langchainrb 0.7.2 → 0.7.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 49f95a7d3bf92523a3bb74ffd9c1cff35c258c4ecb9523e75b3be4ffdf333359
-  data.tar.gz: a114fc925963757330e83e9287314b1c363206a31293e788ab8f7cc5f8e82249
+  metadata.gz: 3d2d42bf6883822d160e0eeeb4adbfe1598ee271bd3dfd8d4d4b914db814ed0d
+  data.tar.gz: f041fc5f276258072275ab5979bf670cc5c6a122b8d4d55ca571224af790d43d
 SHA512:
-  metadata.gz: e0fb4076645a2ba09e0e9012fa2ec84260c5294f59628284baace34ad98b4dc2621c29217890aba7995d21288b68b0eab96a4ad4ba74beb1c41d8e79c296539d
-  data.tar.gz: 2d681b82119d4c4356011bcba6f5590429abdb3bea3049ab4c50ba720320493a64838bc08c6b9b8f16d2b2bd71d445795ae56923074a47b26e9948873460a250
+  metadata.gz: 61b3c342e8630e6d3ca325bfb105a29d609d99d668dc5c4cfa1cb2c447c230bb8f1f6aa7d252a08129918a0fa11e37bcab813c9700a4c690dd9e5d337eebeb7d
+  data.tar.gz: 7ef534ed87ae2d6c077854a03eb314390238d95e9c0b49e85c9042d60d122806709ee07e007e5de884535d4cb8b6a3ffa6504a31e6ac36fadbde10e9c1924444

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 ## [Unreleased]
 
+## [0.7.3] - 2023-11-08
+- LLM response passes through the context in RAG cases 
+- Fix gpt-4 token length validation
+
 ## [0.7.2] - 2023-11-02
 - Azure OpenAI LLM support
 

data/README.md

@@ -1,6 +1,6 @@
 💎🔗 Langchain.rb
 ---
-⚡ Building applications with LLMs through composability ⚡
+⚡ Building LLM-powered applications in Ruby ⚡
 
 For deep Rails integration see: [langchainrb_rails](https://github.com/andreibondarev/langchainrb_rails) gem.
 
@@ -11,21 +11,24 @@ Available for paid consulting engagements! [Email me](mailto:andrei@sourcelabs.i
 [![Docs](http://img.shields.io/badge/yard-docs-blue.svg)](http://rubydoc.info/gems/langchainrb)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](https://github.com/andreibondarev/langchainrb/blob/main/LICENSE.txt)
 [![](https://dcbadge.vercel.app/api/server/WDARp7J2n8?compact=true&style=flat)](https://discord.gg/WDARp7J2n8)
+[![X](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40rushing_andrei)](https://twitter.com/rushing_andrei)
 
-Langchain.rb is a library that's an abstraction layer on top many emergent AI, ML and other DS tools. The goal is to abstract complexity and difficult concepts to make building AI/ML-supercharged applications approachable for traditional software engineers.
+## Use Cases
+* Retrieval Augmented Generation (RAG) and vector search
+* Chat bots
+* [AI agents](https://github.com/andreibondarev/langchainrb/tree/main/lib/langchain/agent/agents.md)
 
-## Explore Langchain.rb
+## Table of Contents
 
 - [Installation](#installation)
 - [Usage](#usage)
-- [Vector Search Databases](#using-vector-search-databases-)
-- [Standalone LLMs](#using-standalone-llms-️)
-- [Prompts](#using-prompts-)
-- [Output Parsers](#using-output-parsers)
-- [Agents](#using-agents-)
-- [Loaders](#loaders-)
-- [Examples](#examples)
+- [Large Language Models (LLMs)](#large-language-models-llms)
+- [Prompt Management](#prompt-management)
+- [Output Parsers](#output-parsers)
+- [Building RAG](#building-retrieval-augment-generation-rag-system)
+- [Building chat bots](#building-chat-bots)
 - [Evaluations](#evaluations-evals)
+- [Examples](#examples)
 - [Logging](#logging)
 - [Development](#development)
 - [Discord](#discord)
@@ -46,264 +49,65 @@ If bundler is not being used to manage dependencies, install the gem by executin
 require "langchain"
 ```
 
-#### Supported vector search databases and features:
-
-| Database | Querying           | Storage | Schema Management | Backups | Rails Integration |
-| -------- |:------------------:| -------:| -----------------:| -------:| -----------------:|
-| [Chroma](https://trychroma.com/) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | :white_check_mark: |
-| [Hnswlib](https://github.com/nmslib/hnswlib/) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | WIP               |
-| [Milvus](https://milvus.io/) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | :white_check_mark: |
-| [Pinecone](https://www.pinecone.io/) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | :white_check_mark: |
-| [Pgvector](https://github.com/pgvector/pgvector) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | :white_check_mark: |
-| [Qdrant](https://qdrant.tech/) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | :white_check_mark: |
-| [Weaviate](https://weaviate.io/) | :white_check_mark: | :white_check_mark: | :white_check_mark: | WIP     | :white_check_mark: |
-
-### Using Vector Search Databases 🔍
-
-Choose the LLM provider you'll be using (OpenAI or Cohere) and retrieve the API key.
-
-Add `gem "weaviate-ruby", "~> 0.8.3"`  to your Gemfile.
-
-Pick the vector search database you'll be using and instantiate the client:
-```ruby
-client = Langchain::Vectorsearch::Weaviate.new(
-    url: ENV["WEAVIATE_URL"],
-    api_key: ENV["WEAVIATE_API_KEY"],
-    index_name: "",
-    llm: Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
-)
-
-# You can instantiate any other supported vector search database:
-client = Langchain::Vectorsearch::Chroma.new(...) # `gem "chroma-db", "~> 0.6.0"`
-client = Langchain::Vectorsearch::Hnswlib.new(...) # `gem "hnswlib", "~> 0.8.1"`
-client = Langchain::Vectorsearch::Milvus.new(...) # `gem "milvus", "~> 0.9.2"`
-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"`
-```
-
-```ruby
-# Creating the default schema
-client.create_default_schema
-```
-
-```ruby
-# Store plain texts in 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."
-    ]
-)
-```
-```ruby
-# Store the contents of your files in your vector search 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])
-```
-```ruby
-# Retrieve similar documents based on the query string passed in
-client.similarity_search(
-    query:,
-    k:       # number of results to be retrieved
-)
-```
-```ruby
-# Retrieve similar documents based on the query string passed in via the [HyDE technique](https://arxiv.org/abs/2212.10496)
-client.similarity_search_with_hyde()
-```
-```ruby
-# Retrieve similar documents based on the embedding passed in
-client.similarity_search_by_vector(
-    embedding:,
-    k:       # number of results to be retrieved
-)
-```
-```ruby
-# Q&A-style querying based on the question passed in
-client.ask(
-    question:
-)
-```
-
-## Integrating Vector Search into ActiveRecord models
-```ruby
-class Product < ActiveRecord::Base
-  vectorsearch provider: Langchain::Vectorsearch::Qdrant.new(
-                 api_key: ENV["QDRANT_API_KEY"],
-                 url: ENV["QDRANT_URL"],
-                 index_name: "Products",
-                 llm: Langchain::LLM::GooglePalm.new(api_key: ENV["GOOGLE_PALM_API_KEY"])
-               )
+## Large Language Models (LLMs)
+Langchain.rb wraps all supported LLMs in a unified interface allowing you to easily swap out and test out different models.
 
-  after_save :upsert_to_vectorsearch
-end
-```
+#### Supported LLMs and features:
+| LLM providers                                    | embed()            | complete()         | chat()              | summarize()        | Notes              |
+| --------                                         |:------------------:| :-------:          | :-----------------: | :-------:          | :----------------- |
+| [OpenAI](https://openai.com/)                    | :white_check_mark: | :white_check_mark: | :white_check_mark:  | ❌                 | Including Azure OpenAI |
+| [AI21](https://ai21.com/)                        | ❌                 | :white_check_mark: | ❌                  | :white_check_mark: |                    |
+| [Anthropic](https://milvus.io/)                  | ❌                 | :white_check_mark: | ❌                  | ❌                 |                    |
+| [Cohere](https://www.pinecone.io/)               | :white_check_mark: | :white_check_mark: | :white_check_mark:  | :white_check_mark: |                    |
+| [GooglePalm](https://ai.google/discover/palm2/) | :white_check_mark: | :white_check_mark: | :white_check_mark:  | :white_check_mark: |                    |
+| [HuggingFace](https://huggingface.co/)          | :white_check_mark: | ❌                 | ❌                  | ❌                 |                    |
+| [Ollama](https://ollama.ai/)                     | :white_check_mark: | :white_check_mark: | ❌                  | ❌                 |                    |
+| [Replicate](https://replicate.com/)              | :white_check_mark: | :white_check_mark: | :white_check_mark:  | :white_check_mark: |                    |
 
-### Exposed ActiveRecord methods
-```ruby
-# Retrieve similar products based on the query string passed in
-Product.similarity_search(
-    query:,
-    k:       # number of results to be retrieved
-)
-```
-```ruby
-# Q&A-style querying based on the question passed in
-Product.ask(
-    question:
-)
-```
-
-Additional info [here](https://github.com/andreibondarev/langchainrb/blob/main/lib/langchain/active_record/hooks.rb#L10-L38).
-
-### Using Standalone LLMs 🗣️
-
-Add `gem "ruby-openai", "~> 4.0.0"` to your Gemfile.
+#### Using standalone LLMs:
 
 #### OpenAI
-```ruby
-openai = 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:
-```ruby
-openai = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"], llm_options: {uri_base: "http://localhost:1234"}) )
-```
-```ruby
-openai.embed(text: "foo bar")
-```
-```ruby
-openai.complete(prompt: "What is the meaning of life?")
-```
-
-##### Open AI Function calls support
-
-Conversation support
-
-```ruby
-chat = Langchain::Conversation.new(llm: openai)
-```
-```ruby
-chat.set_context("You are the climate bot")
-chat.set_functions(functions)
-```
 
-qdrant:
-
-```ruby
-client.llm.functions = functions
-```
-
-#### Azure
 Add `gem "ruby-openai", "~> 5.2.0"` to your Gemfile.
 
 ```ruby
-azure = Langchain::LLM::Azure.new(
-  api_key: ENV["AZURE_API_KEY"],
-  llm_options: {
-    api_type: :azure,
-    api_version: "2023-03-15-preview"
-  },
-  embedding_deployment_url: ENV.fetch("AZURE_EMBEDDING_URI"),
-  chat_deployment_url: ENV.fetch("AZURE_CHAT_URI")
-)
-```
-where `AZURE_EMBEDDING_URI` is e.g. `https://custom-domain.openai.azure.com/openai/deployments/gpt-35-turbo` and `AZURE_CHAT_URI` is e.g. `https://custom-domain.openai.azure.com/openai/deployments/ada-2`
-
-You can pass additional parameters to the constructor, it will be passed to the Azure client:
-```ruby
-azure = Langchain::LLM::Azure.new(
-  api_key: ENV["AZURE_API_KEY"],
-  llm_options: {
-    api_type: :azure,
-    api_version: "2023-03-15-preview",
-    request_timeout: 240 # Optional
-  },
-  embedding_deployment_url: ENV.fetch("AZURE_EMBEDDING_URI"),
-  chat_deployment_url: ENV.fetch("AZURE_CHAT_URI")
-)
-```
-```ruby
-azure.embed(text: "foo bar")
-```
-```ruby
-azure.complete(prompt: "What is the meaning of life?")
-```
-
-#### Cohere
-Add `gem "cohere-ruby", "~> 0.9.6"` to your Gemfile.
-
-```ruby
-cohere = Langchain::LLM::Cohere.new(api_key: ENV["COHERE_API_KEY"])
-```
-```ruby
-cohere.embed(text: "foo bar")
-```
-```ruby
-cohere.complete(prompt: "What is the meaning of life?")
-```
-
-#### HuggingFace
-Add `gem "hugging-face", "~> 0.3.2"` to your Gemfile.
-```ruby
-hugging_face = Langchain::LLM::HuggingFace.new(api_key: ENV["HUGGING_FACE_API_KEY"])
-```
-
-#### Replicate
-Add `gem "replicate-ruby", "~> 0.2.2"` to your Gemfile.
-```ruby
-replicate = Langchain::LLM::Replicate.new(api_key: ENV["REPLICATE_API_KEY"])
+llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
 ```
-
-#### Google PaLM (Pathways Language Model)
-Add `"google_palm_api", "~> 0.1.3"` to your Gemfile.
+You can pass additional parameters to the constructor, it will be passed to the OpenAI client:
 ```ruby
-google_palm = Langchain::LLM::GooglePalm.new(api_key: ENV["GOOGLE_PALM_API_KEY"])
+llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"], llm_options: { ... })
 ```
 
-#### AI21
-Add `gem "ai21", "~> 0.2.1"` to your Gemfile.
+Generate vector embeddings:
 ```ruby
-ai21 = Langchain::LLM::AI21.new(api_key: ENV["AI21_API_KEY"])
+llm.embed(text: "foo bar")
 ```
 
-#### Anthropic
-Add `gem "anthropic", "~> 0.1.0"` to your Gemfile.
+Generate a text completion:
 ```ruby
-anthropic = Langchain::LLM::Anthropic.new(api_key: ENV["ANTHROPIC_API_KEY"])
+llm.complete(prompt: "What is the meaning of life?")
 ```
 
+Generate a chat completion:
 ```ruby
-anthropic.complete(prompt: "What is the meaning of life?")
+llm.chat(prompt: "Hey! How are you?")
 ```
 
-#### Ollama
+Summarize the text:
 ```ruby
-ollama = Langchain::LLM::Ollama.new(url: ENV["OLLAMA_URL"])
+llm.complete(text: "...")
 ```
 
+You can use any other LLM by invoking the same interface:
 ```ruby
-ollama.complete(prompt: "What is the meaning of life?")
-```
-```ruby
-ollama.embed(text: "Hello world!")
+llm = Langchain::LLM::GooglePalm.new(...)
 ```
 
-### Using Prompts 📋
+### Prompt Management
 
 #### Prompt Templates
 
-Create a prompt with one input variable:
-
-```ruby
-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:
+Create a prompt with input variables:
 
