Ruby Llm

From the release notes

RubyLLM 2.0 brings more of each provider's API to Ruby and Rails, with new AI operations, explicit conversation controls, and agents that can resume across requests and jobs. Highlights Seventeen built-in providers, one Ruby API. New integrations include Cohere, Deepgram, ElevenLabs, and Ollama Cloud. Providers and protocols are separate, so integrations can reuse existing wire formats. Agents that wait for you. Human tool approvals, cancellation, and step-by-step loop control work in plain Ruby and persist across Rails jobs. Video, speech, documents, and search. Generate video and speech, extract text with OCR, rerank search results, and work with multimodal embeddings, files, batches, and hosted research. More capable conversations. Typed citations, provider-hosted tools and remote MCP, thinking controls, prompt caching, model fallbacks, and context compaction. Usage you can account for. Track each provider attempt, including retries and fallbacks, with normalized tokens and costs and a historical Rails usage ledger. A consistent Rails integration. Your app owns chats and messages; RubyLLM maintains its supporting tables. Persisted agents use the same public API and work with Active Storage, Action Text, Active Job, and Hotwire. bundle add ruby_llm --version 2.0.0 Upgrading from 1.x? Read the upgrade guide for API changes and phased Rails migrations. Start with What's New in 2.0 for working examples, or continue below for the detailed changes and credits. New Providers and protocols Seventeen providers are built in. Cohere, Deepgram, ElevenLabs, and Ollama Cloud join OpenAI, Anthropic, Gemini, Vertex AI, Bedrock, Azure, xAI, DeepSeek, Mistral, OpenRouter, Perplexity, Ollama, and GPUStack. By @crmne. (a5dbcda9, 71a69a07) Providers can reuse protocols, and one provider can offer several. Providers own authentication, endpoints, catalogs, and service settings. Protocols own requests, parsing, streaming, and error normalization. Model and operation selection pick the right protocol; protocol: provides an explicit override. By @crmne. (d398354d, 3400654b) The provider coverage comparison is much larger. The interactive coverage matrix compares selected shared features with 1.16 and links each cell to sources, implementation, validation, and restrictions. By @crmne. (4683f905, 6051a544) OpenAI uses Responses by default. Chat Completions remains selectable. Responses adds hosted tools, native reasoning replay, citations, file references, and compaction; speech, file transcription, Files, chat batches, and embedding batches use their own operations. Exact request counting uses the Responses input-token endpoint. By @crmne; thanks @mastraus, @andrew-woblavobla, @tpaulshippy, @khasinski, @afurm and @nbelzer. (0875ce2d, 18d3622e, #213, #785, #770, #786) Anthropic gets document citations, hosted tools, files, batches, and context compaction. Web search, web fetch, code execution, and remote MCP use named provider tools, preserve their nativ

From the release notes

RubyLLM 2.0.0.rc4 fixes prompt caching and improves Rails copy upgrades. Keep automatic prompt caching enabled alongside explicit cache_until_here boundaries across Anthropic, OpenRouter, Bedrock Converse, and OpenAI-compatible protocols (#930). RubyLLM sends both requested controls and lets the provider apply its caching rules. On supported OpenAI-compatible models, use with_caching(mode: "explicit") to request explicit-only caching. Preserve Active Record autosave behavior with the Rails copy-upgrade guards, and configure RubyLLM before loading those guards. Add --discard-incomplete-tool-calls to copy-upgrade finish migrations. This opt-in cleanup removes incomplete legacy calls before verification while preserving calls with results and protected 2.0 conversations. Read the upgrade guide before using it; discarded calls are not restored by rollback or resume. Generate simpler copy-upgrade migrations without rename-only helpers. Use provider instance names in instrumentation so delegated providers report the correct name (#926). Refresh the bundled model catalog and available-models documentation. Make 2.0 the default documentation site, with 1.x documentation available at rubyllm.com/v1. Install this prerelease with: gem 'ruby_llm', '2.0.0.rc4' Coming from 1.x? Follow the 2.0 upgrade guide before upgrading an existing application. Changes since RC3