response
+      JSON.parse(response)
     end
 
     # Search for similar texts
@@ -129,7 +129,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -140,7 +140,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/milvus.rb

@@ -156,7 +156,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       content_field = search_results.dig("results", "fields_data").select { |field| field.dig("field_name") == "content" }
@@ -167,7 +167,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/pgvector.rb

@@ -146,7 +146,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -157,7 +157,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/pinecone.rb

@@ -171,7 +171,7 @@ module Langchain::Vectorsearch
     # @param filter [String] The filter to use
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, namespace: "", filter: nil, k: 4, &)
+    def ask(question:, namespace: "", filter: nil, k: 4, &block)
       search_results = similarity_search(query: question, namespace: namespace, filter: filter, k: k)
 
       context = search_results.map do |result|
@@ -182,7 +182,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/qdrant.rb

@@ -137,7 +137,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -148,7 +148,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/weaviate.rb

@@ -6,7 +6,7 @@ module Langchain::Vectorsearch
     # Wrapper around Weaviate
     #
     # Gem requirements:
-    #     gem "weaviate-ruby", "~> 0.8.9"
+    #     gem "weaviate-ruby", "~> 0.9.0"
     #
     # Usage:
     #     weaviate = Langchain::Vectorsearch::Weaviate.new(url: ENV["WEAVIATE_URL"], api_key: ENV["WEAVIATE_API_KEY"], index_name: "Docs", llm: llm)
@@ -17,7 +17,7 @@ module Langchain::Vectorsearch
     # @param api_key [String] The API key to use
     # @param index_name [String] The capitalized name of the index to use
     # @param llm [Object] The LLM client to use
-    def initialize(url:, api_key:, index_name:, llm:)
+    def initialize(url:, index_name:, llm:, api_key: nil)
       depends_on "weaviate-ruby", req: "weaviate"
 
       @client = ::Weaviate::Client.new(
@@ -143,7 +143,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [Hash] The answer
-    def ask(question:, k: 4, &)
+    def ask(question:, k: 4, &block)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -154,7 +154,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &)
+      response = llm.chat(messages: messages, &block)
 
       response.context = context
       response

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.14.0"
+  VERSION = "0.15.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.14.0
+  version: 0.15.0
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-07-12 00:00:00.000000000 Z
+date: 2024-08-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: baran
@@ -774,27 +774,17 @@ files:
 - lib/langchain/prompt/few_shot_prompt_template.rb
 - lib/langchain/prompt/loading.rb
 - lib/langchain/prompt/prompt_template.rb
-- lib/langchain/tool/base.rb
-- lib/langchain/tool/calculator/calculator.json
-- lib/langchain/tool/calculator/calculator.rb
-- lib/langchain/tool/database/database.json
-- lib/langchain/tool/database/database.rb
-- lib/langchain/tool/file_system/file_system.json
-- lib/langchain/tool/file_system/file_system.rb
-- lib/langchain/tool/google_search/google_search.json
-- lib/langchain/tool/google_search/google_search.rb
-- lib/langchain/tool/news_retriever/news_retriever.json
-- lib/langchain/tool/news_retriever/news_retriever.rb
-- lib/langchain/tool/ruby_code_interpreter/ruby_code_interpreter.json
-- lib/langchain/tool/ruby_code_interpreter/ruby_code_interpreter.rb
-- lib/langchain/tool/tavily/tavily.json
-- lib/langchain/tool/tavily/tavily.rb
-- lib/langchain/tool/vectorsearch/vectorsearch.json
-- lib/langchain/tool/vectorsearch/vectorsearch.rb
-- lib/langchain/tool/weather/weather.json
-- lib/langchain/tool/weather/weather.rb
-- lib/langchain/tool/wikipedia/wikipedia.json
-- lib/langchain/tool/wikipedia/wikipedia.rb
+- lib/langchain/tool/calculator.rb
+- lib/langchain/tool/database.rb
+- lib/langchain/tool/file_system.rb
+- lib/langchain/tool/google_search.rb
+- lib/langchain/tool/news_retriever.rb
+- lib/langchain/tool/ruby_code_interpreter.rb
+- lib/langchain/tool/tavily.rb
+- lib/langchain/tool/vectorsearch.rb
+- lib/langchain/tool/weather.rb
+- lib/langchain/tool/wikipedia.rb
+- lib/langchain/tool_definition.rb
 - lib/langchain/utils/cosine_similarity.rb
 - lib/langchain/utils/hash_transformer.rb
 - lib/langchain/vectorsearch/base.rb

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"]
-      }
-    }
-  }
-]