langchainrb 0.7.2 → 0.7.5

data/lib/langchain/agent/agents.md

@@ -0,0 +1,54 @@
+
+### Agents 🤖
+Agents are semi-autonomous bots that can respond to user questions and use available to them Tools to provide informed replies. They break down problems into series of steps and define Actions (and Action Inputs) along the way that are executed and fed back to them as additional information. Once an Agent decides that it has the Final Answer it responds with it.
+
+#### ReAct Agent
+
+Add `gem "ruby-openai"`, `gem "eqn"`, and `gem "google_search_results"` to your Gemfile
+
+```ruby
+search_tool = Langchain::Tool::GoogleSearch.new(api_key: ENV["SERPAPI_API_KEY"])
+calculator = Langchain::Tool::Calculator.new
+
+openai = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+
+agent = Langchain::Agent::ReActAgent.new(
+  llm: openai,
+  tools: [search_tool, calculator]
+)
+```
+```ruby
+agent.run(question: "How many full soccer fields would be needed to cover the distance between NYC and DC in a straight line?")
+#=> "Approximately 2,945 soccer fields would be needed to cover the distance between NYC and DC in a straight line."
+```
+
+#### SQL-Query Agent
+
+Add `gem "sequel"` to your Gemfile
+
+```ruby
+database = Langchain::Tool::Database.new(connection_string: "postgres://user:password@localhost:5432/db_name")
+
+agent = Langchain::Agent::SQLQueryAgent.new(llm: Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"]), db: database)
+```
+```ruby
+agent.run(question: "How many users have a name with length greater than 5 in the users table?")
+#=> "14 users have a name with length greater than 5 in the users table."
+```
+
+#### Demo
+![May-12-2023 13-09-13](https://github.com/andreibondarev/langchainrb/assets/541665/6bad4cd9-976c-420f-9cf9-b85bf84f7eaf)
+
+![May-12-2023 13-07-45](https://github.com/andreibondarev/langchainrb/assets/541665/9aacdcc7-4225-4ea0-ab96-7ee48826eb9b)
+
+#### Available Tools 🛠️
+
+| Name         | Description                                        | ENV Requirements                                              | Gem Requirements                          |
+| ------------ | :------------------------------------------------: | :-----------------------------------------------------------: | :---------------------------------------: |
+| "calculator" | Useful for getting the result of a math expression |                                                               | `gem "eqn", "~> 1.6.5"`                   |
+| "database"   | Useful for querying a SQL database |                                                               | `gem "sequel", "~> 5.68.0"`                   |
+| "ruby_code_interpreter" | Interprets Ruby expressions             |                                                               | `gem "safe_ruby", "~> 1.0.4"`             |
+| "google_search"     | A wrapper around Google Search                     | `ENV["SERPAPI_API_KEY"]` (https://serpapi.com/manage-api-key) | `gem "google_search_results", "~> 2.0.0"` |
+| "weather"  | Calls Open Weather API to retrieve the current weather        |      `ENV["OPEN_WEATHER_API_KEY"]` (https://home.openweathermap.org/api_keys)               | `gem "open-weather-ruby-client", "~> 0.3.0"`    |
+| "wikipedia"  | Calls Wikipedia API to retrieve the summary        |                                                               | `gem "wikipedia-client", "~> 1.17.0"`     |
+

