langchainrb_rails 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b792e1a7888a17c54fad522042ee7f6935df92e684119d4177f9627abb999dfd
-  data.tar.gz: 77444b9ed6d52443c890f045c121ba1a58f78b4d532954fc858e8c01999c90a7
+  metadata.gz: 37760a671cfe732f12ddb79769997ae325240b5c1b0bb96ee3e13786d605cc6a
+  data.tar.gz: 89b9aa5c04ffb28823836cfef7428990e27e1d38dc231240fb4e7004ab3db614
 SHA512:
-  metadata.gz: 5d26a5c5d4a10e6ea4794d809ceb15feb6262deb4754bfc12362e1e0e536b8643f46a9f98d464ae7372d6ef1b3d45ed34cf0d5e4c88977b135b4be1d982d5c85
-  data.tar.gz: '084a74842710d2b24db00e01344cbde645249671f4f975a9cc8f37763af53597e4cd3d2b5cd0f036320e181cbc20f8be8dca525279550529f9d58d8234fd601b'
+  metadata.gz: 78c3d36d67ace05932ef36bc9e9136837bb350e5698aad55836f3d6dea0602228f461f2ae1aafc10ec050151d7f6b71e5a7cca21357b1a5f6bf2410f38596a69
+  data.tar.gz: fa5a1bdd97e82d71f9b4b35d0c1f15245c87966cdef60117364174f8306a7df72848dda3b52e2635844a5ae05d25a9e1c6166bf7a25b9ccd52565ae787c8fc86

data/.rubocop.yml

@@ -0,0 +1,28 @@
+AllCops:
+  TargetRubyVersion: 2.7
+  NewCops: enable
+  Exclude:
+    - 'bin/**/*'
+    - 'db/schema.rb'
+    - 'vendor/**/*'
+    - 'spec/fixtures/**/*'
+
+Metrics/LineLength:
+  Max: 140
+
+Metrics/BlockLength:
+  Exclude:
+    - 'spec/**/*.rb'
+
+Style/Documentation:
+  Enabled: false
+
+Style/FrozenStringLiteralComment:
+  Enabled: true
+
+Style/StringLiterals:
+  Enabled: false
+
+Lint/SuppressedException:
+  Exclude:
+    - 'spec/**/*.rb'

data/.tool-versions

@@ -0,0 +1 @@
+ruby 3.1.2

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 ## [Unreleased]
 
-## [0.1.0] - 2023-10-22
+## [0.1.3] - 2023-11-01
+- Pgvector vectorsearch generator
+
+## [0.1.2] - 2023-10-27
+- Pinecone vectorsearch generator
 
+## [0.1.1] - 2023-10-23
+
+## [0.1.0] - 2023-10-22
 - Initial release

data/Gemfile

@@ -9,6 +9,10 @@ gem "rake", "~> 13.0"
 
 gem "rspec", "~> 3.0"
 
+gem "bundler-audit", require: false
+gem "brakeman", require: false
+gem "rubocop", require: false
+
 gem "standardrb"
 
 gem "langchainrb"

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    langchainrb_rails (0.1.2)
+    langchainrb_rails (0.1.3)
       langchainrb (~> 0.7.0)
 
