langchainrb 0.7.5 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f4c388275b83a0e4260f4ae9271f4c164a8d34ea5ea9585916d91e7e9c17c980
-  data.tar.gz: 8daa400de3ed80bb3fb9c53cc19ef4d56f137c2aa157bd268dbda488d0fca432
+  metadata.gz: 8ea2adff257b4151b8acf24a02de851df2d99fe8890d6afd06bcdc3a5f53e9e1
+  data.tar.gz: 646a5f9246bffc20654672393f9175c1f0f30533ba1546cef05ce951d449c9ec
 SHA512:
-  metadata.gz: 4bae87c050be6a8fa011c1ae5de4b119abac498669f2e63ca1829e11b7b5ecca7610330be670d24fd6cb98c2e2599c593e9922378985efc586d76c124efb865e
-  data.tar.gz: 2a39b084c6a239aeb0de22bfc87629d2f2909b23eabfcf71a835a1f1624d84afe3ea106afdafb8f1fb301b7934d73abc7253c9b8bd3f6c9b170231ebb5af0936
+  metadata.gz: 3b2aaace63c46b7eec9d8cc04a2cd9cc84c79c90a5a1f1ce1bcb11e4416021f89293d40309ca35b0e4dbb2036a2962bde0faa28ad46d081846dcb00a9a1bf783
+  data.tar.gz: fd5e8e03053ab99a737b3ce17c12ae76da2bc1d0b4bda89eb16e16afe43f260325af78a7c62faf0041c8869cbd94c0a5bbbda920bb7e1d7f175ac35545b53f00

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 ## [Unreleased]
 
+## [0.8.0]
+- [BREAKING] Updated llama_cpp.rb to 0.9.4. The model file format used by the underlying llama.cpp library has changed to GGUF. llama.cpp ships with scripts to convert existing files and GGUF format models can be downloaded from HuggingFace.
+- Introducing Langchain::LLM::GoogleVertexAi LLM provider
+
 ## [0.7.5] - 2023-11-13
 - Fixes
 

data/README.md

@@ -1,3 +1,6 @@
+# Please fill out the [Ruby AI Survey 2023](https://docs.google.com/forms/d/1dH_0js1wpEyh1YqPTOxU3b5fXj76sb5lYp12lVoNNZE/edit).
+Results will be anonymized and shared!
+
 💎🔗 Langchain.rb
 ---
 ⚡ Building LLM-powered applications in Ruby ⚡
@@ -53,23 +56,24 @@ require "langchain"
 Langchain.rb wraps all supported LLMs in a unified interface allowing you to easily swap out and test out different models.
 
 #### Supported LLMs and features:
-| LLM providers                                    | embed()            | complete()         | chat()              | summarize()        | Notes              |
-| --------                                         |:------------------:| :-------:          | :-----------------: | :-------:          | :----------------- |
-| [OpenAI](https://openai.com/)                    | :white_check_mark: | :white_check_mark: | :white_check_mark:  | ❌                 | Including Azure OpenAI |
-| [AI21](https://ai21.com/)                        | ❌                 | :white_check_mark: | ❌                  | :white_check_mark: |                    |
-| [Anthropic](https://milvus.io/)                  | ❌                 | :white_check_mark: | ❌                  | ❌                 |                    |
-| [AWS Bedrock](https://aws.amazon.com/bedrock)    | :white_check_mark: | :white_check_mark: | ❌                  | ❌                 | Provides AWS, Cohere, AI21, Antropic and Stability AI models |
-| [Cohere](https://www.pinecone.io/)               | :white_check_mark: | :white_check_mark: | :white_check_mark:  | :white_check_mark: |                    |
-| [GooglePalm](https://ai.google/discover/palm2/) | :white_check_mark: | :white_check_mark: | :white_check_mark:  | :white_check_mark: |                    |
-| [HuggingFace](https://huggingface.co/)          | :white_check_mark: | ❌                 | ❌                  | ❌                 |                    |
-| [Ollama](https://ollama.ai/)                     | :white_check_mark: | :white_check_mark: | ❌                  | ❌                 |                    |
-| [Replicate](https://replicate.com/)              | :white_check_mark: | :white_check_mark: | :white_check_mark:  | :white_check_mark: |                    |
+| LLM providers                                                                                   | embed()            | complete()         | chat()              | summarize()        | Notes              |
+| --------                                                                                        |:------------------:| :-------:          | :-----------------: | :-------:          | :----------------- |
+| [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 |
+| [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) | ✅                 | ❌                 | ❌                  | ❌                 |                    |
+| [HuggingFace](https://huggingface.co/?utm_source=langchainrb&utm_medium=github)                 | ✅                 | ❌                 | ❌                  | ❌                 |                    |
+| [Ollama](https://ollama.ai/?utm_source=langchainrb&utm_medium=github)                           | ✅                 | ✅                 | ❌                  | ❌                 |                    |
+| [Replicate](https://replicate.com/?utm_source=langchainrb&utm_medium=github)                    | ✅                 | ✅                 | ✅                  | ✅                 |                    |
 