 ```ruby
 prompt = Langchain::Prompt::PromptTemplate.new(template: "Tell me a {adjective} joke about {content}.", input_variables: ["adjective", "content"])
@@ -384,7 +188,8 @@ prompt = Langchain::Prompt.load_from_path(file_path: "spec/fixtures/prompt/promp
 prompt.input_variables #=> ["adjective", "content"]
 ```
 
-### Using Output Parsers
+
+### Output Parsers
 
 Parse LLM text responses into structured output, such as JSON.
 
@@ -484,93 +289,147 @@ fix_parser.parse(llm_response)
 
 See [here](https://github.com/andreibondarev/langchainrb/tree/main/examples/create_and_manage_prompt_templates_using_structured_output_parser.rb) for a concrete example
 
-### Using Agents 🤖
-Agents are semi-autonomous bots that can respond to user questions and use available to them Tools to provide informed replies. They break down problems into series of steps and define Actions (and Action Inputs) along the way that are executed and fed back to them as additional information. Once an Agent decides that it has the Final Answer it responds with it.
+## 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.
 
-#### ReAct Agent
+### 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.
 
-Add `gem "ruby-openai"`, `gem "eqn"`, and `gem "google_search_results"` to your Gemfile
+#### Supported vector search databases and features:
 
-```ruby
-search_tool = Langchain::Tool::GoogleSearch.new(api_key: ENV["SERPAPI_API_KEY"])
-calculator = Langchain::Tool::Calculator.new
+| Database                                         | Open-source        | Cloud offering     |
+| --------                                         |:------------------:| :------------:     |
+| [Chroma](https://trychroma.com/)                 | :white_check_mark: | :white_check_mark: |
+| [Hnswlib](https://github.com/nmslib/hnswlib/)    | :white_check_mark: | ❌                 |
+| [Milvus](https://milvus.io/)                     | :white_check_mark: | :white_check_mark: Zilliz Cloud |
+| [Pinecone](https://www.pinecone.io/)             | ❌                 | :white_check_mark: |
+| [Pgvector](https://github.com/pgvector/pgvector) | :white_check_mark: | :white_check_mark: |
+| [Qdrant](https://qdrant.tech/)                   | :white_check_mark: | :white_check_mark: |
+| [Weaviate](https://weaviate.io/)                 | :white_check_mark: | :white_check_mark: |
 
-openai = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+### Using Vector Search Databases 🔍
 
-agent = Langchain::Agent::ReActAgent.new(
-  llm: openai,
-  tools: [search_tool, calculator]
-)
-```
+Pick the vector search database you'll be using, add the gem dependency and instantiate the client:
 ```ruby
-agent.run(question: "How many full soccer fields would be needed to cover the distance between NYC and DC in a straight line?")
-#=> "Approximately 2,945 soccer fields would be needed to cover the distance between NYC and DC in a straight line."
+gem "weaviate-ruby", "~> 0.8.9"
 ```
 
-#### SQL-Query Agent
+Choose and instantiate the LLM provider you'll be using to generate embeddings
+```ruby
+llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+```
 
-Add `gem "sequel"` to your Gemfile
+```ruby
+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:
 ```ruby
-database = Langchain::Tool::Database.new(connection_string: "postgres://user:password@localhost:5432/db_name")
+client = Langchain::Vectorsearch::Chroma.new(...)   # `gem "chroma-db", "~> 0.6.0"`
+client = Langchain::Vectorsearch::Hnswlib.new(...)  # `gem "hnswlib", "~> 0.8.1"`
+client = Langchain::Vectorsearch::Milvus.new(...)   # `gem "milvus", "~> 0.9.2"`
+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"`
+```
 
-agent = Langchain::Agent::SQLQueryAgent.new(llm: Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"]), db: database)
+Create the default schema:
+```ruby
+client.create_default_schema
 ```
+
+Add plain text data to your vector search database:
 ```ruby
-agent.run(question: "How many users have a name with length greater than 5 in the users table?")
-#=> "14 users have a name with length greater than 5 in the users table."
+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."
+  ]
+)
 ```
 
-#### Demo
-![May-12-2023 13-09-13](https://github.com/andreibondarev/langchainrb/assets/541665/6bad4cd9-976c-420f-9cf9-b85bf84f7eaf)
+Or use the file parsers to load, parse and index data into your database:
+```ruby
+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")
 
-![May-12-2023 13-07-45](https://github.com/andreibondarev/langchainrb/assets/541665/9aacdcc7-4225-4ea0-ab96-7ee48826eb9b)
+client.add_data(paths: [my_pdf, my_text, my_docx])
+```
+Supported file formats: docx, html, pdf, text, json, jsonl, csv, xlsx.
 
-#### Available Tools 🛠️
+Retrieve similar documents based on the query string passed in:
+```ruby
+client.similarity_search(
+  query:,
+  k:       # number of results to be retrieved
+)
+```
 
-| 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"`                   |
-| "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"` |
-| "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"`     |
+Retrieve similar documents based on the query string passed in via the [HyDE technique](https://arxiv.org/abs/2212.10496):
+```ruby
+client.similarity_search_with_hyde()
+```
 
-#### Loaders 🚚
+Retrieve similar documents based on the embedding passed in:
+```ruby
+client.similarity_search_by_vector(
+  embedding:,
+  k:       # number of results to be retrieved
+)
+```
 
-Need to read data from various sources? Load it up.
+RAG-based querying
+```ruby
+client.ask(
+  question:
+)
+```
 
-##### Usage
+## Building chat bots
 
-Just call `Langchan::Loader.load` with the path to the file or a URL you want to load.
+### Conversation class
 
+Choose and instantiate the LLM provider you'll be using:
 ```ruby
-Langchain::Loader.load('/path/to/file.pdf')
+llm = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
 ```
-
-or
-
+Instantiate the Conversation class:
 ```ruby
-Langchain::Loader.load('https://www.example.com/file.pdf')
+chat = Langchain::Conversation.new(llm: llm)
 ```
 
-##### Supported Formats
+(Optional) Set the conversation context:
+```ruby
+chat.set_context("You are a chatbot from the future")
+```
 
+Exchange messages with the LLM
+```ruby
+chat.message("Tell me about future technologies")
+```
 
-| Format | Pocessor                     |       Gem Requirements       |
-| ------ | ---------------------------- | :--------------------------: |
-| docx   | Langchain::Processors::Docx  |   `gem "docx", "~> 0.8.0"`   |
-| html   | Langchain::Processors::HTML  | `gem "nokogiri", "~> 1.13"`  |
-| pdf    | Langchain::Processors::PDF   | `gem "pdf-reader", "~> 1.4"` |
-| text   | Langchain::Processors::Text  |                              |
-| JSON   | Langchain::Processors::JSON  |                              |
-| JSONL  | Langchain::Processors::JSONL |                              |
-| csv    | Langchain::Processors::CSV   |                              |
-| xlsx   | Langchain::Processors::Xlsx  |   `gem "roo", "~> 2.10.0"`   |
+To stream the chat response:
+```ruby
+chat = Langchain::Conversation.new(llm: llm) do |chunk|
+  print(chunk)
+end
+```
 
-## Examples
-Additional examples available: [/examples](https://github.com/andreibondarev/langchainrb/tree/main/examples)
+Open AI Functions support
+```ruby
+chat.set_functions(functions)
+```
 
 ## 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.
@@ -598,13 +457,16 @@ ragas.score(answer: "", question: "", context: "")
 # }
 ```
 
+## Examples
+Additional examples available: [/examples](https://github.com/andreibondarev/langchainrb/tree/main/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:
 
 ```ruby
-Langchain.logger.level = :info
+Langchain.logger.level = :debug
 ```
 
 ## Development
@@ -618,31 +480,6 @@ Langchain.logger.level = :info
 ## Discord
 Join us in the [Langchain.rb](https://discord.gg/WDARp7J2n8) Discord server.
 
-## Core Contributors
-[<img style="border-radius:50%" alt="Andrei Bondarev" src="https://avatars.githubusercontent.com/u/541665?v=4" width="80" height="80" class="avatar">](https://twitter.com/rushing_andrei)
-
-## Contributors
-[<img style="border-radius:50%" alt="Alex Chaplinsky" src="https://avatars.githubusercontent.com/u/695947?v=4" width="80" height="80" class="avatar">](https://github.com/alchaplinsky)
-[<img style="border-radius:50%" alt="Josh Nichols" src="https://avatars.githubusercontent.com/u/159?v=4" width="80" height="80" class="avatar">](https://github.com/technicalpickles)
-[<img style="border-radius:50%" alt="Matt Lindsey" src="https://avatars.githubusercontent.com/u/5638339?v=4" width="80" height="80" class="avatar">](https://github.com/mattlindsey)
-[<img style="border-radius:50%" alt="Ricky Chilcott" src="https://avatars.githubusercontent.com/u/445759?v=4" width="80" height="80" class="avatar">](https://github.com/rickychilcott)
-[<img style="border-radius:50%" alt="Moeki Kawakami" src="https://avatars.githubusercontent.com/u/72325947?v=4" width="80" height="80" class="avatar">](https://github.com/moekidev)
-[<img style="border-radius:50%" alt="Jens Stmrs" src="https://avatars.githubusercontent.com/u/3492669?v=4" width="80" height="80" class="avatar">](https://github.com/faustus7)
-[<img style="border-radius:50%" alt="Rafael Figueiredo" src="https://avatars.githubusercontent.com/u/35845775?v=4" width="80" height="80" class="avatar">](https://github.com/rafaelqfigueiredo)
-[<img style="border-radius:50%" alt="Piero Dotti" src="https://avatars.githubusercontent.com/u/5167659?v=4" width="80" height="80" class="avatar">](https://github.com/ProGM)
-[<img style="border-radius:50%" alt="Michał Ciemięga" src="https://avatars.githubusercontent.com/u/389828?v=4" width="80" height="80" class="avatar">](https://github.com/zewelor)
-[<img style="border-radius:50%" alt="Bruno Bornsztein" src="https://avatars.githubusercontent.com/u/3760?v=4" width="80" height="80" class="avatar">](https://github.com/bborn)
-[<img style="border-radius:50%" alt="Tim Williams" src="https://avatars.githubusercontent.com/u/1192351?v=4" width="80" height="80" class="avatar">](https://github.com/timrwilliams)
-[<img style="border-radius:50%" alt="Zhenhang Tung" src="https://avatars.githubusercontent.com/u/8170159?v=4" width="80" height="80" class="avatar">](https://github.com/ZhenhangTung)
-[<img style="border-radius:50%" alt="Hama" src="https://avatars.githubusercontent.com/u/38002468?v=4" width="80" height="80" class="avatar">](https://github.com/akmhmgc)
-[<img style="border-radius:50%" alt="Josh Weir" src="https://avatars.githubusercontent.com/u/10720337?v=4" width="80" height="80" class="avatar">](https://github.com/joshweir)
-[<img style="border-radius:50%" alt="Arthur Hess" src="https://avatars.githubusercontent.com/u/446035?v=4" width="80" height="80" class="avatar">](https://github.com/arthurhess)
-[<img style="border-radius:50%" alt="Jin Shen" src="https://avatars.githubusercontent.com/u/54917718?v=4" width="80" height="80" class="avatar">](https://github.com/jacshen-ebay)
-[<img style="border-radius:50%" alt="Earle Bunao" src="https://avatars.githubusercontent.com/u/4653624?v=4" width="80" height="80" class="avatar">](https://github.com/erbunao)
-[<img style="border-radius:50%" alt="Maël H." src="https://avatars.githubusercontent.com/u/61985678?v=4" width="80" height="80" class="avatar">](https://github.com/mael-ha)
-[<img style="border-radius:50%" alt="Chris O. Adebiyi" src="https://avatars.githubusercontent.com/u/62605573?v=4" width="80" height="80" class="avatar">](https://github.com/oluvvafemi)
-[<img style="border-radius:50%" alt="Aaron Breckenridge" src="https://avatars.githubusercontent.com/u/201360?v=4" width="80" height="80" class="avatar">](https://github.com/breckenedge)
-
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=andreibondarev/langchainrb&type=Date)](https://star-history.com/#andreibondarev/langchainrb&Date)

