jekyll_ai_related_posts 0.1.0 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8b59977a0c1d912e06792f7123c7d443547f1decb9fdf4042d90a4fcd4e1eb4e
-  data.tar.gz: 159db1306777a201cff3a9d3532ddba444164dbfb780207fb9457ce4898df5f8
+  metadata.gz: dde47b3847f5f2578a80f8f208049f912d409e7812a2927dda4ea333b0b8cd82
+  data.tar.gz: 9d94d4dd9695b96467349818d20f961ac9a55f9bd5c4968c3703636854d71edb
 SHA512:
-  metadata.gz: e0f73857997bdacd22059c542a1d2a642a3ea76aa165241c155a0e8b2cafdc4f48607f334a2ed7a265a252e86969d9e523bf4ef2ac5889e1f39c36d1a27792f5
-  data.tar.gz: a5f5f573459deb7fab308b1fb98a1d60ce1aeda95e28860161ed886a3ab90c43f1b7d36fea6cc5c570b05cd15284a59240e8676f5b10f44290b05fbacbd379df
+  metadata.gz: 857d8f3e381b1f4f3d52c411cc5ab630f4539ab735df57b33276f5b9df0647bebe44319b3a8a2a647f75cc3910409863aeae56d412dd48827fa5116870ea7975
+  data.tar.gz: eab136bfd7e226dcc0dfd71c14a0a9924b5e3aa59f8c376200129b3237e39f7e47ce540d55d03a080d834ebe56306b5827de44d8e55b9f04e71aedfbc3c9b60a

data/CHANGELOG.md

@@ -1,5 +1,11 @@
 ## [Unreleased]
 
-## [0.1.0] - 2024-04-18
+- [Bugfix] Include up to 10 related posts (like native Jekyll does) instead of just 3.
+
+## [0.1.1] - 2024-04-23
+
+- [Bugfix] Exception when running in cache-only mode.
+
+## [0.1.0] - 2024-04-23
 
 - Initial release

data/README.md

@@ -1,5 +1,7 @@
 # Jekyll AI Related Posts 🪄
 
+Rubygems: [jekyll_ai_related_posts](https://rubygems.org/gems/jekyll_ai_related_posts)
+
 Jekyll ships with functionality that populates
 [related_posts](https://jekyllrb.com/docs/variables/) with the ten most recent
 posts. If you install
@@ -18,7 +20,22 @@ posts with the accuracy of OpenAI's models (or any other LLM, for that matter).
 
 Jekyll AI Related Posts is a [Jekyll
 plugin](https://jekyllrb.com/docs/plugins/installation/). It can be installed
-using any Jekyll plugin installation method.
+using any Jekyll plugin installation method. For example, in your `_config.yml`:
+
+```yaml
+plugins:
+  - jekyll_ai_related_posts
+```
+
+You should also ignore the cache files that this plugin generates. (This will
+help avoid a regeneration loop when using `jekyll serve`.)
+
+```yaml
+exclude:
+  - .ai_related_posts_cache.sqlite3
+  - .ai_related_posts_cache.sqlite3-journal
+```
+
 
