langchainrb 0.11.3 → 0.11.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c678ae75bc25b0501223f5b6ffd396a9159af4d0ddd87ddb1657429ed2ba24ce
-  data.tar.gz: df50ef0a6d9c1a3100153a06084556cac983069d1a38739bd6606f39f63bd332
+  metadata.gz: 22781a12fbb032cfd70fe45c9a0b96621b2d47f4d6ef912547b327790d6dfcaa
+  data.tar.gz: c8ab04c3bf520e7af0d298f4cd15e9c9df149fd7618d8998c53ec8b684ddddea
 SHA512:
-  metadata.gz: 3ec9f92f4c6221184b7a0a2c118caa6a56e7bc8505a83d5b5acb4daeb769ff90d8822b43c28f57adc06435dd2df5577268721345c4061d3dad6ecb919be18efc
-  data.tar.gz: 53d54b0c6a82082438f2e2f1ca70d097a9b916bc283b72e52ce466b6f012c9624cf094586b17e93eaa49a796bf9911051d3f4b494b9ecc93c3ac6ee6cdc7e8fe
+  metadata.gz: 65c2068d4e0289b4aa081ab659b4470a312c387a138b4a367cf5717a9d232b39ab44f7dcbfddcb382e0f8ea1b735553c630e5106d49884e6d91c6cee667fcd1d
+  data.tar.gz: a2a15c08e593903e6fdf67cc2ee1e3a5188c9d2aaae6a2c3dad991dbdb1b13c75cd76f5a557bbbc2581b30f87860d5719b75bb65ecb4c1c83e05b8e7aedc5714

data/CHANGELOG.md

@@ -1,9 +1,10 @@
 ## [Unreleased]
-- New `Langchain::Processors::Pptx` to parse .pptx files
-- New `Langchain::LLM::Anthropic#chat()` support
-- Misc fixes
 
-## [0.11.3]
+## [0.11.4] - 2024-04-19
+- New `Langchain::LLM::AWSBedrock#chat()` to wrap Bedrock Claude requests
+- New `Langchain::LLM::OllamaResponse#total_tokens()` method
+
+## [0.11.3] - 2024-04-16
 - New `Langchain::Processors::Pptx` to parse .pptx files
 - New `Langchain::LLM::Anthropic#chat()` support
 - Misc fixes

data/README.md

@@ -60,7 +60,7 @@ Langchain.rb wraps supported LLMs in a unified interface allowing you to easily
 | [OpenAI](https://openai.com/?utm_source=langchainrb&utm_medium=github)                          | ✅                 | ✅                 | ✅                  | ❌                 | Including Azure OpenAI |
 | [AI21](https://ai21.com/?utm_source=langchainrb&utm_medium=github)                              | ❌                 | ✅                 | ❌                  | ✅                 |                    |
 | [Anthropic](https://anthropic.com/?utm_source=langchainrb&utm_medium=github)                    | ❌                 | ✅                 | ✅                  | ❌                 |                    |
-| [AWS Bedrock](https://aws.amazon.com/bedrock?utm_source=langchainrb&utm_medium=github)          | ✅                 | ✅                 | ❌                  | ❌                 | Provides AWS, Cohere, AI21, Antropic and Stability AI models |
+| [AWS Bedrock](https://aws.amazon.com/bedrock?utm_source=langchainrb&utm_medium=github)          | ✅                 | ✅                 | ✅                  | ❌                 | Provides AWS, Cohere, AI21, Antropic and Stability AI models |
 | [Cohere](https://cohere.com/?utm_source=langchainrb&utm_medium=github)                          | ✅                 | ✅                 | ✅                  | ✅                 |                    |
 | [GooglePalm](https://ai.google/discover/palm2?utm_source=langchainrb&utm_medium=github)         | ✅                 | ✅                 | ✅                  | ✅                 |                    |
 | [Google Vertex AI](https://cloud.google.com/vertex-ai?utm_source=langchainrb&utm_medium=github) | ✅                 | ✅                 | ❌                  | ✅                 |                    |

data/lib/langchain/llm/aws_bedrock.rb

@@ -46,7 +46,10 @@ module Langchain::LLM
       }
     }.freeze
 
+    attr_reader :client, :defaults
+
     SUPPORTED_COMPLETION_PROVIDERS = %i[anthropic cohere ai21].freeze
+    SUPPORTED_CHAT_COMPLETION_PROVIDERS = %i[anthropic].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: {})
@@ -91,6 +94,8 @@ module Langchain::LLM
     def complete(prompt:, **params)
       raise "Completion provider #{completion_provider} is not supported." unless SUPPORTED_COMPLETION_PROVIDERS.include?(completion_provider)
 
+      raise "Model #{@defaults[:completion_model_name]} only supports #chat." if @defaults[:completion_model_name].include?("claude-3")
+
       parameters = compose_parameters params
 
       parameters[:prompt] = wrap_prompt prompt
@@ -105,6 +110,53 @@ module Langchain::LLM
       parse_response response
     end
 
+    # Generate a chat completion for a given prompt
+    # Currently only configured to work with the Anthropic provider and
+    # the claude-3 model family
+    # @param messages [Array] The messages to generate a completion for
+    # @param system [String] The system prompt to provide instructions
+    # @param model [String] The model to use for completion defaults to @defaults[:chat_completion_model_name]
+    # @param max_tokens [Integer] The maximum number of tokens to generate
+    # @param stop_sequences [Array] The stop sequences to use for completion
+    # @param temperature [Float] The temperature to use for completion
+    # @param top_p [Float] The top p to use for completion
+    # @param top_k [Integer] The top k to use for completion
+    # @return [Langchain::LLM::AnthropicMessagesResponse] Response object
+    def chat(
+      messages: [],
+      system: nil,
+      model: defaults[:completion_model_name],
+      max_tokens: defaults[:max_tokens_to_sample],
+      stop_sequences: nil,
+      temperature: nil,
+      top_p: nil,
+      top_k: nil
+    )
+      raise ArgumentError.new("messages argument is required") if messages.empty?
+
+      raise "Model #{model} does not support chat completions." unless Langchain::LLM::AwsBedrock::SUPPORTED_CHAT_COMPLETION_PROVIDERS.include?(completion_provider)
+
+      inference_parameters = {
+        messages: messages,
+        max_tokens: max_tokens,
+        anthropic_version: @defaults[:anthropic_version]
+      }
+      inference_parameters[:system] = system if system
+      inference_parameters[:stop_sequences] = stop_sequences if stop_sequences
+      inference_parameters[:temperature] = temperature if temperature
+      inference_parameters[:top_p] = top_p if top_p
+      inference_parameters[:top_k] = top_k if top_k
+
+      response = client.invoke_model({
+        model_id: model,
+        body: inference_parameters.to_json,
+        content_type: "application/json",
+        accept: "application/json"
+      })
+
+      parse_response response
+    end
+
     private
 
     def completion_provider

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

@@ -44,5 +44,9 @@ module Langchain::LLM
     def completion_tokens
       raw_response.dig("eval_count")
     end
+
+    def total_tokens
+      prompt_tokens + completion_tokens
+    end
   end
 end

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.11.3"
+  VERSION = "0.11.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.11.3
+  version: 0.11.4
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-04-17 00:00:00.000000000 Z
+date: 2024-04-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport