There's a lot of open issues
Build LLM-backed Ruby applications with Ruby's Langchain.rb


~> 1.2.0
~> 2.8
>= 0
~> 2.7.6
~> 3.10.0
~> 0.9.10
~> 1.6.5
~> 0.9.3
~> 0.1.6
~> 0.9.4
~> 0.8.10
~> 0.3.4
~> 0.6.0
~> 0.8.0
~> 1.13
~> 1.5
~> 0.2.1
~> 1.0.4
~> 0.2.1
~> 2.2.7
~> 0.9.34
~> 2.10.0
~> 5.68.0
~> 0.8.1
~> 0.9.4
~> 0.3
~> 0.0.4
~> 6.4.0


~> 1.1.0
~> 0.1.9
~> 2.5
>= 0
~> 2.0.0
 Project Readme

💎🔗 Langchain.rb

⚡ Building LLM-powered applications in Ruby ⚡

For deep Rails integration see: langchainrb_rails gem.

Available for paid consulting engagements! Email me.

Tests status Gem Version Docs License X

Use Cases

  • Retrieval Augmented Generation (RAG) and vector search
  • Assistants (chat bots)

Table of Contents

  • Installation
  • Usage
  • Large Language Models (LLMs)
  • Prompt Management
  • Output Parsers
  • Building RAG
  • Assistants
  • Evaluations
  • Examples
  • Logging
  • Problems
  • Development
  • Discord


Install the gem and add to the application's Gemfile by executing:

bundle add langchainrb

If bundler is not being used to manage dependencies, install the gem by executing:

gem install langchainrb

Additional gems may be required. They're not included by default so you can include only what you need.


require "langchain"

Large Language Models (LLMs)

Langchain.rb wraps supported LLMs in a unified interface allowing you to easily swap out and test out different models.

Supported LLMs and features:

LLM providers embed() complete() chat() summarize() Notes
OpenAI Including Azure OpenAI
AwsBedrock Provides AWS, Cohere, AI21, Antropic and Stability AI models
GoogleVertexAI Requires Google Cloud service auth
GoogleGemini Requires Gemini API Key (Limited to US)

Using standalone LLMs:


Add gem "ruby-openai", "~> 6.3.0" to your Gemfile.

llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])

You can pass additional parameters to the constructor, it will be passed to the OpenAI client:

llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"], llm_options: { ... })

Generate vector embeddings:

llm.embed(text: "foo bar").embedding

Generate a chat completion:

llm.chat(messages: [{role: "user", content: "What is the meaning of life?"}]).completion

Summarize the text:

llm.summarize(text: "...").completion

You can use any other LLM by invoking the same interface:

llm = Langchain::LLM::GooglePalm.new(api_key: ENV["GOOGLE_PALM_API_KEY"], default_options: { ... })

Prompt Management

Prompt Templates

Create a prompt with input variables:

prompt = Langchain::Prompt::PromptTemplate.new(template: "Tell me a {adjective} joke about {content}.", input_variables: ["adjective", "content"])
prompt.format(adjective: "funny", content: "chickens") # "Tell me a funny joke about chickens."

Creating a PromptTemplate using just a prompt and no input_variables:

prompt = Langchain::Prompt::PromptTemplate.from_template("Tell me a funny joke about chickens.")
prompt.input_variables # []
prompt.format # "Tell me a funny joke about chickens."

Save prompt template to JSON file:

prompt.save(file_path: "spec/fixtures/prompt/prompt_template.json")

Loading a new prompt template using a JSON file:

prompt = Langchain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/prompt_template.json")
prompt.input_variables # ["adjective", "content"]

Few Shot Prompt Templates

Create a prompt with a few shot examples:

prompt = Langchain::Prompt::FewShotPromptTemplate.new(
  prefix: "Write antonyms for the following words.",
  suffix: "Input: {adjective}\nOutput:",
  example_prompt: Langchain::Prompt::PromptTemplate.new(
    input_variables: ["input", "output"],
    template: "Input: {input}\nOutput: {output}"
  examples: [
    { "input": "happy", "output": "sad" },
    { "input": "tall", "output": "short" }
   input_variables: ["adjective"]

prompt.format(adjective: "good")

# Write antonyms for the following words.
# Input: happy
# Output: sad
# Input: tall
# Output: short
# Input: good
# Output:

Save prompt template to JSON file:

prompt.save(file_path: "spec/fixtures/prompt/few_shot_prompt_template.json")

Loading a new prompt template using a JSON file:

prompt = Langchain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/few_shot_prompt_template.json")
prompt.prefix # "Write antonyms for the following words."