 ## Configuration
 
@@ -57,6 +74,27 @@ to use it:
 </ul>
 ```
 
+### First Run
+
+The first time the plugin runs, it will fetch embeddings for all your posts.
+Based on some light testing, this took me 0.5 sec per post, or about 50 sec for
+a blog with 100 posts. All subsequent runs will be faster since embeddings will
+be cached.
+
+### Performance
+
+On an example blog with ~100 posts, this plugin produces more accurate results
+than classifier-reborn (LSI) in about the same amount of time. See [this blog
+post](https://www.mikekasberg.com/blog/2024/04/23/better-related-posts-in-jekyll-using-ai.html)
+for details.
+
+### Cost
+
+The API costs to use this plugin with OpenAI's API are minimal. I ran this
+plugin for all 84 posts on [mikekasberg.com](https://www.mikekasberg.com) for
+$0.00 in API fees (1,277 tokens on the text-embedding-3-small model). (Your
+results may vary, but should remain inexpensive.)
+
 ### Upgrading from Built-In Related Posts
 
 If you're already using Jekyll's built-in `site.related_posts` and you want to
@@ -68,6 +106,17 @@ upgrade to AI related posts:
   option to the `jekyll` command. You can remove the `classifier-reborn` gem and
   its dependencies (Numo).
 
+### Cache File (.ai_related_posts_cache.sqlite3)
+
+This plugin will cache embeddings in `.ai_related_posts_cache.sqlite3` in your
+Jekyll source root (typically the root of your project directory). The file
+itself is a SQLite database file. For most cases, I'd recommend adding this file
+to your `.gitignore` since it's a binary cache file. However, you _may_ choose
+to check it in to git if, for example, you want to share cached embeddings
+across many machines (and are willing to check in a binary file on the order of
+1-10Mb to do so). If the file is not present, it will be re-created and
+embeddings will be fetched from the API (which may result in higher API usage
+fees if done frequently).
 
 ## How It Works
 
@@ -88,10 +137,9 @@ After checking out the repo, run `bin/setup` to install dependencies. Then, run
 `rake spec` to run the tests. You can also run `bin/console` for an interactive
 prompt that will allow you to experiment.
 
-To install this gem onto your local machine, run `bundle exec rake install`. To
-release a new version, update the version number in `version.rb`, and then run
-`bundle exec rake release`, which will create a git tag for the version, push
-git commits and the created tag, and push the `.gem` file to
+To release a new version, update the version number in `version.rb`, and then
+run `bundle exec rake release`, which will create a git tag for the version,
+push git commits and the created tag, and push the `.gem` file to
 [rubygems.org](https://rubygems.org).
 
 ## Contributing

data/gemfiles/current.gemfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in jekyll_ai_related_posts.gemspec
+gemspec path: '../'
+
+gem "rake", "~> 13.0"
+
+gem "rspec", "~> 3.0"
+
+gem "rubocop", "~> 1.21"
+gem "rubocop-rails-omakase", require: false
+
+gem "debug"

data/gemfiles/jekyll3.gemfile

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gem "jekyll", "~> 3.9"
+gem "kramdown-parser-gfm"
+
+# Specify your gem's dependencies in jekyll_ai_related_posts.gemspec
+gemspec path: '../'
+
+gem "rake", "~> 13.0"
+
+gem "rspec", "~> 3.0"
+
+gem "rubocop", "~> 1.21"
+gem "rubocop-rails-omakase", require: false
+
+gem "debug"

data/lib/jekyll_ai_related_posts/generator.rb

@@ -12,6 +12,11 @@ module JekyllAiRelatedPosts
       @site = site
       setup_database
 
+      @indexed_posts = {}
+      site.posts.docs.each do |p|
+        @indexed_posts[p.relative_path] = p
+      end
+
       if fetch_enabled?
         Jekyll.logger.info "[ai_related_posts] Generating related posts..."
         @embeddings_fetcher = new_fetcher
@@ -20,11 +25,6 @@ module JekyllAiRelatedPosts
           ensure_embedding_cached(p)
         end
 
-        @indexed_posts = {}
-        site.posts.docs.each do |p|
-          @indexed_posts[p.relative_path] = p
-        end
-
         @site.posts.docs.each do |p|
           find_related(p)
         end
@@ -111,7 +111,7 @@ module JekyllAiRelatedPosts
                                                                                         relative_path: post.relative_path
                                                                                       } ]))
       # The first result is the post itself, with a distance of 0.
-      rowids = results.sort_by { |r| r["distance"] }.drop(1).first(3).map { |r| r["rowid"] }
+      rowids = results.sort_by { |r| r["distance"] }.drop(1).first(10).map { |r| r["rowid"] }
 
       posts_by_rowid = {}
       rowids.each do |rowid|

data/lib/jekyll_ai_related_posts/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module JekyllAiRelatedPosts
-  VERSION = "0.1.0"
+  VERSION = "0.1.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: jekyll_ai_related_posts
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.2
 platform: ruby
 authors:
 - Mike Kasberg
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-04-23 00:00:00.000000000 Z
+date: 2024-04-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '7.1'
+        version: '7.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '7.1'
+        version: '7.0'
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
@@ -107,6 +107,8 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- gemfiles/current.gemfile
+- gemfiles/jekyll3.gemfile
 - lib/jekyll_ai_related_posts.rb
 - lib/jekyll_ai_related_posts/generator.rb
 - lib/jekyll_ai_related_posts/models/post.rb
@@ -119,7 +121,7 @@ metadata:
   allowed_push_host: https://rubygems.org
   homepage_uri: https://github.com/mkasberg/jekyll_ai_related_posts
   source_code_uri: https://github.com/mkasberg/jekyll_ai_related_posts
-  changelog_uri: https://github.com/mkasberg/jekyll_ai_related_posts
+  changelog_uri: https://github.com/mkasberg/jekyll_ai_related_posts/blob/main/CHANGELOG.md
 post_install_message:
 rdoc_options: []
 require_paths: