Add Perplexity provider support

- Implement Perplexity as OpenAI-compatible provider
- Add 5 Perplexity models with pricing information
- Handle HTML error responses from Perplexity API
- Add test coverage with proper skips for unsupported features
- Update documentation and configuration

Author: crmne

README.md

@@ -24,6 +24,9 @@
   <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/openrouter.svg" alt="OpenRouter" class="logo-medium">
   <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/openrouter-text.svg" alt="OpenRouter" class="logo-small">
   &nbsp;
+  <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/perplexity-color.svg" alt="Perplexity" class="logo-medium">
+  <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/perplexity-text.svg" alt="Perplexity" class="logo-small">
+  &nbsp;
 </div>
 
 <div class="badge-container">
@@ -102,7 +105,7 @@ response = chat.with_schema(ProductSchema)
 
 ## Core Capabilities
 
-*   💬 **Unified Chat:** Converse with models from OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Ollama, or any OpenAI-compatible API using `RubyLLM.chat`.
+*   💬 **Unified Chat:** Converse with models from OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Perplexity, Ollama, or any OpenAI-compatible API using `RubyLLM.chat`.
 *   👁️ **Vision:** Analyze images within chats.
 *   🔊 **Audio:** Transcribe and understand audio content.
 *   📄 **Document Analysis:** Extract information from PDFs, text files, CSV, JSON, XML, Markdown, and code files.
@@ -114,7 +117,7 @@ response = chat.with_schema(ProductSchema)
 *   🌊 **Streaming:** Process responses in real-time with idiomatic Ruby blocks.
 *   ⚡ **Async Support:** Built-in fiber-based concurrency for high-performance operations.
 *   🎯 **Smart Configuration:** Global and scoped configs with automatic retries and proxy support.
-*   📚 **Model Registry:** Access 100+ models with capability detection and pricing info.
+*   📚 **Model Registry:** Access 500+ models with capability detection and pricing info.
 
 ## Installation
 
@@ -141,7 +144,7 @@ See the [Installation Guide](https://rubyllm.com/installation) for full details.
 Add persistence to your chat models effortlessly:
 
 ```bash
-# Generate models and migrations (available in v1.4.0)
+# Generate models and migrations
 rails generate ruby_llm:install
 ```
 

bin/console

@@ -13,6 +13,7 @@ RubyLLM.configure do |config|
   config.anthropic_api_key = ENV.fetch('ANTHROPIC_API_KEY', nil)
   config.gemini_api_key = ENV.fetch('GEMINI_API_KEY', nil)
   config.deepseek_api_key = ENV.fetch('DEEPSEEK_API_KEY', nil)
+  config.perplexity_api_key = ENV.fetch('PERPLEXITY_API_KEY', nil)
   config.openrouter_api_key = ENV.fetch('OPENROUTER_API_KEY', nil)
   config.ollama_api_base = ENV.fetch('OLLAMA_API_BASE', nil)
   config.bedrock_api_key = ENV.fetch('AWS_ACCESS_KEY_ID', nil)

docs/configuration.md

@@ -52,9 +52,10 @@ RubyLLM.configure do |config|
   config.gemini_api_key = ENV.fetch('GEMINI_API_KEY', nil)
   config.deepseek_api_key = ENV.fetch('DEEPSEEK_API_KEY', nil)
   config.openrouter_api_key = ENV.fetch('OPENROUTER_API_KEY', nil)
+  config.perplexity_api_key = ENV.fetch('PERPLEXITY_API_KEY', nil) # Available in v1.5.0
   config.ollama_api_base = ENV.fetch('OLLAMA_API_BASE', nil)
-  config.gpustack_api_base = ENV.fetch('GPUSTACK_API_BASE', nil) # Available in v1.4.0
-  config.gpustack_api_key = ENV.fetch('GPUSTACK_API_KEY', nil) # Available in v1.4.0
+  config.gpustack_api_base = ENV.fetch('GPUSTACK_API_BASE', nil)
+  config.gpustack_api_key = ENV.fetch('GPUSTACK_API_KEY', nil)
 
   # --- AWS Bedrock Credentials ---
   # Uses standard AWS credential chain (environment, shared config, IAM role)
@@ -108,7 +109,8 @@ Set the corresponding `*_api_key` attribute for each provider you want to enable
 *   `gemini_api_key`
 *   `deepseek_api_key`
 *   `openrouter_api_key`
-*   `gpustack_api_key` (Available in v1.4.0)
+*   `gpustack_api_key`
+*   `perplexity_api_key` (Available in v1.5.0)
 *   `bedrock_api_key`, `bedrock_secret_key`, `bedrock_region`, `bedrock_session_token` (See AWS documentation for standard credential methods if not set explicitly).
 