 GEM
@@ -86,7 +86,11 @@ GEM
     baran (0.1.9)
     base64 (0.1.1)
     bigdecimal (3.1.4)
+    brakeman (6.0.1)
     builder (3.2.4)
+    bundler-audit (0.9.1)
+      bundler (>= 1.2.0, < 3)
+      thor (~> 1.0)
     byebug (11.1.3)
     coderay (1.1.3)
     colorize (0.8.1)
@@ -109,12 +113,14 @@ GEM
     json (2.6.3)
     json-schema (4.0.0)
       addressable (>= 2.8)
-    langchainrb (0.7.0)
+    langchainrb (0.7.1)
       baran (~> 0.1.9)
       colorize (~> 0.8.1)
       json-schema (~> 4.0.0)
+      matrix
       pragmatic_segmenter (~> 0.3.0)
       tiktoken_ruby (~> 0.0.5)
+      to_bool (~> 2.0.0)
       zeitwerk (~> 2.5)
     language_server-protocol (3.17.0.3)
     lint_roller (1.1.0)
@@ -127,8 +133,10 @@ GEM
       net-pop
       net-smtp
     marcel (1.0.2)
+    matrix (0.4.2)
     method_source (1.0.0)
     mini_mime (1.1.5)
+    mini_portile2 (2.8.5)
     minitest (5.20.0)
     mutex_m (0.1.2)
     net-imap (0.4.2)
@@ -141,8 +149,13 @@ GEM
     net-smtp (0.4.0)
       net-protocol
     nio4r (2.5.9)
+    nokogiri (1.15.4)
+      mini_portile2 (~> 2.8.2)
+      racc (~> 1.4)
     nokogiri (1.15.4-x86_64-darwin)
       racc (~> 1.4)
+    nokogiri (1.15.4-x86_64-linux)
+      racc (~> 1.4)
     parallel (1.23.0)
     parser (3.2.2.4)
       ast (~> 2.4.1)
@@ -198,6 +211,7 @@ GEM
       zeitwerk (~> 2.6)
     rainbow (3.1.1)
     rake (13.0.6)
+    rb_sys (0.9.82)
     rdoc (6.5.0)
       psych (>= 4.0.0)
     regexp_parser (2.8.2)
@@ -252,8 +266,12 @@ GEM
       standard
     stringio (3.0.8)
     thor (1.3.0)
+    tiktoken_ruby (0.0.6)
+      rb_sys (~> 0.9.68)
     tiktoken_ruby (0.0.6-x86_64-darwin)
+    tiktoken_ruby (0.0.6-x86_64-linux)
     timeout (0.4.0)
+    to_bool (2.0.0)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
     unicode (0.4.4.4)
@@ -263,18 +281,24 @@ GEM
       websocket-extensions (>= 0.1.0)
     websocket-extensions (0.1.5)
     yard (0.9.34)
-    zeitwerk (2.6.11)
+    zeitwerk (2.6.12)
 
 PLATFORMS
+  ruby
   x86_64-darwin-19
+  x86_64-darwin-22
+  x86_64-linux
 
 DEPENDENCIES
+  brakeman
+  bundler-audit
   langchainrb
   langchainrb_rails!
   pry-byebug (~> 3.10.0)
   rails (> 6.0.0)
   rake (~> 13.0)
   rspec (~> 3.0)
+  rubocop
   standardrb
   yard (~> 0.9.34)
 

data/README.md

@@ -1,8 +1,6 @@
 💎🔗 Langchain.rb for Rails
 ---
-⚡ Building applications with LLMs through composability ⚡
-
-👨‍💻👩‍💻 CURRENTLY SEEKING PEOPLE TO FORM THE CORE GROUP OF MAINTAINERS WITH
+The fastest way to sprinkle AI ✨ on top of your Rails app. Add OpenAI-powered question-and-answering in minutes.
 
 ![Tests status](https://github.com/andreibondarev/langchainrb_rails/actions/workflows/ci.yml/badge.svg?branch=main)
 [![Gem Version](https://badge.fury.io/rb/langchainrb_rails.svg)](https://badge.fury.io/rb/langchainrb_rails)
@@ -10,24 +8,107 @@
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](https://github.com/andreibondarev/langchainrb_rails/blob/main/LICENSE.txt)
 [![](https://dcbadge.vercel.app/api/server/WDARp7J2n8?compact=true&style=flat)](https://discord.gg/WDARp7J2n8)
 
+## Dependencies
+
+* Ruby 3.0+
+* Postgres 11+
+
+## Table of Contents
 
-Langchain.rb is a library that's an abstraction layer on top many emergent AI, ML and other DS tools. The goal is to abstract complexity and difficult concepts to make building AI/ML-supercharged applications approachable for traditional software engineers.
+- [Installation](#installation)
+- [Generators](#rails-generators)
 
 ## Installation
 
 Install the gem and add to the application's Gemfile by executing:
-
-    bundle add langchainrb_rails
+```bash
+bundle add langchainrb_rails
+```
 
 If bundler is not being used to manage dependencies, install the gem by executing:
+```bash
+gem install langchainrb_rails
+```
+
+## Configuration w/ [Pgvector](https://github.com/pgvector/pgvector) (requires Postgres 11+)
+
+1. Run the Rails generator to add vectorsearch to your ActiveRecord model
+```bash
+rails generate langchainrb_rails:pgvector --model=Product --llm=openai
+```
+
+This adds required dependencies to your Gemfile, creates the `config/initializers/langchainrb_rails.rb` initializer file, database migrations, and adds the necessary code to the ActiveRecord model to enable vectorsearch.
 
-    gem install langchainrb_rails
+2. Bundle and migrate
+```bash
+bundle install && rails db:migrate
+```
+
+3. Set the env var `OPENAI_API_KEY` to your OpenAI API key: https://platform.openai.com/account/api-keys
+```ruby
+ENV["OPENAI_API_KEY"]= 
+```
+
+5. Generate embeddings for your model
+```ruby
+Product.embed!
+```
+
+This can take a while depending on the number of database records.
+
+## Usage
+
+### Question and Answering
+```ruby
+Product.ask("list the brands of shoes that are in stock")
+```
+
+Returns a `String` with a natural language answer. The answer is assembled using the following steps:
+
+1. An embedding is generated for the passed in `question` using the selected LLM.
+2. We calculate a [cosine similarity](https://en.wikipedia.org/wiki/Cosine_similarity) to find records that most closely match your question's embedding.
+3. A prompt is created using the question and the above records (their `#as_vector` representation )are added as context.
+4. This prompt is passed to the LLM to generate an answer
+
+### Similarity Search
+```ruby
+Product.similarity_search("t-shirt")
+```
+
+Returns ActiveRecord relation that most closely matches the `query` using vector search.
+
+## Customization
+
+### Changing the vector representation of a record
+
+By default, embeddings are generated by calling the following method on your model instance:
+```ruby
+to_json(except: :embedding)
+```
+
+You can override this by defining an `#as_vector` method in your model:
+```ruby
+def as_vector
+  { name: name, description: description, category: category.name, ... }.to_json
+end
+```
+
+Re-generate embeddings after modifying this method:
+
+```ruby
+product.embed!
+```
 
 ## Rails Generators
 
-### Pinecone Generator - adds vectorsearch to your ActiveRecord model
+### Pgvector Generator
 
+```bash
+rails generate langchainrb_rails:pgvector --model=Product --llm=openai
 ```
+
+### Pinecone Generator - adds vectorsearch to your ActiveRecord model
+```bash
 rails generate langchainrb_rails:pinecone --model=Product --llm=openai
 ```
 
@@ -39,3 +120,4 @@ Pinecone Generator does the following:
 1. Creates the `config/initializers/langchainrb_rails.rb` initializer file
 2. Adds necessary code to the ActiveRecord model to enable vectorsearch
 3. Adds `pinecone` gem to the Gemfile
+

data/lib/langchainrb_overrides/vectorsearch/pgvector.rb

@@ -0,0 +1,124 @@
+# frozen_string_literal: true
+
+# Overriding Langchain.rb's Pgvector implementation to use ActiveRecord.
+# Original implementation: https://github.com/andreibondarev/langchainrb/blob/main/lib/langchain/vectorsearch/pgvector.rb
+
+module Langchain::Vectorsearch
+  class Pgvector < Base
+    #
+    # The PostgreSQL vector search adapter
+    #
+    # Gem requirements:
+    #     gem "pgvector", "~> 0.2"
+    #
+    # Usage:
+    #     pgvector = Langchain::Vectorsearch::Pgvector.new(llm:)
+    #
+
+    # The operators supported by the PostgreSQL vector search adapter
+    OPERATORS = [
+      "cosine",
+      "euclidean",
+      "inner_product"
+    ]
+    DEFAULT_OPERATOR = "cosine"
+
+    attr_reader :operator, :llm
+    attr_accessor :model
+
+    # @param url [String] The URL of the PostgreSQL database
+    # @param index_name [String] The name of the table to use for the index
+    # @param llm [Object] The LLM client to use
+    # @param namespace [String] The namespace to use for the index when inserting/querying
+    def initialize(llm:)
+      # If the line below is called, the generator fails as calls to
+      # LangchainrbRails.config.vectorsearch will generate an exception.
+      # These happen in the template files.
+      # depends_on "neighbor"
+
+      @operator = DEFAULT_OPERATOR
+
+      super(llm: llm)
+    end
+
+    # Add a list of texts to the index
+    # @param texts [Array<String>] The texts to add to the index
+    # @param ids [Array<String>] The ids to add to the index, in the same order as the texts
+    # @return [Array<Integer>] The the ids of the added texts.
+    def add_texts(texts:, ids:)
+      embeddings = texts.map do |text|
+        llm.embed(text: text).embedding
+      end
+
+      # I believe the records returned by #find must be in the
+      # same order as the embeddings. I _think_ this works for uuid ids but didn't test
+      # deeply.
+      # TODO - implement find_each so we don't load all records into memory
+      model.find(ids).each.with_index do |record, i|
+        record.update_column(:embedding, embeddings[i])
+      end
+    end
+
+    def update_texts(texts:, ids:)
+      add_texts(texts: texts, ids: ids)
+    end
+
+    # Invoke a rake task that will create an initializer (`config/initializers/langchain.rb`) file
+    # and db/migrations/* files
+    def create_default_schema
+      Rake::Task["pgvector"].invoke
+    end
+
+    # Destroy default schema
+    def destroy_default_schema
+      # Tell the user to rollback the migration
+    end
+
+    # Search for similar texts in the index
+    # @param query [String] The text to search for
+    # @param k [Integer] The number of top results to return
+    # @return [Array<Hash>] The results of the search
+    # TODO - drop the named "query:" param so it is the same interface as #ask?
+    def similarity_search(query:, k: 4)
+      embedding = llm.embed(text: query).embedding
+
+      similarity_search_by_vector(
+        embedding: embedding,
+        k: k
+      )
+    end
+
+    # Search for similar texts in the index by the passed in vector.
+    # You must generate your own vector using the same LLM that generated the embeddings stored in the Vectorsearch DB.
+    # @param embedding [Array<Float>] The vector to search for
+    # @param k [Integer] The number of top results to return
+    # @return [Array<Hash>] The results of the search
+    # TODO - drop the named "embedding:" param so it is the same interface as #ask?
+    def similarity_search_by_vector(embedding:, k: 4)
+      model
+        .nearest_neighbors(:embedding, embedding, distance: operator)
+        .limit(k)
+    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)
+      # Noisy as the embedding column has a lot of data
+      ActiveRecord::Base.logger.silence do
+        search_results = similarity_search(query: question, k: k)
+
+        context = search_results.map do |result|
+          result.as_vector
+        end
+        context = context.join("\n---\n")
+
+        prompt = generate_rag_prompt(question: question, context: context)
+
+        llm.chat(prompt: prompt, &block)
+      end
+    end
+  end
+end

data/lib/langchainrb_rails/active_record/hooks.rb

@@ -61,7 +61,9 @@ module LangchainrbRails
       #
       # @return [String] the text representation of the model
       def as_vector
-        to_json
+        # Don't vectorize the embedding ... this would happen if it already exists
+        # for a record and we update.
+        to_json(except: :embedding)
       end
 
       module ClassMethods
@@ -70,6 +72,21 @@ module LangchainrbRails
         # @param provider [Object] The `Langchain::Vectorsearch::*` instance
         def vectorsearch
           class_variable_set(:@@provider, LangchainrbRails.config.vectorsearch)
+
+          # Pgvector-specific configuration
+          if LangchainrbRails.config.vectorsearch.is_a?(Langchain::Vectorsearch::Pgvector)
+            has_neighbors(:embedding)
+          end
+
+          LangchainrbRails.config.vectorsearch.model = self
+        end
+
+        # Iterates over records and generate embeddings.
+        # Will re-generate for ALL records (not just records with embeddings).
+        def embed!
+          find_each do |record|
+            record.upsert_to_vectorsearch
+          end
         end
 
         # Search for similar texts
@@ -84,7 +101,7 @@ module LangchainrbRails
           )
 
           # We use "__id" when Weaviate is the provider
-          ids = records.map { |record| record.dig("id") || record.dig("__id") }
+          ids = records.map { |record| record.try("id") || record.dig("__id") }
           where(id: ids)
         end
 
@@ -94,12 +111,12 @@ module LangchainrbRails
         # @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)
+        def ask(question, k: 4, &block)
           class_variable_get(:@@provider).ask(
-            question: question,
+            question,
             k: k,
             &block
-          )
+          ).completion
         end
       end
     end

data/lib/langchainrb_rails/generators/langchainrb_rails/base_generator.rb

@@ -0,0 +1,24 @@
+require "rails/generators"
+require "rails/generators/active_record"
+
+module LangchainrbRails
+  module Generators
+    class BaseGenerator < Rails::Generators::Base
+      include ::ActiveRecord::Generators::Migration
+
+      class_option :model, type: :string, required: true, desc: "ActiveRecord Model to add vectorsearch to", aliases: "-m"
+      class_option :llm, type: :string, required: true, desc: "LLM provider that will be used to generate embeddings and completions"
+
+      # Available LLM providers to be passed in as --llm option
+      LLMS = {
+        "cohere" => "Langchain::LLM::Cohere",
+        "google_palm" => "Langchain::LLM::GooglePalm",
+        "hugging_face" => "Langchain::LLM::HuggingFace",
+        "llama_cpp" => "Langchain::LLM::LlamaCpp",
+        "ollama" => "Langchain::LLM::Ollama",
+        "openai" => "Langchain::LLM::OpenAI",
+        "replicate" => "Langchain::LLM::Replicate"
+      }
+    end
+  end
+end

data/lib/langchainrb_rails/generators/langchainrb_rails/chroma_generator.rb

@@ -0,0 +1,54 @@
+# frozen_string_literal: true
+
+module LangchainrbRails
+  module Generators
+    #
+    # ChromaGenerator does the following:
+    # 1. Creates the `langchainrb_rails.rb` initializer file
+    # 2. Adds necessary code to the ActiveRecord model to enable vectorsearch
+    # 3. Adds `chroma-db` gem to the Gemfile
+    #
+    # Usage:
+    #     rails generate langchainrb_rails:chrome --model=Product --llm=openai
+    #
+    class ChromaGenerator < LangchainrbRails::Generators::BaseGenerator
+      desc "This generator adds Chroma vectorsearch integration to your ActiveRecord model"
+      source_root File.join(__dir__, "templates")
+
+      # Creates the `langchainrb_rails.rb` initializer file
+      def create_initializer_file
+        template "chroma_initializer.rb", "config/initializers/langchainrb_rails.rb"
+      end
+
+      # Adds `vectorsearch` class method to the model and `after_save` callback that calls `upsert_to_vectorsearch()`
+      def add_to_model
+        inject_into_class "app/models/#{model_name.downcase}.rb", model_name do
+          "  vectorsearch\n\n  after_save :upsert_to_vectorsearch\n\n"
+        end
+      end
+
+      # Adds `chroma-db` gem to the Gemfile
+      # TODO: Can we automatically run `bundle install`?
+      def add_to_gemfile
+        gem "chroma-db", version: "~> 0.6.0"
+      end
+
+      private
+
+      # @return [String] Name of the model
+      def model_name
+        options["model"]
+      end
+
+      # @return [String] LLM provider to use
+      def llm
+        options["llm"]
+      end
+
+      # @return [Langchain::LLM::*] LLM class
+      def llm_class
+        Langchain::LLM.const_get(LLMS[llm])
+      end
+    end
+  end
+end

data/lib/langchainrb_rails/generators/langchainrb_rails/pgvector_generator.rb

@@ -0,0 +1,75 @@
+# frozen_string_literal: true
+
+module LangchainrbRails
+  module Generators
+    #
+    # Usage:
+    #     rails g langchain:pgvector -model=Product -llm=openai
+    #
+    class PgvectorGenerator < LangchainrbRails::Generators::BaseGenerator
+      desc "This generator adds Pgvector vectorsearch integration to your ActiveRecord model"
+      source_root File.join(__dir__, "templates")
+
+      def copy_migration
+        migration_template "enable_vector_extension_template.rb", "db/migrate/enable_vector_extension.rb", migration_version: migration_version
+        migration_template "add_vector_column_template.rb", "db/migrate/add_vector_column_to_#{table_name}.rb", migration_version: migration_version
+      end
+
+      def create_initializer_file
+        template "pgvector_initializer.rb", "config/initializers/langchainrb_rails.rb"
+      end
+
+      def migration_version
+        "[#{::ActiveRecord::VERSION::MAJOR}.#{::ActiveRecord::VERSION::MINOR}]"
+      end
+
+      def add_to_model
+        inject_into_class "app/models/#{model_name.downcase}.rb", model_name do
+          "  vectorsearch\n\n  after_save :upsert_to_vectorsearch\n\n"
+        end
+      end
+
+      def add_to_gemfile
+        # Dependency for Langchain PgVector
+        gem "neighbor"
+        gem "ruby-openai"
+      end
+
+      def post_install_message
+        say "Please do the following to start Q&A with your #{model_name} records:", :green
+        say "1. Run `bundle install` to install the new gems."
+        say "2. Set `OPENAI_API_KEY` environment variable to your OpenAI API key."
+        say "3. Run `rails db:migrate` to apply the database migrations to enable pgvector and add the embedding column."
+        say "4. In Rails console, run `#{model_name}.embed!` to set the embeddings for all records."
+        say "5. Ask a question in the Rails console, ie: `#{model_name}.ask('[YOUR QUESTION]')`"
+      end
+
+      private
+
+      # @return [String] Name of the model
+      def model_name
+        options["model"]
+      end
+
+      # @return [String] Table name of the model
+      def table_name
+        model_name.downcase.pluralize
+      end
+
+      # @return [String] LLM provider to use
+      def llm
+        options["llm"]
+      end
+
+      # @return [Langchain::LLM::*] LLM class
+      def llm_class
+        Langchain::LLM.const_get(LLMS[llm])
+      end
+
+      # @return [Integer] Dimension of the vector to be used
+      def vector_dimension
+        llm_class.default_dimension
+      end
+    end
+  end
+end

data/lib/langchainrb_rails/generators/langchainrb_rails/pinecone_generator.rb

@@ -1,4 +1,4 @@
-require "rails/generators/active_record"
+# frozen_string_literal: true
 
 module LangchainrbRails
   module Generators
@@ -11,26 +11,10 @@ module LangchainrbRails
     # Usage:
     #     rails generate langchainrb_rails:pinecone --model=Product --llm=openai
     #
-    class PineconeGenerator < Rails::Generators::Base
+    class PineconeGenerator < LangchainrbRails::Generators::BaseGenerator
       desc "This generator adds Pinecone vectorsearch integration to your ActiveRecord model"
-
-      include ::ActiveRecord::Generators::Migration
       source_root File.join(__dir__, "templates")
 
-      class_option :model, type: :string, required: true, desc: "ActiveRecord Model to add vectorsearch to", aliases: "-m"
-      class_option :llm, type: :string, required: true, desc: "LLM provider that will be used to generate embeddings and completions"
-
-      # Available LLM providers to be passed in as --llm option
-      LLMS = {
-        "cohere" => "Langchain::LLM::Cohere",
-        "google_palm" => "Langchain::LLM::GooglePalm",
-        "hugging_face" => "Langchain::LLM::HuggingFace",
-        "llama_cpp" => "Langchain::LLM::LlamaCpp",
-        "ollama" => "Langchain::LLM::Ollama",
-        "openai" => "Langchain::LLM::OpenAI",
-        "replicate" => "Langchain::LLM::Replicate"
-      }
-
       # Creates the `langchainrb_rails.rb` initializer file
       def create_initializer_file
         template "pinecone_initializer.rb", "config/initializers/langchainrb_rails.rb"
@@ -46,7 +30,7 @@ module LangchainrbRails
       # Adds `pinecone` gem to the Gemfile
       # TODO: Can we automatically run `bundle install`?
       def add_to_gemfile
-        gem "pinecone"
+        gem "pinecone", version: "~> 0.1.6"
       end
 
       private

data/lib/langchainrb_rails/generators/langchainrb_rails/templates/add_vector_column_template.rb.tt

@@ -0,0 +1,10 @@
+class <%= migration_class_name %> < ActiveRecord::Migration<%= migration_version %>
+  def change
+    add_column :<%= table_name %>, :embedding, :vector,
+      limit: LangchainrbRails
+        .config
+        .vectorsearch
+        .llm
+        .default_dimension
+  end
+end

data/lib/langchainrb_rails/generators/langchainrb_rails/templates/chroma_initializer.rb.tt

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+LangchainrbRails.configure do |config|
+  config.vectorsearch = Langchain::Vectorsearch::Chroma.new(
+    llm: <%= llm_class %>.new(api_key: ENV["<%= llm.upcase %>_API_KEY"]),
+    url: ENV["CHROMA_URL"],
+    index_name: ""
+  )
+end

data/lib/langchainrb_rails/generators/langchainrb_rails/templates/enable_vector_extension_template.rb.tt

@@ -0,0 +1,5 @@
+class <%= migration_class_name %> < ActiveRecord::Migration<%= migration_version %>
+  def change
+    enable_extension "vector"
+  end
+end

data/lib/langchainrb_rails/generators/langchainrb_rails/templates/pgvector_initializer.rb.tt

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+LangchainrbRails.configure do |config|
+  config.vectorsearch = Langchain::Vectorsearch::Pgvector.new(
+    llm: <%= llm_class %>.new(api_key: ENV["OPENAI_API_KEY"])
+  )
+end

data/lib/langchainrb_rails/railtie.rb

@@ -9,7 +9,9 @@ module LangchainrbRails
     end
 
     generators do
+      require_relative "generators/langchainrb_rails/chroma_generator"
       require_relative "generators/langchainrb_rails/pinecone_generator"
+      require_relative "generators/langchainrb_rails/pgvector_generator"
     end
   end
 end

data/lib/langchainrb_rails/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LangchainrbRails
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

data/lib/langchainrb_rails.rb

@@ -1,9 +1,12 @@
 # frozen_string_literal: true
 
+require "forwardable"
 require "langchain"
+require "rails"
 require_relative "langchainrb_rails/version"
 require "langchainrb_rails/railtie"
 require "langchainrb_rails/config"
+require_relative "langchainrb_overrides/vectorsearch/pgvector"
 
 module LangchainrbRails
   class Error < StandardError; end
@@ -13,6 +16,8 @@ module LangchainrbRails
   end
 
   module Generators
+    autoload :BaseGenerator, "langchainrb_rails/generators/langchainrb_rails/base_generator"
+    autoload :ChromaGenerator, "langchainrb_rails/generators/langchainrb_rails/chroma_generator"
     autoload :PgvectorGenerator, "langchainrb_rails/generators/langchainrb_rails/pgvector_generator"
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb_rails
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-10-27 00:00:00.000000000 Z
+date: 2023-11-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: langchainrb
@@ -74,16 +74,26 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".rspec"
+- ".rubocop.yml"
+- ".tool-versions"
 - CHANGELOG.md
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
 - README.md
 - Rakefile
+- lib/langchainrb_overrides/vectorsearch/pgvector.rb
 - lib/langchainrb_rails.rb
 - lib/langchainrb_rails/active_record/hooks.rb
 - lib/langchainrb_rails/config.rb
+- lib/langchainrb_rails/generators/langchainrb_rails/base_generator.rb
+- lib/langchainrb_rails/generators/langchainrb_rails/chroma_generator.rb
+- lib/langchainrb_rails/generators/langchainrb_rails/pgvector_generator.rb
 - lib/langchainrb_rails/generators/langchainrb_rails/pinecone_generator.rb
+- lib/langchainrb_rails/generators/langchainrb_rails/templates/add_vector_column_template.rb.tt
+- lib/langchainrb_rails/generators/langchainrb_rails/templates/chroma_initializer.rb.tt
+- lib/langchainrb_rails/generators/langchainrb_rails/templates/enable_vector_extension_template.rb.tt
+- lib/langchainrb_rails/generators/langchainrb_rails/templates/pgvector_initializer.rb.tt
 - lib/langchainrb_rails/generators/langchainrb_rails/templates/pinecone_initializer.rb.tt
 - lib/langchainrb_rails/railtie.rb
 - lib/langchainrb_rails/version.rb
@@ -111,7 +121,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
 summary: Rails wrapper for langchainrb gem