data/lib/langchain/agent/agents.md

@@ -0,0 +1,54 @@
+
+### Agents 🤖
+Agents are semi-autonomous bots that can respond to user questions and use available to them Tools to provide informed replies. They break down problems into series of steps and define Actions (and Action Inputs) along the way that are executed and fed back to them as additional information. Once an Agent decides that it has the Final Answer it responds with it.
+
+#### ReAct Agent
+
+Add `gem "ruby-openai"`, `gem "eqn"`, and `gem "google_search_results"` to your Gemfile
+
+```ruby
+search_tool = Langchain::Tool::GoogleSearch.new(api_key: ENV["SERPAPI_API_KEY"])
+calculator = Langchain::Tool::Calculator.new
+
+openai = Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"])
+
+agent = Langchain::Agent::ReActAgent.new(
+  llm: openai,
+  tools: [search_tool, calculator]
+)
+```
+```ruby
+agent.run(question: "How many full soccer fields would be needed to cover the distance between NYC and DC in a straight line?")
+#=> "Approximately 2,945 soccer fields would be needed to cover the distance between NYC and DC in a straight line."
+```
+
+#### SQL-Query Agent
+
+Add `gem "sequel"` to your Gemfile
+
+```ruby
+database = Langchain::Tool::Database.new(connection_string: "postgres://user:password@localhost:5432/db_name")
+
+agent = Langchain::Agent::SQLQueryAgent.new(llm: Langchain::LLM::OpenAI.new(api_key: ENV["OPENAI_API_KEY"]), db: database)
+```
+```ruby
+agent.run(question: "How many users have a name with length greater than 5 in the users table?")
+#=> "14 users have a name with length greater than 5 in the users table."
+```
+
+#### Demo
+![May-12-2023 13-09-13](https://github.com/andreibondarev/langchainrb/assets/541665/6bad4cd9-976c-420f-9cf9-b85bf84f7eaf)
+
+![May-12-2023 13-07-45](https://github.com/andreibondarev/langchainrb/assets/541665/9aacdcc7-4225-4ea0-ab96-7ee48826eb9b)
+
+#### 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"`                   |
+| "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"` |
+| "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"`     |
+

data/lib/langchain/evals/ragas/{critique.rb → aspect_critique.rb}

@@ -4,7 +4,7 @@ module Langchain
   module Evals
     module Ragas
       # 123
-      class Critique
+      class AspectCritique
         attr_reader :llm, :criterias
 
         CRITERIAS = {
@@ -53,7 +53,7 @@ module Langchain
         # @return [PromptTemplate] PromptTemplate instance
         def critique_prompt_template
           @template_one ||= Langchain::Prompt.load_from_path(
-            file_path: Langchain.root.join("langchain/evals/ragas/prompts/critique.yml")
+            file_path: Langchain.root.join("langchain/evals/ragas/prompts/aspect_critique.yml")
           )
         end
       end

data/lib/langchain/llm/openai.rb

@@ -4,7 +4,7 @@ module Langchain::LLM
   # LLM interface for OpenAI APIs: https://platform.openai.com/overview
   #
   # Gem requirements:
-  #    gem "ruby-openai", "~> 4.0.0"
+  #    gem "ruby-openai", "~> 5.2.0"
   #
   # Usage:
   #    openai = Langchain::LLM::OpenAI.new(api_key:, llm_options: {})

data/lib/langchain/llm/response/base_response.rb

@@ -5,6 +5,9 @@ module Langchain
     class BaseResponse
       attr_reader :raw_response, :model
 
+      # Save context in the response when doing RAG workflow vectorsearch#ask()
+      attr_accessor :context
+
       def initialize(raw_response, model: nil)
         @raw_response = raw_response
         @model = model

data/lib/langchain/prompt/loading.rb

@@ -33,7 +33,7 @@ module Langchain::Prompt
         when ".json"
           config = JSON.parse(File.read(file_path))
         when ".yaml", ".yml"
-          config = YAML.safe_load(File.read(file_path))
+          config = YAML.safe_load_file(file_path)
         else
           raise ArgumentError, "Got unsupported file type #{file_path.extname}"
         end

data/lib/langchain/utils/token_length/ai21_validator.rb

@@ -30,6 +30,7 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS[model_name]
         end
+        singleton_class.alias_method :completion_token_limit, :token_limit
       end
     end
   end

data/lib/langchain/utils/token_length/base_validator.rb

@@ -20,6 +20,9 @@ module Langchain
           end
 
           leftover_tokens = token_limit(model_name) - text_token_length
+          # Some models have a separate token limit for completion (e.g. GPT-4 Turbo)
+          # We want the lower of the two limits
+          leftover_tokens = [leftover_tokens, completion_token_limit(model_name)].min
 
