ruby_llm 1.3.0 → 1.3.2beta1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8a1f6385e98e9396c7f9d8021bd2e574f5f8c8aa1cc05c7f10311e2059101017
-  data.tar.gz: e7617280adc17488f9dbc810b424b22ee21f36c0684f0a5f37762dd290d6c0de
+  metadata.gz: b069393971ae461a63487ba8a13d1f81a791d96fc0f537fceb02de88d9e690d0
+  data.tar.gz: c34f0884ffd9cffd3c0311ebbe8d7fbacc151b17512984b999dace24fa0bfe74
 SHA512:
-  metadata.gz: 80bcef1cb440519b7eb146bd4064f8eb5a40cf1fd5e309ac582c6be8a3aee0a33b244e8c4961bc69ac763b2665adab918238a0d8787b41c2fb6e5e7fd6343ae3
-  data.tar.gz: 3d95b550d6d879ad29e20bb328cb09d7191b4055180cba95e237ddab2d1173845463d62e407c777d6b76425958531fb6e7abc664939478c9e89b41565971ad2b
+  metadata.gz: 5ba83dd19febb3070e0f127eb6dc87fd92664d8afae2f4024240588fdc8624dabdcc5c2b089e5147d22601c3505b966f4bed7383fbf6e36ce8dff5bea568ef87
+  data.tar.gz: b7940d1a6b8bf72ba08eb9d63440505935022d372ffdab6aac51599fb23a9e68af49085cb965488f7306d28143f7b39ec9c0138a93ba52ad3ca3ac574e03a442

data/README.md

@@ -37,7 +37,7 @@
 
 Every AI provider comes with its own client library, its own response format, its own conventions for streaming, and its own way of handling errors. Want to use multiple providers? Prepare to juggle incompatible APIs and bloated dependencies.
 
-RubyLLM fixes all that. One beautiful API for everything. One consistent format. Minimal dependencies — just Faraday and Zeitwerk. Because working with AI should be a joy, not a chore.
+RubyLLM fixes all that. One beautiful API for everything. One consistent format. Minimal dependencies — just Faraday, Zeitwerk, and Marcel. Because working with AI should be a joy, not a chore.
 
 ## What makes it great
 
@@ -46,14 +46,14 @@ RubyLLM fixes all that. One beautiful API for everything. One consistent format.
 chat = RubyLLM.chat
 chat.ask "What's the best way to learn Ruby?"
 
-# Analyze images
-chat.ask "What's in this image?", with: { image: "ruby_conf.jpg" }
+# Analyze images, audio, documents, and text files
+chat.ask "What's in this image?", with: "ruby_conf.jpg"
+chat.ask "Describe this meeting", with: "meeting.wav"
+chat.ask "Summarize this document", with: "contract.pdf"
+chat.ask "Explain this code", with: "app.rb"
 
-# Analyze audio recordings
-chat.ask "Describe this meeting", with: { audio: "meeting.wav" }
-
-# Analyze documents
-chat.ask "Summarize this document", with: { pdf: "contract.pdf" }
+# Multiple files at once - types automatically detected
+chat.ask "Analyze these files", with: ["diagram.png", "report.pdf", "notes.txt"]
 
