[BOT ISSUE] langchainrb gem not instrumented
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 38/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Quiet
- Tech stack
- ruby
- Domain
- observability
Research direction
Start by comparing the existing integrations under lib/braintrust/contrib/*/integration.rb, then inspect Appraisals and braintrust.gemspec for dependency and appraisal conventions. Review langchainrb's chat, completion, embedding, tool-calling, structured-output, and assistant APIs before narrowing the integration scope. Done means the agreed langchainrb execution surfaces are instrumented and covered by the repository's integration and dependency checks.
Written by the indexing model from the issue text.
Description
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
- GitHub: https://github.com/patterns-ai-core/langchainrb
- RubyGems: https://rubygems.org/gems/langchainrb (~1.1M downloads, v0.19.5, May 2025)
- Documentation: https://rubydoc.info/gems/langchainrb
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 oflangchainrb- Grep for
langchainacrosslib/braintrust/returns zero matches
- Dominant language
- Ruby
- Stars
- 9
- Forks
- 10
- Avg merge
- 22h 10m
- Merged PRs (30d)
- 6
Getting set up
- Ships a Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from braintrustdata/braintrust-sdk-ruby
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
ruby
Difficulty 4/5 3-5 days Newbie friendliness 48/100
-
ruby
Difficulty 4/5 3-5 days Newbie friendliness 48/100
All issues in braintrustdata/braintrust-sdk-ruby
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
eurosky-social/eu-haul#32 ·
-
good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
benbalter/add-to-org#17 ·
-
good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
benbalter/change_agent#11 ·
-
good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
benbalter/count-org-loc#20 ·
-
good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
benbalter/sitemap-parser#33 ·