 ## Ollama API Base (`ollama_api_base`)

docs/guides/available-models.md

@@ -251,8 +251,6 @@ You can set the temperature using `with_temperature`, which returns the `Chat` i
 ## Custom Request Parameters (`with_params`)
 {: .d-inline-block }
 
-Available in v1.4.0
-{: .label .label-yellow }
 
 You can configure additional provider-specific features by adding custom fields to each API request. Use the `with_params` method.
 
@@ -268,8 +266,6 @@ Allowed parameters vary widely by provider and model. Please consult the provide
 ## Structured Output with JSON Schemas (`with_schema`)
 {: .d-inline-block }
 
-Available in v1.4.0
-{: .label .label-yellow }
 
 RubyLLM supports structured output, which guarantees that AI responses conform to your specified JSON schema. This is different from JSON mode – while JSON mode guarantees valid JSON syntax, structured output enforces the exact schema you define.
 

docs/guides/chat.md

@@ -62,8 +62,6 @@ This approach has one important consequence: **you cannot use `validates :conten
 ### Quick Setup with Generator
 {: .d-inline-block }
 
-Available in v1.4.0
-{: .label .label-yellow }
 
 The easiest way to get started is using the provided Rails generator:
 
@@ -362,8 +360,6 @@ The attachment API automatically detects file types based on file extension or c
 ### Structured Output with Schemas
 {: .d-inline-block }
 
-Available in v1.4.0
-{: .label .label-yellow }
 
 Structured output works seamlessly with Rails persistence:
 

docs/guides/rails.md

@@ -49,6 +49,10 @@ One beautiful API for ChatGPT, Claude, Gemini, and more. Chat, images, embedding
     <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/openrouter.svg" alt="OpenRouter" class="logo-medium">
     <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/openrouter-text.svg" alt="OpenRouter" class="logo-small">
   </div>
+  <div class="provider-logo">
+    <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/perplexity-color.svg" alt="Perplexity" class="logo-medium">
+    <img src="https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/perplexity-text.svg" alt="Perplexity" class="logo-small">
+  </div>
 </div>
 
 <div class="badge-container">
@@ -129,7 +133,7 @@ response = chat.with_schema(ProductSchema)
 
 ## Core Capabilities
 
-*   💬 **Unified Chat:** Converse with models from OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Ollama, or any OpenAI-compatible API using `RubyLLM.chat`.
+*   💬 **Unified Chat:** Converse with models from OpenAI, Anthropic, Gemini, Bedrock, OpenRouter, DeepSeek, Perplexity, Ollama, or any OpenAI-compatible API using `RubyLLM.chat`.
 *   👁️ **Vision:** Analyze images within chats.
 *   🔊 **Audio:** Transcribe and understand audio content.
 *   📄 **Document Analysis:** Extract information from PDFs, text files, CSV, JSON, XML, Markdown, and code files.
@@ -141,7 +145,7 @@ response = chat.with_schema(ProductSchema)
 *   🌊 **Streaming:** Process responses in real-time with idiomatic Ruby blocks.
 *   ⚡ **Async Support:** Built-in fiber-based concurrency for high-performance operations.
 *   🎯 **Smart Configuration:** Global and scoped configs with automatic retries and proxy support.
-*   📚 **Model Registry:** Access 100+ models with capability detection and pricing info.
+*   📚 **Model Registry:** Access 500+ models with capability detection and pricing info.
 
 ## Installation
 
@@ -168,7 +172,7 @@ See the [Installation Guide](https://rubyllm.com/installation) for full details.
 Add persistence to your chat models effortlessly:
 
 ```bash
-# Generate models and migrations (available in v1.4.0)
+# Generate models and migrations
 rails generate ruby_llm:install
 ```
 

docs/index.md

@@ -16,6 +16,7 @@
   'openai' => 'OpenAI',
   'api' => 'API',
   'deepseek' => 'DeepSeek',
+  'perplexity' => 'Perplexity',
   'bedrock' => 'Bedrock',
   'openrouter' => 'OpenRouter',
   'gpustack' => 'GPUStack',
@@ -82,6 +83,7 @@ def logger
 RubyLLM::Provider.register :anthropic, RubyLLM::Providers::Anthropic
 RubyLLM::Provider.register :gemini, RubyLLM::Providers::Gemini
 RubyLLM::Provider.register :deepseek, RubyLLM::Providers::DeepSeek
+RubyLLM::Provider.register :perplexity, RubyLLM::Providers::Perplexity
 RubyLLM::Provider.register :bedrock, RubyLLM::Providers::Bedrock
 RubyLLM::Provider.register :openrouter, RubyLLM::Providers::OpenRouter
 RubyLLM::Provider.register :ollama, RubyLLM::Providers::Ollama

lib/ruby_llm.rb

@@ -18,6 +18,7 @@ class Configuration
                   :anthropic_api_key,
                   :gemini_api_key,
                   :deepseek_api_key,
+                  :perplexity_api_key,
                   :bedrock_api_key,
                   :bedrock_secret_key,
                   :bedrock_region,