 #### Using standalone LLMs:
 
 #### OpenAI
 
-Add `gem "ruby-openai", "~> 5.2.0"` to your Gemfile.
+Add `gem "ruby-openai", "~> 6.1.0"` to your Gemfile.
 
 ```ruby
 llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
@@ -303,15 +307,16 @@ Langchain.rb provides a convenient unified interface on top of supported vectors
 
 #### Supported vector search databases and features:
 
-| Database                                         | Open-source        | Cloud offering     |
-| --------                                         |:------------------:| :------------:     |
-| [Chroma](https://trychroma.com/)                 | :white_check_mark: | :white_check_mark: |
-| [Hnswlib](https://github.com/nmslib/hnswlib/)    | :white_check_mark: | ❌                 |
-| [Milvus](https://milvus.io/)                     | :white_check_mark: | :white_check_mark: Zilliz Cloud |
-| [Pinecone](https://www.pinecone.io/)             | ❌                 | :white_check_mark: |
-| [Pgvector](https://github.com/pgvector/pgvector) | :white_check_mark: | :white_check_mark: |
-| [Qdrant](https://qdrant.tech/)                   | :white_check_mark: | :white_check_mark: |
-| [Weaviate](https://weaviate.io/)                 | :white_check_mark: | :white_check_mark: |
+| Database                                                                                   | Open-source        | Cloud offering     |
+| --------                                                                                   |:------------------:| :------------:     |
+| [Chroma](https://trychroma.com/?utm_source=langchainrb&utm_medium=github)                  | ✅                 | ✅                 |
+| [Hnswlib](https://github.com/nmslib/hnswlib/?utm_source=langchainrb&utm_medium=github)     | ✅                 | ❌                 |
+| [Milvus](https://milvus.io/?utm_source=langchainrb&utm_medium=github)                      | ✅                 | ✅ Zilliz Cloud    |
+| [Pinecone](https://www.pinecone.io/?utm_source=langchainrb&utm_medium=github)              | ❌                 | ✅                 |
+| [Pgvector](https://github.com/pgvector/pgvector/?utm_source=langchainrb&utm_medium=github) | ✅                 | ✅                 |
+| [Qdrant](https://qdrant.tech/?utm_source=langchainrb&utm_medium=github)                    | ✅                 | ✅                 |
+| [Weaviate](https://weaviate.io/?utm_source=langchainrb&utm_medium=github)                  | ✅                 | ✅                 |
+| [Elasticsearch](https://www.elastic.co/?utm_source=langchainrb&utm_medium=github)          | ✅                 | ✅                 |
 
 ### Using Vector Search Databases 🔍
 
@@ -341,7 +346,8 @@ client = Langchain::Vectorsearch::Hnswlib.new(...)  # `gem "hnswlib", "~> 0.8.1"
 client = Langchain::Vectorsearch::Milvus.new(...)   # `gem "milvus", "~> 0.9.2"`
 client = Langchain::Vectorsearch::Pinecone.new(...) # `gem "pinecone", "~> 0.1.6"`
 client = Langchain::Vectorsearch::Pgvector.new(...) # `gem "pgvector", "~> 0.2"`
-client = Langchain::Vectorsearch::Qdrant.new(...)   # `gem"qdrant-ruby", "~> 0.9.3"`
+client = Langchain::Vectorsearch::Qdrant.new(...)   # `gem "qdrant-ruby", "~> 0.9.3"`
+client = Langchain::Vectorsearch::Elasticsearch.new(...)   # `gem "elasticsearch", "~> 8.2.0"`
 ```
 
