ragdoll-cli 0.1.11 → 0.1.12

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 89c5200b031e287b125fb93d7025ea666ad3456bdc209fbc68a0dc70b673a410
-  data.tar.gz: 5bfa7dabb52f7b990b5935736ec1710a3b0f4cace386903bb9491bcf4f88720a
+  metadata.gz: 95d02e9e2a6f2ed5278406deae5fb36a8b55aaa1fa9228e3ca4bc8ad602daaf8
+  data.tar.gz: 34e38890fb8829a213057bb4f3142ce81c620e1e2463b70b8b3d2d0692beae5a
 SHA512:
-  metadata.gz: f3eb42ababba85311e9d6bb3db1b5cf4f63f00e46a4a07ea8e9ec21841a9b4cdea44d36619b168a9298d08393d250917f66c14fa82c72b3866937833b3a44bae
-  data.tar.gz: 2a5085c3c38a9147f2bf26fb8a4ad2814bccdb05dfa3d5d76f5cb7ec21319d82d969758eece5b066f01b50100efa85ae9a9abfa20badca70d9144b5bd52c7906
+  metadata.gz: 5767875a5559078f341466140788711c61b45f9cd52bc77fd0844b43574a84c9462367abbe29c88d9c997df86f6e6996f116fbe2c4bb5201321f13d8ccac6eb5
+  data.tar.gz: 68d51ae3e7061e95a9a2f74f55d269afdc3af9bb377edd6edb5758eae7a49938a4f3032cb3c358a4e82d367b1a28ff26882183b6f7714fa4cf04eb556a988c8f

data/README.md

@@ -1,7 +1,7 @@
-<div align="center" style="background-color: yellow; color: black; padding: 20px; margin: 20px 0; border: 2px solid black; font-size: 48px; font-weight: bold;">
-  ⚠️ CAUTION ⚠️<br />
-  Software Under Development by a Crazy Man
-</div>
+> [!CAUTION]
+> **Software Under Development by a Crazy Man**
+>
+> Evolved from multi-modal to unified text-based RAG architecture.
 <br />
 <div align="center">
   <table>
@@ -12,7 +12,7 @@
         </a>
       </td>
       <td width="50%" valign="top">
-        <p>Multi-modal RAG (Retrieval-Augmented Generation) is an architecture that integrates multiple data types (such as text, images, and audio) to enhance AI response generation. It combines retrieval-based methods, which fetch relevant information from a knowledge base, with generative large language models (LLMs) that create coherent and contextually appropriate outputs. This approach allows for more comprehensive and engaging user interactions, such as chatbots that respond with both text and images or educational tools that incorporate visual aids into learning materials. By leveraging various modalities, multi-modal RAG systems improve context understanding and user experience.</p>
+        <p>Unified Text-Based RAG converts all media types—images, audio, documents—into comprehensive text representations before vectorization. This approach enables powerful cross-modal search where you can find images through AI-generated descriptions, audio through transcripts, and all content through a single, unified text-based search index. The system combines intelligent text conversion with retrieval-based methods and generative large language models for enhanced AI response generation.</p>
       </td>
     </tr>
   </table>
@@ -20,7 +20,7 @@
 
 # Ragdoll::CLI
 
-Standalone command-line interface for the Ragdoll RAG (Retrieval-Augmented Generation) system. Provides document import, search, and management capabilities through a simple CLI.
+Standalone command-line interface for the Ragdoll unified text-based RAG system. Converts all media types to searchable text and provides powerful cross-modal search capabilities through a simple CLI.
 
 ## Installation
 

data/lib/ragdoll/cli/commands/search.rb

@@ -10,6 +10,11 @@ module Ragdoll
 
         puts "Searching for: #{query}"
         puts "Search type: #{options[:search_type] || 'semantic'}"
+
+        # Show deprecation warning for content_type
+        if options[:content_type]
+          puts "⚠️  DEPRECATED: --content_type option is deprecated. Unified text-based system converts all media to searchable text."
+        end
         
         # Show hybrid search weights if applicable
         if options[:search_type] == 'hybrid'

data/lib/ragdoll/cli/configuration_loader.rb

@@ -22,7 +22,9 @@ module Ragdoll
 
         default_config = {
           'llm_provider' => 'openai',
-          'embedding_model' => 'text-embedding-3-small',
+          'embedding_model' => 'text-embedding-3-large',
+          'embedding_provider' => 'openai',
+          'use_unified_content' => true,
           'chunk_size' => 1000,
           'chunk_overlap' => 200,
           'search_similarity_threshold' => 0.7,
@@ -72,7 +74,13 @@ module Ragdoll
             ragdoll_config.llm_provider = config['llm_provider']&.to_sym || :openai
           end
           if ragdoll_config.respond_to?(:embedding_model=)
-            ragdoll_config.embedding_model = config['embedding_model'] || 'text-embedding-3-small'
+            ragdoll_config.embedding_model = config['embedding_model'] || 'text-embedding-3-large'
+          end
+          if ragdoll_config.respond_to?(:embedding_provider=)
+            ragdoll_config.embedding_provider = config['embedding_provider']&.to_sym || :openai
+          end
+          if ragdoll_config.respond_to?(:use_unified_content=)
+            ragdoll_config.use_unified_content = config['use_unified_content'] != false
           end
 
           # Processing settings

data/lib/ragdoll/cli/version.rb

@@ -3,6 +3,6 @@
 
 module Ragdoll
   module CLI
-    VERSION = "0.1.11"
+    VERSION = "0.1.12"
   end
 end

data/lib/ragdoll/cli.rb

@@ -42,7 +42,7 @@ module Ragdoll
       method_option :threshold, type: :numeric,
                                desc: 'Similarity threshold (0.0-1.0, lower = more results)'
       method_option :content_type, type: :string, aliases: '-c',
-                                   desc: 'Filter by content type (text, image, audio)'
+                                   desc: 'DEPRECATED: Content type filtering (unified text-based system converts all media to text)'
       method_option :classification, type: :string, aliases: '-C',
                                      desc: 'Filter by classification'
       method_option :keywords, type: :string, aliases: '-k',

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ragdoll-cli
 version: !ruby/object:Gem::Version
-  version: 0.1.11
+  version: 0.1.12
 platform: ruby
 authors:
 - Dewayne VanHoozer
@@ -15,14 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.10
+        version: 0.1.12
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.10
+        version: 0.1.12
 - !ruby/object:Gem::Dependency
   name: ruby-progressbar
   requirement: !ruby/object:Gem::Requirement
@@ -177,8 +177,9 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: Command-line interface for Ragdoll RAG system with semantic, full-text,
-  and hybrid search capabilities. Under development. Contributors welcome.
+description: Command-line interface for Ragdoll's unified text-based RAG system. Converts
+  all media types (images, audio, documents) to searchable text for powerful cross-modal
+  search capabilities. Under development. Contributors welcome.
 email:
 - dvanhoozer@gmail.com
 executables:
@@ -227,7 +228,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.7.1
+rubygems_version: 3.7.2
 specification_version: 4
-summary: Multi-Modal Retrieval Augmented Generation for the CLI
+summary: Unified Text-Based RAG CLI for Cross-Modal Search
 test_files: []