data/lib/langchain/llm/aws_bedrock.rb

@@ -0,0 +1,216 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  # LLM interface for Aws Bedrock APIs: https://docs.aws.amazon.com/bedrock/
+  #
+  # Gem requirements:
+  #    gem 'aws-sdk-bedrockruntime', '~> 1.1'
+  #
+  # Usage:
+  #    bedrock = Langchain::LLM::AwsBedrock.new(llm_options: {})
+  #
+  class AwsBedrock < Base
+    DEFAULTS = {
+      completion_model_name: "anthropic.claude-v2",
+      embedding_model_name: "amazon.titan-embed-text-v1",
+      max_tokens_to_sample: 300,
+      temperature: 1,
+      top_k: 250,
+      top_p: 0.999,
+      stop_sequences: ["\n\nHuman:"],
+      anthropic_version: "bedrock-2023-05-31",
+      return_likelihoods: "NONE",
+      count_penalty: {
+        scale: 0,
+        apply_to_whitespaces: false,
+        apply_to_punctuations: false,
+        apply_to_numbers: false,
+        apply_to_stopwords: false,
+        apply_to_emojis: false
+      },
+      presence_penalty: {
+        scale: 0,
+        apply_to_whitespaces: false,
+        apply_to_punctuations: false,
+        apply_to_numbers: false,
+        apply_to_stopwords: false,
+        apply_to_emojis: false
+      },
+      frequency_penalty: {
+        scale: 0,
+        apply_to_whitespaces: false,
+        apply_to_punctuations: false,
+        apply_to_numbers: false,
+        apply_to_stopwords: false,
+        apply_to_emojis: false
+      }
+    }.freeze
+
+    SUPPORTED_COMPLETION_PROVIDERS = %i[anthropic cohere ai21].freeze
+    SUPPORTED_EMBEDDING_PROVIDERS = %i[amazon].freeze
+
+    def initialize(completion_model: DEFAULTS[:completion_model_name], embedding_model: DEFAULTS[:embedding_model_name], 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)
+    end
+
+    #
+    # Generate an embedding for a given text
+    #
+    # @param text [String] The text to generate an embedding for
+    # @param params extra parameters passed to Aws::BedrockRuntime::Client#invoke_model
+    # @return [Langchain::LLM::AwsTitanResponse] Response object
+    #
+    def embed(text:, **params)
+      raise "Completion provider #{embedding_provider} is not supported." unless SUPPORTED_EMBEDDING_PROVIDERS.include?(embedding_provider)
+
+      parameters = {inputText: text}
+      parameters = parameters.merge(params)
+
+      response = client.invoke_model({
+        model_id: @defaults[:embedding_model_name],
+        body: parameters.to_json,
+        content_type: "application/json",
+        accept: "application/json"
+      })
+
+      Langchain::LLM::AwsTitanResponse.new(JSON.parse(response.body.string))
+    end
+
+    #
+    # Generate a completion for a given prompt
+    #
+    # @param prompt [String] The prompt to generate a completion for
+    # @param params  extra parameters passed to Aws::BedrockRuntime::Client#invoke_model
+    # @return [Langchain::LLM::AnthropicResponse], [Langchain::LLM::CohereResponse] or [Langchain::LLM::AI21Response] Response object
+    #
+    def complete(prompt:, **params)
+      raise "Completion provider #{completion_provider} is not supported." unless SUPPORTED_COMPLETION_PROVIDERS.include?(completion_provider)
+
+      parameters = compose_parameters params
+
+      parameters[:prompt] = wrap_prompt prompt
+
+      response = client.invoke_model({
+        model_id: @defaults[:completion_model_name],
+        body: parameters.to_json,
+        content_type: "application/json",
+        accept: "application/json"
+      })
+
+      parse_response response
+    end
+
+    private
+
+    def completion_provider
+      @defaults[:completion_model_name].split(".").first.to_sym
+    end
+
+    def embedding_provider
+      @defaults[:embedding_model_name].split(".").first.to_sym
+    end
+
+    def wrap_prompt(prompt)
+      if completion_provider == :anthropic
+        "\n\nHuman: #{prompt}\n\nAssistant:"
+      else
+        prompt
+      end
+    end
+
+    def max_tokens_key
+      if completion_provider == :anthropic
+        :max_tokens_to_sample
+      elsif completion_provider == :cohere
+        :max_tokens
+      elsif completion_provider == :ai21
+        :maxTokens
+      end
+    end
+
+    def compose_parameters(params)
+      if completion_provider == :anthropic
+        compose_parameters_anthropic params
+      elsif completion_provider == :cohere
+        compose_parameters_cohere params
+      elsif completion_provider == :ai21
+        compose_parameters_ai21 params
+      end
+    end
+
+    def parse_response(response)
+      if completion_provider == :anthropic
+        Langchain::LLM::AnthropicResponse.new(JSON.parse(response.body.string))
+      elsif completion_provider == :cohere
+        Langchain::LLM::CohereResponse.new(JSON.parse(response.body.string))
+      elsif completion_provider == :ai21
+        Langchain::LLM::AI21Response.new(JSON.parse(response.body.string, symbolize_names: true))
+      end
+    end
+
+    def compose_parameters_cohere(params)
+      default_params = @defaults.merge(params)
+
+      {
+        max_tokens: default_params[:max_tokens_to_sample],
+        temperature: default_params[:temperature],
+        p: default_params[:top_p],
+        k: default_params[:top_k],
+        stop_sequences: default_params[:stop_sequences]
+      }
+    end
+
+    def compose_parameters_anthropic(params)
+      default_params = @defaults.merge(params)
+
+      {
+        max_tokens_to_sample: default_params[:max_tokens_to_sample],
+        temperature: default_params[:temperature],
+        top_k: default_params[:top_k],
+        top_p: default_params[:top_p],
+        stop_sequences: default_params[:stop_sequences],
+        anthropic_version: default_params[:anthropic_version]
+      }
+    end
+
+    def compose_parameters_ai21(params)
+      default_params = @defaults.merge(params)
+
+      {
+        maxTokens: default_params[:max_tokens_to_sample],
+        temperature: default_params[:temperature],
+        topP: default_params[:top_p],
+        stopSequences: default_params[:stop_sequences],
+        countPenalty: {
+          scale: default_params[:count_penalty][:scale],
+          applyToWhitespaces: default_params[:count_penalty][:apply_to_whitespaces],
+          applyToPunctuations: default_params[:count_penalty][:apply_to_punctuations],
+          applyToNumbers: default_params[:count_penalty][:apply_to_numbers],
+          applyToStopwords: default_params[:count_penalty][:apply_to_stopwords],
+          applyToEmojis: default_params[:count_penalty][:apply_to_emojis]
+        },
+        presencePenalty: {
+          scale: default_params[:presence_penalty][:scale],
+          applyToWhitespaces: default_params[:presence_penalty][:apply_to_whitespaces],
+          applyToPunctuations: default_params[:presence_penalty][:apply_to_punctuations],
+          applyToNumbers: default_params[:presence_penalty][:apply_to_numbers],
+          applyToStopwords: default_params[:presence_penalty][:apply_to_stopwords],
+          applyToEmojis: default_params[:presence_penalty][:apply_to_emojis]
+        },
+        frequencyPenalty: {
+          scale: default_params[:frequency_penalty][:scale],
+          applyToWhitespaces: default_params[:frequency_penalty][:apply_to_whitespaces],
+          applyToPunctuations: default_params[:frequency_penalty][:apply_to_punctuations],
+          applyToNumbers: default_params[:frequency_penalty][:apply_to_numbers],
+          applyToStopwords: default_params[:frequency_penalty][:apply_to_stopwords],
+          applyToEmojis: default_params[:frequency_penalty][:apply_to_emojis]
+        }
+      }
+    end
+  end
+end

data/lib/langchain/llm/openai.rb

@@ -4,7 +4,7 @@ module Langchain::LLM
   # LLM interface for OpenAI APIs: https://platform.openai.com/overview
   #
   # Gem requirements:
-  #    gem "ruby-openai", "~> 4.0.0"
+  #    gem "ruby-openai", "~> 5.2.0"
   #
   # Usage:
   #    openai = Langchain::LLM::OpenAI.new(api_key:, llm_options: {})
@@ -29,6 +29,7 @@ module Langchain::LLM
     LENGTH_VALIDATOR = Langchain::Utils::TokenLength::OpenAIValidator
 
     attr_accessor :functions
+    attr_accessor :response_chunks
 
     def initialize(api_key:, llm_options: {}, default_options: {})
       depends_on "ruby-openai", req: "openai"
@@ -69,7 +70,7 @@ module Langchain::LLM
       return legacy_complete(prompt, parameters) if is_legacy_model?(parameters[:model])
 
       parameters[:messages] = compose_chat_messages(prompt: prompt)
-      parameters[:max_tokens] = validate_max_tokens(parameters[:messages], parameters[:model])
+      parameters[:max_tokens] = validate_max_tokens(parameters[:messages], parameters[:model], parameters[:max_tokens])
 
       response = with_api_error_handling do
         client.chat(parameters: parameters)
@@ -131,13 +132,11 @@ module Langchain::LLM
       if functions
         parameters[:functions] = functions
       else
-        parameters[:max_tokens] = validate_max_tokens(parameters[:messages], parameters[:model])
+        parameters[:max_tokens] = validate_max_tokens(parameters[:messages], parameters[:model], parameters[:max_tokens])
       end
 
       response = with_api_error_handling { client.chat(parameters: parameters) }
-
-      return if block
-
+      response = response_from_chunks if block
       Langchain::LLM::OpenAIResponse.new(response)
     end
 
@@ -181,8 +180,11 @@ module Langchain::LLM
       parameters = default_params.merge(params)
 
       if block
+        @response_chunks = []
         parameters[:stream] = proc do |chunk, _bytesize|
-          yield chunk.dig("choices", 0)
+          chunk_content = chunk.dig("choices", 0)
+          @response_chunks << chunk
+          yield chunk_content
         end
       end
 
@@ -230,13 +232,28 @@ module Langchain::LLM
       response
     end
 
-    def validate_max_tokens(messages, model)
-      LENGTH_VALIDATOR.validate_max_tokens!(messages, model)
+    def validate_max_tokens(messages, model, max_tokens = nil)
+      LENGTH_VALIDATOR.validate_max_tokens!(messages, model, max_tokens: max_tokens)
     end
 
     def extract_response(response)
       results = response.dig("choices").map { |choice| choice.dig("message", "content") }
       (results.size == 1) ? results.first : results
     end
+
+    def response_from_chunks
+      @response_chunks.first&.slice("id", "object", "created", "model")&.merge(
+        {
+          "choices" => [
+            {
+              "message" => {
+                "role" => "assistant",
+                "content" => @response_chunks.map { |chunk| chunk.dig("choices", 0, "delta", "content") }.join
+              }
+            }
+          ]
+        }
+      )
+    end
   end
 end

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

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  class AwsTitanResponse < BaseResponse
+    def embedding
+      embeddings&.first
+    end
+
+    def embeddings
+      [raw_response.dig("embedding")]
+    end
+
+    def prompt_tokens
+      raw_response.dig("inputTextTokenCount")
+    end
+  end
+end

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

@@ -5,6 +5,9 @@ module Langchain
     class BaseResponse
       attr_reader :raw_response, :model
 
+      # Save context in the response when doing RAG workflow vectorsearch#ask()
+      attr_accessor :context
+
       def initialize(raw_response, model: nil)
         @raw_response = raw_response
         @model = model

data/lib/langchain/utils/token_length/ai21_validator.rb

@@ -30,6 +30,7 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS[model_name]
         end
+        singleton_class.alias_method :completion_token_limit, :token_limit
       end
     end
   end

data/lib/langchain/utils/token_length/base_validator.rb

@@ -21,12 +21,16 @@ module Langchain
 
           leftover_tokens = token_limit(model_name) - text_token_length
 
+          # Some models have a separate token limit for completions (e.g. GPT-4 Turbo)
+          # We want the lower of the two limits
+          max_tokens = [leftover_tokens, completion_token_limit(model_name)].min
+
           # Raise an error even if whole prompt is equal to the model's token limit (leftover_tokens == 0)
-          if leftover_tokens < 0
+          if max_tokens < 0
             raise limit_exceeded_exception(token_limit(model_name), text_token_length)
           end
 
-          leftover_tokens
+          max_tokens
         end
 
         def self.limit_exceeded_exception(limit, length)

data/lib/langchain/utils/token_length/cohere_validator.rb

@@ -38,6 +38,7 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS[model_name]
         end
+        singleton_class.alias_method :completion_token_limit, :token_limit
       end
     end
   end

data/lib/langchain/utils/token_length/google_palm_validator.rb

@@ -46,6 +46,7 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS.dig(model_name, "input_token_limit")
         end
+        singleton_class.alias_method :completion_token_limit, :token_limit
       end
     end
   end

data/lib/langchain/utils/token_length/openai_validator.rb

@@ -10,6 +10,14 @@ module Langchain
       # It is used to validate the token length before the API call is made
       #
       class OpenAIValidator < BaseValidator
+        COMPLETION_TOKEN_LIMITS = {
+          # GPT-4 Turbo has a separate token limit for completion
+          # Source:
+          # https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
+          "gpt-4-1106-preview" => 4096,
+          "gpt-4-vision-preview" => 4096
+        }
+
         TOKEN_LIMITS = {
           # Source:
           # https://platform.openai.com/docs/api-reference/embeddings
@@ -29,6 +37,8 @@ module Langchain
           "gpt-4-32k" => 32768,
           "gpt-4-32k-0314" => 32768,
           "gpt-4-32k-0613" => 32768,
+          "gpt-4-1106-preview" => 128000,
+          "gpt-4-vision-preview" => 128000,
           "text-curie-001" => 2049,
           "text-babbage-001" => 2049,
           "text-ada-001" => 2049,
@@ -53,6 +63,16 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS[model_name]
         end
+
+        def self.completion_token_limit(model_name)
+          COMPLETION_TOKEN_LIMITS[model_name] || token_limit(model_name)
+        end
+
+        # If :max_tokens is passed in, take the lower of it and the calculated max_tokens
+        def self.validate_max_tokens!(content, model_name, options = {})
+          max_tokens = super(content, model_name, options)
+          [options[:max_tokens], max_tokens].reject(&:nil?).min
+        end
       end
     end
   end