 Create the default schema:

data/lib/langchain/llm/azure.rb

@@ -4,7 +4,7 @@ module Langchain::LLM
   # LLM interface for Azure OpenAI Service APIs: https://learn.microsoft.com/en-us/azure/ai-services/openai/
   #
   # Gem requirements:
-  #    gem "ruby-openai", "~> 5.2.0"
+  #    gem "ruby-openai", "~> 6.1.0"
   #
   # Usage:
   #    openai = Langchain::LLM::Azure.new(api_key:, llm_options: {}, embedding_deployment_url: chat_deployment_url:)

data/lib/langchain/llm/google_vertex_ai.rb

@@ -0,0 +1,55 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  #
+  # Wrapper around the Google Vertex AI APIs: https://cloud.google.com/vertex-ai?hl=en
+  #
+  # Gem requirements:
+  #     gem "google-apis-aiplatform_v1", "~> 0.7"
+  #
+  # Usage:
+  #     google_palm = Langchain::LLM::GoogleVertexAi.new(project_id: ENV["GOOGLE_VERTEX_AI_PROJECT_ID"])
+  #
+  class GoogleVertexAi < Base
+    DEFAULTS = {
+      temperature: 0.2,
+      dimension: 768,
+      embeddings_model_name: "textembedding-gecko"
+    }.freeze
+
+    attr_reader :project_id, :client
+
+    def initialize(project_id:, default_options: {})
+      depends_on "google-apis-aiplatform_v1"
+
+      @project_id = project_id
+
+      @client = Google::Apis::AiplatformV1::AiplatformService.new
+
+      # TODO: Adapt for other regions; Pass it in via the constructor
+      @client.root_url = "https://us-central1-aiplatform.googleapis.com/"
+      @client.authorization = Google::Auth.get_application_default
+
+      @defaults = DEFAULTS.merge(default_options)
+    end
+
+    #
+    # Generate an embedding for a given text
+    #
+    # @param text [String] The text to generate an embedding for
+    # @return [Langchain::LLM::GooglePalmResponse] Response object
+    #
+    def embed(text:)
+      content = [{content: text}]
+      request = Google::Apis::AiplatformV1::GoogleCloudAiplatformV1PredictRequest.new(instances: content)
+
+      api_path = "projects/#{@project_id}/locations/us-central1/publishers/google/models/#{@defaults[:embeddings_model_name]}"
+
+      puts("api_path: #{api_path}")
+
+      response = client.predict_project_location_publisher_model(api_path, request)
+
+      Langchain::LLM::GoogleVertexAiResponse.new(response.to_h, model: @defaults[:embeddings_model_name])
+    end
+  end
+end

data/lib/langchain/llm/llama_cpp.rb

@@ -22,7 +22,7 @@ module Langchain::LLM
     # @param n_ctx [Integer] The number of context tokens to use
     # @param n_threads [Integer] The CPU number of threads to use
     # @param seed [Integer] The seed to use
-    def initialize(model_path:, n_gpu_layers: 1, n_ctx: 2048, n_threads: 1, seed: -1)
+    def initialize(model_path:, n_gpu_layers: 1, n_ctx: 2048, n_threads: 1, seed: 0)
       depends_on "llama_cpp"
 
       @model_path = model_path
@@ -33,30 +33,25 @@ module Langchain::LLM
     end
 
     # @param text [String] The text to embed
-    # @param n_threads [Integer] The number of CPU threads to use
     # @return [Array<Float>] The embedding
-    def embed(text:, n_threads: nil)
+    def embed(text:)
       # contexts are kinda stateful when it comes to embeddings, so allocate one each time
       context = embedding_context
 
-      embedding_input = context.tokenize(text: text, add_bos: true)
+      embedding_input = @model.tokenize(text: text, add_bos: true)
       return unless embedding_input.size.positive?
 
-      n_threads ||= self.n_threads
-
-      context.eval(tokens: embedding_input, n_past: 0, n_threads: n_threads)
-      context.embeddings
+      context.eval(tokens: embedding_input, n_past: 0)
+      Langchain::LLM::LlamaCppResponse.new(context, model: context.model.desc)
     end
 
     # @param prompt [String] The prompt to complete
     # @param n_predict [Integer] The number of tokens to predict
-    # @param n_threads [Integer] The number of CPU threads to use
     # @return [String] The completed prompt
-    def complete(prompt:, n_predict: 128, n_threads: nil)
-      n_threads ||= self.n_threads
+    def complete(prompt:, n_predict: 128)
       # contexts do not appear to be stateful when it comes to completion, so re-use the same one
       context = completion_context
-      ::LLaMACpp.generate(context, prompt, n_threads: n_threads, n_predict: n_predict)
+      ::LLaMACpp.generate(context, prompt, n_predict: n_predict)
     end
 
     private
@@ -71,23 +66,30 @@ module Langchain::LLM
 
       context_params.seed = seed
       context_params.n_ctx = n_ctx
-      context_params.n_gpu_layers = n_gpu_layers
+      context_params.n_threads = n_threads
       context_params.embedding = embeddings
 
       context_params
     end
 
+    def build_model_params
+      model_params = ::LLaMACpp::ModelParams.new
+      model_params.n_gpu_layers = n_gpu_layers
+
+      model_params
+    end
+
     def build_model(embeddings: false)
       return @model if defined?(@model)
-      @model = ::LLaMACpp::Model.new(model_path: model_path, params: build_context_params(embeddings: embeddings))
+      @model = ::LLaMACpp::Model.new(model_path: model_path, params: build_model_params)
     end
 
     def build_completion_context
-      ::LLaMACpp::Context.new(model: build_model)
+      ::LLaMACpp::Context.new(model: build_model, params: build_context_params(embeddings: false))
     end
 
     def build_embedding_context
-      ::LLaMACpp::Context.new(model: build_model(embeddings: true))
+      ::LLaMACpp::Context.new(model: build_model, params: build_context_params(embeddings: true))
     end
 
     def completion_context

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", "~> 5.2.0"
+  #    gem "ruby-openai", "~> 6.1.0"
   #
   # Usage:
   #    openai = Langchain::LLM::OpenAI.new(api_key:, llm_options: {})
@@ -29,7 +29,6 @@ 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"
@@ -137,6 +136,7 @@ module Langchain::LLM
 
       response = with_api_error_handling { client.chat(parameters: parameters) }
       response = response_from_chunks if block
+      reset_response_chunks
       Langchain::LLM::OpenAIResponse.new(response)
     end
 
@@ -158,6 +158,12 @@ module Langchain::LLM
 
     private
 
+    attr_reader :response_chunks
+
+    def reset_response_chunks
+      @response_chunks = []
+    end
+
     def is_legacy_model?(model)
       LEGACY_COMPLETION_MODELS.any? { |legacy_model| model.include?(legacy_model) }
     end
@@ -242,18 +248,18 @@ module Langchain::LLM
     end
 
     def response_from_chunks
-      @response_chunks.first&.slice("id", "object", "created", "model")&.merge(
+      grouped_chunks = @response_chunks.group_by { |chunk| chunk.dig("choices", 0, "index") }
+      final_choices = grouped_chunks.map do |index, chunks|
         {
-          "choices" => [
-            {
-              "message" => {
-                "role" => "assistant",
-                "content" => @response_chunks.map { |chunk| chunk.dig("choices", 0, "delta", "content") }.join
-              }
-            }
-          ]
+          "index" => index,
+          "message" => {
+            "role" => "assistant",
+            "content" => chunks.map { |chunk| chunk.dig("choices", 0, "delta", "content") }.join
+          },
+          "finish_reason" => chunks.last.dig("choices", 0, "finish_reason")
         }
-      )
+      end
+      @response_chunks.first&.slice("id", "object", "created", "model")&.merge({"choices" => final_choices})
     end
   end
 end

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

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  class GoogleVertexAiResponse < BaseResponse
+    attr_reader :prompt_tokens
+
+    def initialize(raw_response, model: nil)
+      @prompt_tokens = prompt_tokens
+      super(raw_response, model: model)
+    end
+
+    def embedding
+      embeddings.first
+    end
+
+    def total_tokens
+      raw_response.dig(:predictions, 0, :embeddings, :statistics, :token_count)
+    end
+
+    def embeddings
+      [raw_response.dig(:predictions, 0, :embeddings, :values)]
+    end
+  end
+end

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

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module Langchain::LLM
+  class LlamaCppResponse < BaseResponse
+    def embedding
+      embeddings
+    end
+
+    def embeddings
+      raw_response.embeddings
+    end
+  end
+end

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

@@ -15,7 +15,8 @@ module Langchain
           # Source:
           # https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
           "gpt-4-1106-preview" => 4096,
-          "gpt-4-vision-preview" => 4096
+          "gpt-4-vision-preview" => 4096,
+          "gpt-3.5-turbo-1106" => 4096
         }
 
         TOKEN_LIMITS = {
@@ -26,6 +27,7 @@ module Langchain
           "gpt-3.5-turbo" => 4096,
           "gpt-3.5-turbo-0301" => 4096,
           "gpt-3.5-turbo-0613" => 4096,
+          "gpt-3.5-turbo-1106" => 16385,
           "gpt-3.5-turbo-16k" => 16384,
           "gpt-3.5-turbo-16k-0613" => 16384,
           "text-davinci-003" => 4097,

data/lib/langchain/vectorsearch/elasticsearch.rb

@@ -46,6 +46,9 @@ module Langchain::Vectorsearch
       super(llm: llm)
     end
 
+    # Add a list of texts to the index
+    # @param texts [Array<String>] The list of texts to add
+    # @return [Elasticsearch::Response] from the Elasticsearch server
     def add_texts(texts: [])
       body = texts.map do |text|
         [
@@ -57,6 +60,10 @@ module Langchain::Vectorsearch
       es_client.bulk(body: body)
     end
 
+    # Add a list of texts to the index
+    # @param texts [Array<String>] The list of texts to update
+    # @param texts [Array<Integer>] The list of texts to update
+    # @return [Elasticsearch::Response] from the Elasticsearch server
     def update_texts(texts: [], ids: [])
       body = texts.map.with_index do |text, i|
         [
@@ -68,6 +75,8 @@ module Langchain::Vectorsearch
       es_client.bulk(body: body)
     end
 
+    # Create the index with the default schema
+    # @return [Elasticsearch::Response] Index creation
     def create_default_schema
       es_client.indices.create(
         index: index_name,
@@ -75,6 +84,8 @@ module Langchain::Vectorsearch
       )
     end
 
+    # Deletes the default schema
+    # @return [Elasticsearch::Response] Index deletion
     def delete_default_schema
       es_client.indices.delete(
         index: index_name
@@ -116,10 +127,30 @@ module Langchain::Vectorsearch
       }
     end
 
-    # TODO: Implement this
-    # def ask()
-    # end
+    # Ask a question and return the answer
+    # @param question [String] The question to ask
+    # @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, &block)
+      search_results = similarity_search(query: question, k: k)
 
+      context = search_results.map do |result|
+        result[:input]
+      end.join("\n---\n")
+
+      prompt = generate_rag_prompt(question: question, context: context)
+
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
+    end
+
+    # Search for similar texts
+    # @param text [String] The text to search for
+    # @param k [Integer] The number of results to return
+    # @param query [Hash] Elasticsearch query that needs to be used while searching (Optional)
+    # @return [Elasticsearch::Response] The response from the server
     def similarity_search(text: "", k: 10, query: {})
       if text.empty? && query.empty?
         raise "Either text or query should pass as an argument"
@@ -134,6 +165,11 @@ module Langchain::Vectorsearch
       es_client.search(body: {query: query, size: k}).body
     end
 
+    # Search for similar texts by embedding
+    # @param embedding [Array<Float>] The embedding to search for
+    # @param k [Integer] The number of results to return
+    # @param query [Hash] Elasticsearch query that needs to be used while searching (Optional)
+    # @return [Elasticsearch::Response] The response from the server
     def similarity_search_by_vector(embedding: [], k: 10, query: {})
       if embedding.empty? && query.empty?
         raise "Either embedding or query should pass as an argument"

data/lib/langchain/vectorsearch/qdrant.rb

@@ -44,14 +44,14 @@ module Langchain::Vectorsearch
     # Add a list of texts to the index
     # @param texts [Array<String>] The list of texts to add
     # @return [Hash] The response from the server
-    def add_texts(texts:, ids: [])
+    def add_texts(texts:, ids: [], payload: {})
       batch = {ids: [], vectors: [], payloads: []}
 
       Array(texts).each_with_index do |text, i|
         id = ids[i] || SecureRandom.uuid
         batch[:ids].push(id)
         batch[:vectors].push(llm.embed(text: text).embedding)
-        batch[:payloads].push({content: text})
+        batch[:payloads].push({content: text}.merge(payload))
       end
 
       client.points.upsert(

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.7.5"
+  VERSION = "0.8.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.7.5
+  version: 0.8.0
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-11-13 00:00:00.000000000 Z
+date: 2023-11-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: baran
@@ -290,6 +290,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.6.5
+- !ruby/object:Gem::Dependency
+  name: google-apis-aiplatform_v1
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.7'
 - !ruby/object:Gem::Dependency
   name: google_palm_api
   requirement: !ruby/object:Gem::Requirement
@@ -366,14 +380,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.3.7
+        version: 0.9.4
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.3.7
+        version: 0.9.4
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -506,14 +520,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.2.0
+        version: 6.1.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.2.0
+        version: 6.1.0
 - !ruby/object:Gem::Dependency
   name: safe_ruby
   requirement: !ruby/object:Gem::Requirement
@@ -619,6 +633,7 @@ files:
 - lib/langchain/llm/base.rb
 - lib/langchain/llm/cohere.rb
 - lib/langchain/llm/google_palm.rb
+- lib/langchain/llm/google_vertex_ai.rb
 - lib/langchain/llm/hugging_face.rb
 - lib/langchain/llm/llama_cpp.rb
 - lib/langchain/llm/ollama.rb
@@ -631,7 +646,9 @@ files:
 - lib/langchain/llm/response/base_response.rb
 - lib/langchain/llm/response/cohere_response.rb
 - lib/langchain/llm/response/google_palm_response.rb
+- lib/langchain/llm/response/google_vertex_ai_response.rb
 - lib/langchain/llm/response/hugging_face_response.rb
+- lib/langchain/llm/response/llama_cpp_response.rb
 - lib/langchain/llm/response/ollama_response.rb
 - lib/langchain/llm/response/openai_response.rb
 - lib/langchain/llm/response/replicate_response.rb