Loading a new prompt template using a YAML file:

prompt = Langchain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/prompt_template.yaml")
prompt.input_variables #=> ["adjective", "content"]

Output Parsers

Parse LLM text responses into structured output, such as JSON.

Structured Output Parser

You can use the StructuredOutputParser to generate a prompt that instructs the LLM to provide a JSON response adhering to a specific JSON schema:

json_schema = {
  type: "object",
  properties: {
    name: {
      type: "string",
      description: "Persons name"
    age: {
      type: "number",
      description: "Persons age"
    interests: {
      type: "array",
      items: {
        type: "object",
        properties: {
          interest: {
            type: "string",
            description: "A topic of interest"
          levelOfInterest: {
            type: "number",
            description: "A value between 0 and 100 of how interested the person is in this interest"
        required: ["interest", "levelOfInterest"],
        additionalProperties: false
      minItems: 1,
      maxItems: 3,
      description: "A list of the person's interests"
  required: ["name", "age", "interests"],
  additionalProperties: false
parser = Langchain::OutputParsers::StructuredOutputParser.from_json_schema(json_schema)
prompt = Langchain::Prompt::PromptTemplate.new(template: "Generate details of a fictional character.\n{format_instructions}\nCharacter description: {description}", input_variables: ["description", "format_instructions"])
prompt_text = prompt.format(description: "Korean chemistry student", format_instructions: parser.get_format_instructions)
# Generate details of a fictional character.
# You must format your output as a JSON value that adheres to a given "JSON Schema" instance.
# ...

Then parse the llm response:

llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
llm_response = llm.chat(messages: [{role: "user", content: prompt_text}]).completion
# {
#   "name" => "Kim Ji-hyun",
#   "age" => 22,
#   "interests" => [
#     {
#       "interest" => "Organic Chemistry",
#       "levelOfInterest" => 85
#     },
#     ...
#   ]
# }

If the parser fails to parse the LLM response, you can use the OutputFixingParser. It sends an error message, prior output, and the original prompt text to the LLM, asking for a "fixed" response:

rescue Langchain::OutputParsers::OutputParserException => e
  fix_parser = Langchain::OutputParsers::OutputFixingParser.from_llm(
    llm: llm,
    parser: parser

Alternatively, if you don't need to handle the OutputParserException, you can simplify the code:

# we already have the `OutputFixingParser`:
# parser = Langchain::OutputParsers::StructuredOutputParser.from_json_schema(json_schema)
fix_parser = Langchain::OutputParsers::OutputFixingParser.from_llm(
  llm: llm,
  parser: parser

See here for a concrete example

Building Retrieval Augment Generation (RAG) system

RAG is a methodology that assists LLMs generate accurate and up-to-date information. A typical RAG workflow follows the 3 steps below:

  1. Relevant knowledge (or data) is retrieved from the knowledge base (typically a vector search DB)
  2. A prompt, containing retrieved knowledge above, is constructed.
  3. LLM receives the prompt above to generate a text completion. Most common use-case for a RAG system is powering Q&A systems where users pose natural language questions and receive answers in natural language.

Vector search databases

Langchain.rb provides a convenient unified interface on top of supported vectorsearch databases that make it easy to configure your index, add data, query and retrieve from it.

Supported vector search databases and features:

Database Open-source Cloud offering
Milvus ✅ Zilliz Cloud

Using Vector Search Databases 🔍

Pick the vector search database you'll be using, add the gem dependency and instantiate the client:

gem "weaviate-ruby", "~> 0.8.9"

Choose and instantiate the LLM provider you'll be using to generate embeddings

llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
client = Langchain::Vectorsearch::Weaviate.new(
    url: ENV["WEAVIATE_URL"],
    api_key: ENV["WEAVIATE_API_KEY"],
    index_name: "Documents",
    llm: llm

You can instantiate any other supported vector search database:

client = Langchain::Vectorsearch::Chroma.new(...)   # `gem "chroma-db", "~> 0.6.0"`
client = Langchain::Vectorsearch::Epsilla.new(...)  # `gem "epsilla-ruby", "~> 0.0.3"`
client = Langchain::Vectorsearch::Hnswlib.new(...)  # `gem "hnswlib", "~> 0.8.1"`
client = Langchain::Vectorsearch::Milvus.new(...)   # `gem "milvus", "~> 0.9.3"`
client = Langchain::Vectorsearch::Pinecone.new(...) # `gem "pinecone", "~> 0.1.6"`
client = Langchain::Vectorsearch::Pgvector.new(...) # `gem "pgvector", "~> 0.2"`
client = Langchain::Vectorsearch::Qdrant.new(...)   # `gem "qdrant-ruby", "~> 0.9.3"`
client = Langchain::Vectorsearch::Elasticsearch.new(...)   # `gem "elasticsearch", "~> 8.2.0"`

Create the default schema:


Add plain text data to your vector search database:

  texts: [
    "Begin by preheating your oven to 375°F (190°C). Prepare four boneless, skinless chicken breasts by cutting a pocket into the side of each breast, being careful not to cut all the way through. Season the chicken with salt and pepper to taste. In a large skillet, melt 2 tablespoons of unsalted butter over medium heat. Add 1 small diced onion and 2 minced garlic cloves, and cook until softened, about 3-4 minutes. Add 8 ounces of fresh spinach and cook until wilted, about 3 minutes. Remove the skillet from heat and let the mixture cool slightly.",
      "In a bowl, combine the spinach mixture with 4 ounces of softened cream cheese, 1/4 cup of grated Parmesan cheese, 1/4 cup of shredded mozzarella cheese, and 1/4 teaspoon of red pepper flakes. Mix until well combined. Stuff each chicken breast pocket with an equal amount of the spinach mixture. Seal the pocket with a toothpick if necessary. In the same skillet, heat 1 tablespoon of olive oil over medium-high heat. Add the stuffed chicken breasts and sear on each side for 3-4 minutes, or until golden brown."

Or use the file parsers to load, parse and index data into your database:

my_pdf = Langchain.root.join("path/to/my.pdf")
my_text = Langchain.root.join("path/to/my.txt")
my_docx = Langchain.root.join("path/to/my.docx")

client.add_data(paths: [my_pdf, my_text, my_docx])

Supported file formats: docx, html, pdf, text, json, jsonl, csv, xlsx, eml, pptx.

Retrieve similar documents based on the query string passed in:

  k:       # number of results to be retrieved

Retrieve similar documents based on the query string passed in via the HyDE technique:


Retrieve similar documents based on the embedding passed in:

  k:       # number of results to be retrieved

RAG-based querying

client.ask(question: "...")


Assistants are Agent-like objects that leverage helpful instructions, LLMs, tools and knowledge to respond to user queries. Assistants can be configured with an LLM of your choice (currently only OpenAI), any vector search database and easily extended with additional tools.

Available Tools 🛠️

Name Description ENV Requirements Gem Requirements
"calculator" Useful for getting the result of a math expression gem "eqn", "~> 1.6.5"
"database" Useful for querying a SQL database gem "sequel", "~> 5.68.0"
"file_system" Interacts with the file system
"ruby_code_interpreter" Interprets Ruby expressions gem "safe_ruby", "~> 1.0.4"
"google_search" A wrapper around Google Search ENV["SERPAPI_API_KEY"] (https://serpapi.com/manage-api-key) gem "google_search_results", "~> 2.0.0"
"news_retriever" A wrapper around NewsApi.org ENV["NEWS_API_KEY"] (https://newsapi.org/)
"tavily" A wrapper around Tavily AI ENV["TAVILY_API_KEY"] (https://tavily.com/)
"weather" Calls Open Weather API to retrieve the current weather ENV["OPEN_WEATHER_API_KEY"] (https://home.openweathermap.org/api_keys) gem "open-weather-ruby-client", "~> 0.3.0"
"wikipedia" Calls Wikipedia API to retrieve the summary gem "wikipedia-client", "~> 1.17.0"


  1. Building an AI Assistant that operates a simulated E-commerce Store
  2. New Langchain.rb Assistants interface
  3. Langchain.rb Assistant demo with NewsRetriever and function calling on Gemini - code

Creating an Assistant

  1. Instantiate an LLM of your choice
llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
  1. Instantiate an Assistant
assistant = Langchain::Assistant.new(
  llm: llm,
  instructions: "You are a Meteorologist Assistant that is able to pull the weather for any location",
  tools: [
    Langchain::Tool::Weather.new(api_key: ENV["OPEN_WEATHER_API_KEY"])

Using an Assistant

You can now add your message to an Assistant.

assistant.add_message content: "What's the weather in New York, New York?"

Run the Assistant to generate a response.


If a Tool is invoked you can manually submit an output.

assistant.submit_tool_output tool_call_id: "...", output: "It's 70 degrees and sunny in New York City"

Or run the assistant with auto_tool_execution: tool to call Tools automatically.

assistant.add_message content: "How about San Diego, CA?"
assistant.run(auto_tool_execution: true)

You can also combine the two by calling:

assistant.add_message_and_run content: "What about Sacramento, CA?", auto_tool_execution: true

Accessing Thread messages

You can access the messages in a Thread by calling assistant.thread.messages.


The Assistant checks the context window limits before every request to the LLM and remove oldest thread messages one by one if the context window is exceeded.

Evaluations (Evals)

The Evaluations module is a collection of tools that can be used to evaluate and track the performance of the output products by LLM and your RAG (Retrieval Augmented Generation) pipelines.


Ragas helps you evaluate your Retrieval Augmented Generation (RAG) pipelines. The implementation is based on this paper and the original Python repo. Ragas tracks the following 3 metrics and assigns the 0.0 - 1.0 scores:

  • Faithfulness - the answer is grounded in the given context.
  • Context Relevance - the retrieved context is focused, containing little to no irrelevant information.
  • Answer Relevance - the generated answer addresses the actual question that was provided.
# We recommend using Langchain::LLM::OpenAI as your llm for Ragas
ragas = Langchain::Evals::Ragas::Main.new(llm: llm)

# The answer that the LLM generated
# The question (or the original prompt) that was asked
# The context that was retrieved (usually from a vectorsearch database)
ragas.score(answer: "", question: "", context: "")
# =>
# {
#   ragas_score: 0.6601257446503674,
#   answer_relevance_score: 0.9573145866787608,
#   context_relevance_score: 0.6666666666666666,
#   faithfulness_score: 0.5
# }


Additional examples available: /examples


Langchain.rb uses standard logging mechanisms and defaults to :warn level. Most messages are at info level, but we will add debug or warn statements as needed. To show all log messages:

Langchain.logger.level = :debug


If you're having issues installing unicode gem required by pragmatic_segmenter, try running:

gem install unicode -- --with-cflags="-Wno-incompatible-function-pointer-types"


  1. git clone https://github.com/andreibondarev/langchainrb.git
  2. cp .env.example .env, then fill out the environment variables in .env
  3. bundle exec rake to ensure that the tests pass and to run standardrb
  4. bin/console to load the gem in a REPL session. Feel free to add your own instances of LLMs, Tools, Agents, etc. and experiment with them.
  5. Optionally, install lefthook git hooks for pre-commit to auto lint: gem install lefthook && lefthook install -f


Join us in the Langchain.rb Discord server.

Star History

Star History Chart


Bug reports and pull requests are welcome on GitHub at https://github.com/andreibondarev/langchainrb.


The gem is available as open source under the terms of the MIT License.