Summary
The langchainrb gem is the most widely adopted Ruby AI framework (~1.1M downloads, v0.19.5, May 2025) and is not instrumented by this SDK. It is the Ruby analog of Python's LangChain, providing chat completions, embeddings, tool calling, RAG, and assistant/agent patterns across multiple providers.
What is missing
No instrumentation exists for any langchainrb execution surface. Key APIs that should be instrumented:
Chat Completions
Langchain::LLM::*#chat(messages:, ...) — unified chat interface across all providers (OpenAI, Anthropic, Google Gemini, Ollama, AWS Bedrock, Azure OpenAI, Cohere, HuggingFace, Mistral, Replicate)
Langchain::LLM::*#complete(prompt:, ...) — text completion
Embeddings
Langchain::LLM::*#embed(text:, ...) — vector embeddings generation across providers
Tool / Function Calling
- Tool definitions and automatic tool execution within chat flows
Structured Outputs
Langchain::OutputParsers::StructuredOutputParser — JSON schema-based structured extraction from LLM responses
Assistants / Agents
Langchain::Assistant — agent framework with tool execution, conversation management, and multi-turn interaction
Braintrust docs status
not_found — No mention of langchainrb as a Ruby integration anywhere in Braintrust documentation. The SDK integrations page at https://www.braintrust.dev/docs/integrations/sdk-integrations lists a general "LangChain" integration but it is not Ruby-specific and does not cover this gem.
Upstream sources
Local repo files inspected
lib/braintrust/contrib/*/integration.rb — only 4 integrations registered: OpenAI, RubyOpenAI, RubyLLM, Anthropic. No langchainrb integration.
lib/braintrust/contrib/ — no directory or files for langchainrb or langchain
Appraisals — no appraisal scenarios for langchainrb
braintrust.gemspec — no mention of langchainrb
- Grep for
langchain across lib/braintrust/ returns zero matches
Summary
The
langchainrbgem is the most widely adopted Ruby AI framework (~1.1M downloads, v0.19.5, May 2025) and is not instrumented by this SDK. It is the Ruby analog of Python's LangChain, providing chat completions, embeddings, tool calling, RAG, and assistant/agent patterns across multiple providers.What is missing
No instrumentation exists for any
langchainrbexecution surface. Key APIs that should be instrumented:Chat Completions
Langchain::LLM::*#chat(messages:, ...)— unified chat interface across all providers (OpenAI, Anthropic, Google Gemini, Ollama, AWS Bedrock, Azure OpenAI, Cohere, HuggingFace, Mistral, Replicate)Langchain::LLM::*#complete(prompt:, ...)— text completionEmbeddings
Langchain::LLM::*#embed(text:, ...)— vector embeddings generation across providersTool / Function Calling
Structured Outputs
Langchain::OutputParsers::StructuredOutputParser— JSON schema-based structured extraction from LLM responsesAssistants / Agents
Langchain::Assistant— agent framework with tool execution, conversation management, and multi-turn interactionBraintrust docs status
not_found— No mention oflangchainrbas a Ruby integration anywhere in Braintrust documentation. The SDK integrations page at https://www.braintrust.dev/docs/integrations/sdk-integrations lists a general "LangChain" integration but it is not Ruby-specific and does not cover this gem.Upstream sources
Local repo files inspected
lib/braintrust/contrib/*/integration.rb— only 4 integrations registered: OpenAI, RubyOpenAI, RubyLLM, Anthropic. No langchainrb integration.lib/braintrust/contrib/— no directory or files forlangchainrborlangchainAppraisals— no appraisal scenarios forlangchainrbbraintrust.gemspec— no mention oflangchainrblangchainacrosslib/braintrust/returns zero matches