           # Raise an error even if whole prompt is equal to the model's token limit (leftover_tokens == 0)
           if leftover_tokens < 0

data/lib/langchain/utils/token_length/cohere_validator.rb

@@ -38,6 +38,7 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS[model_name]
         end
+        singleton_class.alias_method :completion_token_limit, :token_limit
       end
     end
   end

data/lib/langchain/utils/token_length/google_palm_validator.rb

@@ -46,6 +46,7 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS.dig(model_name, "input_token_limit")
         end
+        singleton_class.alias_method :completion_token_limit, :token_limit
       end
     end
   end

data/lib/langchain/utils/token_length/openai_validator.rb

@@ -10,6 +10,14 @@ module Langchain
       # It is used to validate the token length before the API call is made
       #
       class OpenAIValidator < BaseValidator
+        COMPLETION_TOKEN_LIMITS = {
+          # GPT-4 Turbo has a separate token limit for completion
+          # Source:
+          # https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
+          "gpt-4-1106-preview" => 4096,
+          "gpt-4-vision-preview" => 4096
+        }
+
         TOKEN_LIMITS = {
           # Source:
           # https://platform.openai.com/docs/api-reference/embeddings
@@ -29,6 +37,8 @@ module Langchain
           "gpt-4-32k" => 32768,
           "gpt-4-32k-0314" => 32768,
           "gpt-4-32k-0613" => 32768,
+          "gpt-4-1106-preview" => 128000,
+          "gpt-4-vision-preview" => 128000,
           "text-curie-001" => 2049,
           "text-babbage-001" => 2049,
           "text-ada-001" => 2049,
@@ -53,6 +63,10 @@ module Langchain
         def self.token_limit(model_name)
           TOKEN_LIMITS[model_name]
         end
+
+        def self.completion_token_limit(model_name)
+          COMPLETION_TOKEN_LIMITS[model_name] || token_limit(model_name)
+        end
       end
     end
   end

data/lib/langchain/vectorsearch/chroma.rb

@@ -126,7 +126,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
 
     private

data/lib/langchain/vectorsearch/milvus.rb

@@ -151,7 +151,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
   end
 end

data/lib/langchain/vectorsearch/pgvector.rb

@@ -148,7 +148,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
   end
 end

data/lib/langchain/vectorsearch/pinecone.rb

@@ -180,7 +180,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
 
     # Pinecone index

data/lib/langchain/vectorsearch/qdrant.rb

@@ -137,7 +137,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
   end
 end

data/lib/langchain/vectorsearch/weaviate.rb

@@ -6,7 +6,7 @@ module Langchain::Vectorsearch
     # Wrapper around Weaviate
     #
     # Gem requirements:
-    #     gem "weaviate-ruby", "~> 0.8.3"
+    #     gem "weaviate-ruby", "~> 0.8.9"
     #
     # Usage:
     #     weaviate = Langchain::Vectorsearch::Weaviate.new(url:, api_key:, index_name:, llm:)
@@ -137,7 +137,9 @@ module Langchain::Vectorsearch
 
       prompt = generate_rag_prompt(question: question, context: context)
 
-      llm.chat(prompt: prompt, &block)
+      response = llm.chat(prompt: prompt, &block)
+      response.context = context
+      response
     end
 
     private

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.7.2"
+  VERSION = "0.7.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.7.3
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-11-02 00:00:00.000000000 Z
+date: 2023-11-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: baran
@@ -567,6 +567,7 @@ files:
 - LICENSE.txt
 - README.md
 - lib/langchain.rb
+- lib/langchain/agent/agents.md
 - lib/langchain/agent/base.rb
 - lib/langchain/agent/react_agent.rb
 - lib/langchain/agent/react_agent/react_agent_prompt.yaml
@@ -590,13 +591,13 @@ files:
 - lib/langchain/data.rb
 - lib/langchain/dependency_helper.rb
 - lib/langchain/evals/ragas/answer_relevance.rb
+- lib/langchain/evals/ragas/aspect_critique.rb
 - lib/langchain/evals/ragas/context_relevance.rb
-- lib/langchain/evals/ragas/critique.rb
 - lib/langchain/evals/ragas/faithfulness.rb
 - lib/langchain/evals/ragas/main.rb
 - lib/langchain/evals/ragas/prompts/answer_relevance.yml
+- lib/langchain/evals/ragas/prompts/aspect_critique.yml
 - lib/langchain/evals/ragas/prompts/context_relevance.yml
-- lib/langchain/evals/ragas/prompts/critique.yml
 - lib/langchain/evals/ragas/prompts/faithfulness_statements_extraction.yml
 - lib/langchain/evals/ragas/prompts/faithfulness_statements_verification.yml
 - lib/langchain/llm/ai21.rb