data/lib/langchain/vectorsearch/chroma.rb

@@ -126,7 +126,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
 
     private

data/lib/langchain/vectorsearch/milvus.rb

@@ -151,7 +151,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
   end
 end

data/lib/langchain/vectorsearch/pgvector.rb

@@ -148,7 +148,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
   end
 end

data/lib/langchain/vectorsearch/pinecone.rb

@@ -180,7 +180,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
 
     # Pinecone index

data/lib/langchain/vectorsearch/qdrant.rb

@@ -137,7 +137,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
   end
 end

data/lib/langchain/vectorsearch/weaviate.rb

@@ -6,7 +6,7 @@ module Langchain::Vectorsearch
     # Wrapper around Weaviate
     #
     # Gem requirements:
-    #     gem "weaviate-ruby", "~> 0.8.3"
+    #     gem "weaviate-ruby", "~> 0.8.9"
     #
     # Usage:
     #     weaviate = Langchain::Vectorsearch::Weaviate.new(url:, api_key:, index_name:, llm:)
@@ -137,7 +137,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
 
     private

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.7.2"
+  VERSION = "0.7.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.7.5
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-11-02 00:00:00.000000000 Z
+date: 2023-11-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: baran
@@ -206,6 +206,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.1.0
+- !ruby/object:Gem::Dependency
+  name: aws-sdk-bedrockruntime
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.1'
 - !ruby/object:Gem::Dependency
   name: chroma-db
   requirement: !ruby/object:Gem::Requirement
@@ -567,6 +581,7 @@ files:
 - LICENSE.txt
 - README.md
 - lib/langchain.rb
+- lib/langchain/agent/agents.md
 - lib/langchain/agent/base.rb
 - lib/langchain/agent/react_agent.rb
 - lib/langchain/agent/react_agent/react_agent_prompt.yaml
@@ -591,16 +606,15 @@ files:
 - lib/langchain/dependency_helper.rb
 - lib/langchain/evals/ragas/answer_relevance.rb
 - lib/langchain/evals/ragas/context_relevance.rb
-- lib/langchain/evals/ragas/critique.rb
 - lib/langchain/evals/ragas/faithfulness.rb
 - lib/langchain/evals/ragas/main.rb
 - lib/langchain/evals/ragas/prompts/answer_relevance.yml
 - lib/langchain/evals/ragas/prompts/context_relevance.yml
-- lib/langchain/evals/ragas/prompts/critique.yml
 - lib/langchain/evals/ragas/prompts/faithfulness_statements_extraction.yml
 - lib/langchain/evals/ragas/prompts/faithfulness_statements_verification.yml
 - lib/langchain/llm/ai21.rb
 - lib/langchain/llm/anthropic.rb
+- lib/langchain/llm/aws_bedrock.rb
 - lib/langchain/llm/azure.rb
 - lib/langchain/llm/base.rb
 - lib/langchain/llm/cohere.rb
@@ -613,6 +627,7 @@ files:
 - lib/langchain/llm/replicate.rb
 - lib/langchain/llm/response/ai21_response.rb
 - lib/langchain/llm/response/anthropic_response.rb
+- lib/langchain/llm/response/aws_titan_response.rb
 - lib/langchain/llm/response/base_response.rb
 - lib/langchain/llm/response/cohere_response.rb
 - lib/langchain/llm/response/google_palm_response.rb
@@ -621,7 +636,6 @@ files:
 - lib/langchain/llm/response/openai_response.rb
 - lib/langchain/llm/response/replicate_response.rb
 - lib/langchain/loader.rb
-- lib/langchain/loader_chunkers/html.rb
 - lib/langchain/output_parsers/base.rb
 - lib/langchain/output_parsers/output_fixing_parser.rb
 - lib/langchain/output_parsers/prompts/naive_fix_prompt.yaml