diff --git a/README.md b/README.md index 511d6e307205..fffd119c9aab 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ ⚡ Building applications with LLMs through composability ⚡ -[![CI](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml/badge.svg)](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml) ![npm](https://img.shields.io/npm/dm/langchain) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs) + ![npm](https://img.shields.io/npm/dm/langchain) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs) [](https://codespaces.new/langchain-ai/langchainjs) Looking for the Python version? Check out [LangChain](https://github.com/langchain-ai/langchain). @@ -43,15 +43,13 @@ This framework consists of several parts. The LangChain libraries themselves are made up of several different packages. -- **[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions and LangChain Expression Language. +- **[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions. - **[`@langchain/community`](https://github.com/langchain-ai/langchainjs/blob/main/libs/langchain-community)**: Third party integrations. - **[`langchain`](https://github.com/langchain-ai/langchainjs/blob/main/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture. - **[LangGraph.js](https://langchain-ai.github.io/langgraphjs/)**: LangGraph powers production-grade agents, trusted by Linkedin, Uber, Klarna, GitLab, and many more. Build robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it. Integrations may also be split into their own compatible packages. -![LangChain Stack](https://github.com/langchain-ai/langchainjs/blob/main/docs/core_docs/static/svg/langchain_stack_062024.svg) - This library aims to assist in the development of those types of applications. Common examples of these applications include: **❓Question Answering over specific documents** diff --git a/langchain-core/README.md b/langchain-core/README.md index 40ea1f730e47..d63669067142 100644 --- a/langchain-core/README.md +++ b/langchain-core/README.md @@ -1,6 +1,6 @@ # 🦜🍎️ @langchain/core -[![CI](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml/badge.svg)](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml) ![npm](https://img.shields.io/npm/dm/@langchain/core) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) +![npm](https://img.shields.io/npm/dm/@langchain/core) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) `@langchain/core` contains the core abstractions and schemas of LangChain.js, including base classes for language models, chat models, vectorstores, retrievers, and runnables. @@ -8,7 +8,7 @@ chat models, vectorstores, retrievers, and runnables. ## 💾 Quick Install ```bash -$ yarn add @langchain/core +yarn add @langchain/core ``` ## 🤔 What is this? @@ -21,7 +21,7 @@ The benefit of having these abstractions is that any provider can implement the For example, you can install other provider-specific packages like this: ```bash -$ yarn add @langchain/openai +yarn add @langchain/openai ``` And use them as follows: @@ -72,22 +72,6 @@ leigh Note that for compatibility, all used LangChain packages (including the base LangChain package, which itself depends on core!) must share the same version of `@langchain/core`. This means that you may need to install/resolve a specific version of `@langchain/core` that matches the dependencies of your used packages. -## 🔗 What is LangChain Expression Language? - -LangChain Core also contains LangChain Expression Language, or LCEL, a runtime that allows users to compose arbitrary sequences together and get several benefits that are important when building LLM applications. -We call these sequences “runnables”. - -All runnables expose the same interface with single-invocation, batch, streaming and async methods. -This design is useful because it is not enough to have a single sync interface when building an LLM application. -Batch is needed for efficient processing of many inputs. -Streaming (and streaming of intermediate steps) is needed to show the user that progress is being made. -Async interfaces are nice when moving into production. -Rather than having to write multiple implementations for all of those, LCEL allows you to write a runnable once and invoke it in many different ways. - -For more check out the [LCEL docs](https://js.langchain.com/docs/concepts/lcel). - -![LangChain Stack](../docs/core_docs/static/svg/langchain_stack_062024.svg) - ## 📕 Releases & Versioning `@langchain/core` is currently on version `0.3.x`. diff --git a/langchain/README.md b/langchain/README.md index 511d6e307205..f0e1d4867e28 100644 --- a/langchain/README.md +++ b/langchain/README.md @@ -2,7 +2,7 @@ ⚡ Building applications with LLMs through composability ⚡ -[![CI](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml/badge.svg)](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml) ![npm](https://img.shields.io/npm/dm/langchain) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs) +[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) ![npm](https://img.shields.io/npm/dm/langchain) [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai) [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs) [](https://codespaces.new/langchain-ai/langchainjs) Looking for the Python version? Check out [LangChain](https://github.com/langchain-ai/langchain). @@ -43,15 +43,13 @@ This framework consists of several parts. The LangChain libraries themselves are made up of several different packages. -- **[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions and LangChain Expression Language. +- **[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions. - **[`@langchain/community`](https://github.com/langchain-ai/langchainjs/blob/main/libs/langchain-community)**: Third party integrations. - **[`langchain`](https://github.com/langchain-ai/langchainjs/blob/main/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture. - **[LangGraph.js](https://langchain-ai.github.io/langgraphjs/)**: LangGraph powers production-grade agents, trusted by Linkedin, Uber, Klarna, GitLab, and many more. Build robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it. Integrations may also be split into their own compatible packages. -![LangChain Stack](https://github.com/langchain-ai/langchainjs/blob/main/docs/core_docs/static/svg/langchain_stack_062024.svg) - This library aims to assist in the development of those types of applications. Common examples of these applications include: **❓Question Answering over specific documents**