 # Stream responses in real-time
 chat.ask "Tell me a story about a Ruby programmer" do |chunk|
@@ -90,7 +90,7 @@ chat.with_tool(Weather).ask "What's the weather in Berlin? (52.5200, 13.4050)"
 *   💬 **Unified Chat:** Converse with models from OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Ollama, or any OpenAI-compatible API using `RubyLLM.chat`.
 *   👁️ **Vision:** Analyze images within chats.
 *   🔊 **Audio:** Transcribe and understand audio content.
-*   📄 **PDF Analysis:** Extract information and summarize PDF documents.
+*   📄 **Document Analysis:** Extract information from PDFs, text files, and other documents.
 *   🖼️ **Image Generation:** Create images with `RubyLLM.paint`.
 *   📊 **Embeddings:** Generate text embeddings for vector search with `RubyLLM.embed`.
 *   🔧 **Tools (Function Calling):** Let AI models call your Ruby code using `RubyLLM::Tool`.
@@ -143,6 +143,10 @@ end
 # Now interacting with a Chat record persists the conversation:
 chat_record = Chat.create!(model_id: "gpt-4.1-nano")
 chat_record.ask("Explain Active Record callbacks.") # User & Assistant messages saved
+
+# Works seamlessly with file attachments - types automatically detected
+chat_record.ask("What's in this file?", with: "report.pdf")
+chat_record.ask("Analyze these", with: ["image.jpg", "data.csv", "notes.txt"])
 ```
 Check the [Rails Integration Guide](https://rubyllm.com/guides/rails) for more.
 

data/lib/ruby_llm/active_record/acts_as.rb

@@ -18,6 +18,7 @@ module RubyLLM
           has_many :messages,
                    -> { order(created_at: :asc) },
                    class_name: @message_class,
+                   inverse_of: :chat,
                    dependent: :destroy
 
           delegate :add_message, to: :to_llm

data/lib/ruby_llm/aliases.json

@@ -65,13 +65,21 @@
     "gemini": "gemini-2.0-flash-lite-001",
     "openrouter": "google/gemini-2.0-flash-lite-001"
   },
-  "gemini-2.5-flash-preview-05-20": {
-    "gemini": "gemini-2.5-flash-preview-05-20",
-    "openrouter": "google/gemini-2.5-flash-preview-05-20"
+  "gemini-2.5-flash": {
+    "gemini": "gemini-2.5-flash",
+    "openrouter": "google/gemini-2.5-flash"
   },
-  "gemini-2.5-pro-exp-03-25": {
-    "gemini": "gemini-2.5-pro-exp-03-25",
-    "openrouter": "google/gemini-2.5-pro-exp-03-25"
+  "gemini-2.5-flash-lite-preview-06-17": {
+    "gemini": "gemini-2.5-flash-lite-preview-06-17",
+    "openrouter": "google/gemini-2.5-flash-lite-preview-06-17"
+  },
+  "gemini-2.5-pro": {
+    "gemini": "gemini-2.5-pro",
+    "openrouter": "google/gemini-2.5-pro"
+  },
+  "gemini-2.5-pro-preview-05-06": {
+    "gemini": "gemini-2.5-pro-preview-05-06",
+    "openrouter": "google/gemini-2.5-pro-preview-05-06"
   },
   "gemma-3-12b-it": {
     "gemini": "gemma-3-12b-it",
@@ -85,18 +93,14 @@
     "gemini": "gemma-3-4b-it",
     "openrouter": "google/gemma-3-4b-it"
   },
+  "gemma-3n-e4b-it": {
+    "gemini": "gemma-3n-e4b-it",
+    "openrouter": "google/gemma-3n-e4b-it"
+  },
   "gpt-3.5-turbo": {
     "openai": "gpt-3.5-turbo",
     "openrouter": "openai/gpt-3.5-turbo"
   },
-  "gpt-3.5-turbo-0125": {
-    "openai": "gpt-3.5-turbo-0125",
-    "openrouter": "openai/gpt-3.5-turbo-0125"
-  },
-  "gpt-3.5-turbo-1106": {
-    "openai": "gpt-3.5-turbo-1106",
-    "openrouter": "openai/gpt-3.5-turbo-1106"
-  },
   "gpt-3.5-turbo-16k": {
     "openai": "gpt-3.5-turbo-16k",
     "openrouter": "openai/gpt-3.5-turbo-16k"
@@ -133,10 +137,6 @@
     "openai": "gpt-4.1-nano",
     "openrouter": "openai/gpt-4.1-nano"
   },
-  "gpt-4.5-preview": {
-    "openai": "gpt-4.5-preview",
-    "openrouter": "openai/gpt-4.5-preview"
-  },
   "gpt-4o": {
     "openai": "gpt-4o",
     "openrouter": "openai/gpt-4o"
@@ -201,6 +201,10 @@
     "openai": "o3-mini",
     "openrouter": "openai/o3-mini"
   },
+  "o3-pro": {
+    "openai": "o3-pro",
+    "openrouter": "openai/o3-pro"
+  },
   "o4-mini": {
     "openai": "o4-mini",
     "openrouter": "openai/o4-mini"

data/lib/ruby_llm/attachment.rb

@@ -99,7 +99,7 @@ module RubyLLM
     def determine_mime_type
       return @mime_type = active_storage_content_type if active_storage? && active_storage_content_type.present?
 
-      @mime_type = RubyLLM::MimeType.for(@source, name: @filename)
+      @mime_type = RubyLLM::MimeType.for(url? ? nil : @source, name: @filename)
       @mime_type = RubyLLM::MimeType.for(content) if @mime_type == 'application/octet-stream'
       @mime_type = 'audio/wav' if @mime_type == 'audio/x-wav' # Normalize WAV type
     end

data/lib/ruby_llm/chat.rb

@@ -93,18 +93,19 @@ module RubyLLM
     end
 
     def complete(&)
-      @on[:new_message]&.call
       response = @provider.complete(
         messages,
         tools: @tools,
         temperature: @temperature,
         model: @model.id,
         connection: @connection,
-        &
+        &wrap_streaming_block(&)
       )
-      @on[:end_message]&.call(response)
 
+      @on[:new_message]&.call unless block_given?
       add_message response
+      @on[:end_message]&.call(response)
+
       if response.tool_call?
         handle_tool_calls(response, &)
       else
@@ -124,11 +125,28 @@ module RubyLLM
 
     private
 
+    def wrap_streaming_block(&block)
+      return nil unless block_given?
+
+      first_chunk_received = false
+
+      proc do |chunk|
+        # Create message on first content chunk
+        unless first_chunk_received
+          first_chunk_received = true
+          @on[:new_message]&.call
+        end
+
+        # Pass chunk to user's block
+        block.call chunk
+      end
+    end
+
     def handle_tool_calls(response, &)
       response.tool_calls.each_value do |tool_call|
         @on[:new_message]&.call
         result = execute_tool tool_call
-        message = add_tool_result tool_call.id, result
+        message = add_message role: :tool, content: result.to_s, tool_call_id: tool_call.id
         @on[:end_message]&.call(message)
       end
 
@@ -140,13 +158,5 @@ module RubyLLM
       args = tool_call.arguments
       tool.call(args)
     end
-
-    def add_tool_result(tool_use_id, result)
-      add_message(
-        role: :tool,
-        content: result.is_a?(Hash) && result[:error] ? result[:error] : result.to_s,
-        tool_call_id: tool_use_id
-      )
-    end
   end
 end

data/lib/ruby_llm/configuration.rb

@@ -36,6 +36,7 @@ module RubyLLM
                   :retry_interval_randomness,
                   :http_proxy,
                   # Logging configuration
+                  :logger,
                   :log_file,
                   :log_level,
                   :log_assume_model_exists