Rename Langchain.rb to LangChain.rb

In the LLM field, the name LangChain is widely recognized, and the project was
likely originally intended to be called LangChain.rb as a product:
ab9d988

It appears that the current use of the name `Langchain` is due to implementation constraints.
This PR updates the behavior so that Zeitwerk also recognizes the `LangChain` module name for the `langchain.rb` file.

Both the existing `Langchain` and the new `LangChain` module names will work.
However, the `Langchain` constant is now marked as deprecated, and a warning will be shown when it is used:

```console
$ bundle exec ruby -Ilib -rrails -rlangchainrb -e 'Langchain::Errors'
-e:1: warning: `LangChain` is deprecated. Use `LangChain` instead.
```

This change makes it possible to use the name `LangChain`, which is the standard name in the AI ecosystem.
Because `LangChain` is a proper noun, renaming to this widely recognized and commonly used name follows
the principle of least surprise for users.

Author: koic

CHANGELOG.md

@@ -10,6 +10,7 @@
 - [SECURITY]: A change which fixes a security vulnerability.
 
 ## [Unreleased]
+- [COMPAT] [https://github.com/patterns-ai-core/langchainrb/pull/999] Rename `Langchain` to `LangChain`.
 - [COMPAT] [https://github.com/patterns-ai-core/langchainrb/pull/980] Suppress a Ruby 3.4 warning for URI parser.
 - [BREAKING] [https://github.com/patterns-ai-core/langchainrb/pull/997] Remove `Langchain::Vectorsearch::Epsilla` class
 - [BREAKING] [https://github.com/patterns-ai-core/langchainrb/pull/1003] Response classes are now namespaced under `Langchain::LLM::Response`, converted to Rails engine

README.md

@@ -1,2 +1,2 @@
-Langchain::Engine.routes.draw do
+LangChain::Engine.routes.draw do
 end

config/routes.rb

@@ -6,12 +6,12 @@
 # gem install reline
 # or add `gem "reline"` to your Gemfile
 
-openai = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
-assistant = Langchain::Assistant.new(
+openai = LangChain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+assistant = LangChain::Assistant.new(
   llm: openai,
   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"])
+    LangChain::Tool::Weather.new(api_key: ENV["OPEN_WEATHER_API_KEY"])
   ]
 )
 

examples/assistant_chat.rb

@@ -1,10 +1,10 @@
 require "langchain"
 
 # Create a prompt with a few shot examples
-prompt = Langchain::Prompt::FewShotPromptTemplate.new(
+prompt = LangChain::Prompt::FewShotPromptTemplate.new(
   prefix: "Write antonyms for the following words.",
   suffix: "Input: {adjective}\nOutput:",
-  example_prompt: Langchain::Prompt::PromptTemplate.new(
+  example_prompt: LangChain::Prompt::PromptTemplate.new(
     input_variables: ["input", "output"],
     template: "Input: {input}\nOutput: {output}"
   ),
@@ -32,5 +32,5 @@
 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 = LangChain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/few_shot_prompt_template.json")
 prompt.prefix # "Write antonyms for the following words."

examples/create_and_manage_few_shot_prompt_templates.rb

@@ -1,25 +1,25 @@
 require "langchain"
 
 # Create a prompt with one input variable
-prompt = Langchain::Prompt::PromptTemplate.new(template: "Tell me a {adjective} joke.", input_variables: ["adjective"])
+prompt = LangChain::Prompt::PromptTemplate.new(template: "Tell me a {adjective} joke.", input_variables: ["adjective"])
 prompt.format(adjective: "funny") # "Tell me a funny joke."
 
 # Create a prompt with multiple input variables
-prompt = Langchain::Prompt::PromptTemplate.new(template: "Tell me a {adjective} joke about {content}.", input_variables: ["adjective", "content"])
+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 {adjective} joke about {content}.")
+prompt = LangChain::Prompt::PromptTemplate.from_template("Tell me a {adjective} joke about {content}.")
 prompt.input_variables # ["adjective", "content"]
 prompt.format(adjective: "funny", content: "chickens") # "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 = LangChain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/prompt_template.json")
 prompt.input_variables # ["adjective", "content"]
 
 # Loading a new prompt template using a YAML file
-prompt = Langchain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/prompt_template.yaml")
+prompt = LangChain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/prompt_template.yaml")
 prompt.input_variables # ["adjective", "content"]

examples/create_and_manage_prompt_templates.rb

@@ -37,8 +37,8 @@
   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"])
+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.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.
@@ -58,7 +58,7 @@
 
 # Character description: Korean chemistry student
 
-llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+llm = LangChain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
 llm_response = llm.chat(
   messages: [{
     role: "user",
@@ -91,7 +91,7 @@
 #   ```
 # RESPONSE
 
-fix_parser = Langchain::OutputParsers::OutputFixingParser.from_llm(
+fix_parser = LangChain::OutputParsers::OutputFixingParser.from_llm(
   llm: llm,
   parser: parser
 )

examples/create_and_manage_prompt_templates_using_structured_output_parser.rb

@@ -1,9 +1,9 @@
 require_relative "../lib/langchain"
 require "faraday"
 
-llm = Langchain::LLM::Ollama.new(default_options: {chat_model: "llava"})
+llm = LangChain::LLM::Ollama.new(default_options: {chat_model: "llava"})
 
-assistant = Langchain::Assistant.new(llm: llm)
+assistant = LangChain::Assistant.new(llm: llm)
 
 response = assistant.add_message_and_run(
   image_url: "https://gist.githubusercontent.com/andreibondarev/b6f444194d0ee7ab7302a4d83184e53e/raw/099e10af2d84638211e25866f71afa7308226365/sf-cable-car.jpg",

examples/ollama_inquire_about_image.rb

@@ -18,14 +18,14 @@
   }
 ]
 
-openai = Langchain::LLM::OpenAI.new(
+openai = LangChain::LLM::OpenAI.new(
   api_key: ENV["OPENAI_API_KEY"],
   default_options: {
     chat_model: "gpt-3.5-turbo-16k"
   }
 )
 
-client = Langchain::Vectorsearch::Qdrant.new(
+client = LangChain::Vectorsearch::Qdrant.new(
   url: ENV["QDRANT_URL"],
   api_key: ENV["QDRANT_API_KEY"],
   index_name: ENV["QDRANT_INDEX"],

examples/openai_qdrant_function_calls.rb

@@ -5,10 +5,10 @@
 # or add `gem "chroma-db", "~> 0.6.0"` to your Gemfile
 
 # Instantiate the Chroma client
-chroma = Langchain::Vectorsearch::Chroma.new(
+chroma = LangChain::Vectorsearch::Chroma.new(
   url: ENV["CHROMA_URL"],
   index_name: "documents",
-  llm: Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+  llm: LangChain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
 )
 
 # Create the default schema.
@@ -20,9 +20,9 @@
 
 # Set up an array of PDF and TXT documents
 docs = [
-  Langchain.root.join("/docs/document.pdf"),
-  Langchain.root.join("/docs/document.txt"),
-  Langchain.root.join("/docs/document.docx")
+  LangChain.root.join("/docs/document.pdf"),
+  LangChain.root.join("/docs/document.txt"),
+  LangChain.root.join("/docs/document.docx")
 ]
 
 # Add data to the index. Weaviate will use OpenAI to generate embeddings behind the scene.