Awesome
💎🔗 Langchain.rb
⚡ Building LLM-powered applications in Ruby ⚡
For deep Rails integration see: langchainrb_rails gem.
Available for paid consulting engagements! Email me.
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
Installation
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.
Usage
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 |
AI21 | ❌ | ✅ | ❌ | ✅ | |
Anthropic | ❌ | ✅ | ✅ | ❌ | |
AwsBedrock | ✅ | ✅ | ✅ | ❌ | Provides AWS, Cohere, AI21, Antropic and Stability AI models |
Cohere | ✅ | ✅ | ✅ | ✅ | |
GooglePalm | ✅ | ✅ | ✅ | ✅ | |
GoogleVertexAI | ✅ | ❌ | ✅ | ❌ | Requires Google Cloud service auth |
GoogleGemini | ✅ | ❌ | ✅ | ❌ | Requires Gemini API Key (get key) |
HuggingFace | ✅ | ❌ | ❌ | ❌ | |
MistralAI | ✅ | ❌ | ✅ | ❌ | |
Ollama | ✅ | ✅ | ✅ | ✅ | |
Replicate | ✅ | ✅ | ✅ | ✅ |
Using standalone LLMs:
OpenAI
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
parser.parse(llm_response)
# {
# "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:
begin
parser.parse(llm_response)
rescue Langchain::OutputParsers::OutputParserException => e
fix_parser = Langchain::OutputParsers::OutputFixingParser.from_llm(
llm: llm,
parser: parser
)
fix_parser.parse(llm_response)
end
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
)
fix_parser.parse(llm_response)
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:
- Relevant knowledge (or data) is retrieved from the knowledge base (typically a vector search DB)
- A prompt, containing retrieved knowledge above, is constructed.
- 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 |
---|---|---|
Chroma | ✅ | ✅ |
Epsilla | ✅ | ✅ |
Hnswlib | ✅ | ❌ |
Milvus | ✅ | ✅ Zilliz Cloud |
Pinecone | ❌ | ✅ |
Pgvector | ✅ | ✅ |
Qdrant | ✅ | ✅ |
Weaviate | ✅ | ✅ |
Elasticsearch | ✅ | ✅ |
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:
client.create_default_schema
Add plain text data to your vector search database:
client.add_texts(
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:
client.similarity_search(
query:,
k: # number of results to be retrieved
)
Retrieve similar documents based on the query string passed in via the HyDE technique:
client.similarity_search_with_hyde()
Retrieve similar documents based on the embedding passed in:
client.similarity_search_by_vector(
embedding:,
k: # number of results to be retrieved
)
RAG-based querying
client.ask(question: "...")
Assistants
Langchain::Assistant
is a powerful and flexible class that combines Large Language Models (LLMs), tools, and conversation management to create intelligent, interactive assistants. It's designed to handle complex conversations, execute tools, and provide coherent responses based on the context of the interaction.
Features
- Supports multiple LLM providers (OpenAI, Google Gemini, Anthropic, Mistral AI and open-source models via Ollama)
- Integrates with various tools to extend functionality
- Manages conversation threads
- Handles automatic and manual tool execution
- Supports different message formats for various LLM providers
Usage
llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
assistant = Langchain::Assistant.new(
llm: llm,
instructions: "You're a helpful AI assistant",
tools: [Langchain::Tool::NewsRetriever.new(api_key: ENV["NEWS_API_KEY"])]
)
# Add a user message and run the assistant
assistant.add_message_and_run(content: "What's the latest news about AI?")
# Access the conversation thread
messages = assistant.messages
# Run the assistant with automatic tool execution
assistant.run(auto_tool_execution: true)
Configuration
llm
: The LLM instance to use (required)tools
: An array of tool instances (optional)instructions
: System instructions for the assistant (optional)tool_choice
: Specifies how tools should be selected. Default: "auto". A specific tool function name can be passed. This will force the Assistant to always use this function.
Key Methods
add_message
: Adds a user message to the messages arrayrun
: Processes the conversation and generates responsesadd_message_and_run
: Combines adding a message and running the assistantsubmit_tool_output
: Manually submit output to a tool callmessages
: Returns a list of ongoing messages
Built-in Tools 🛠️
Langchain::Tool::Calculator
: Useful for evaluating math expressions. Requiresgem "eqn"
.Langchain::Tool::Database
: Connect your SQL database. Requiresgem "sequel"
.Langchain::Tool::FileSystem
: Interact with the file system (read & write).Langchain::Tool::RubyCodeInterpreter
: Useful for evaluating generated Ruby code. Requiresgem "safe_ruby"
(In need of a better solution).Langchain::Tool::NewsRetriever
: A wrapper around NewsApi.org to fetch news articles.Langchain::Tool::Tavily
: A wrapper around Tavily AI.Langchain::Tool::Weather
: Calls Open Weather API to retrieve the current weather.Langchain::Tool::Wikipedia
: Calls Wikipedia API.
Creating custom Tools
The Langchain::Assistant can be easily extended with custom tools by creating classes that extend Langchain::ToolDefinition
module and implement required methods.
class MovieInfoTool
include Langchain::ToolDefinition
define_function :search_movie, description: "MovieInfoTool: Search for a movie by title" do
property :query, type: "string", description: "The movie title to search for", required: true
end
define_function :get_movie_details, description: "MovieInfoTool: Get detailed information about a specific movie" do
property :movie_id, type: "integer", description: "The TMDb ID of the movie", required: true
end
def initialize(api_key:)
@api_key = api_key
end
def search_movie(query:)
...
end
def get_movie_details(movie_id:)
...
end
end
Example usage:
movie_tool = MovieInfoTool.new(api_key: "...")
assistant = Langchain::Assistant.new(
llm: llm,
instructions: "You're a helpful AI assistant that can provide movie information",
tools: [movie_tool]
)
assistant.add_message_and_run(content: "Can you tell me about the movie 'Inception'?")
# Check the response in the last message in the conversation
assistant.messages.last
Error Handling
The assistant includes error handling for invalid inputs, unsupported LLM types, and tool execution failures. It uses a state machine to manage the conversation flow and handle different scenarios gracefully.
Demos
- Building an AI Assistant that operates a simulated E-commerce Store
- New Langchain.rb Assistants interface
- Langchain.rb Assistant demo with NewsRetriever and function calling on Gemini - code
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
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
# }
Examples
Additional examples available: /examples
Logging
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
Problems
If you're having issues installing unicode
gem required by pragmatic_segmenter
, try running:
gem install unicode -- --with-cflags="-Wno-incompatible-function-pointer-types"
Development
git clone https://github.com/andreibondarev/langchainrb.git
cp .env.example .env
, then fill out the environment variables in.env
bundle exec rake
to ensure that the tests pass and to run standardrbbin/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.- Optionally, install lefthook git hooks for pre-commit to auto lint:
gem install lefthook && lefthook install -f
Discord
Join us in the Langchain.rb Discord server.
Star History
Contributing
Bug reports and pull requests are welcome on GitHub at https://github.com/andreibondarev/langchainrb.
License
The gem is available as open source under the terms of the MIT License.