You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+2-4Lines changed: 2 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
⚡ Building applications with LLMs through composability ⚡
4
4
5
-
[](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml)[](https://opensource.org/licenses/MIT)[](https://twitter.com/langchainai)[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs)
5
+
[](https://opensource.org/licenses/MIT)[](https://twitter.com/langchainai)[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs)
6
6
[<imgsrc="https://github.com/codespaces/badge.svg"title="Open in Github Codespace"width="150"height="20">](https://codespaces.new/langchain-ai/langchainjs)
7
7
8
8
Looking for the Python version? Check out [LangChain](https://github.com/langchain-ai/langchain).
@@ -43,15 +43,13 @@ This framework consists of several parts.
43
43
44
44
The LangChain libraries themselves are made up of several different packages.
45
45
46
-
-**[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions and LangChain Expression Language.
46
+
-**[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions.
47
47
-**[`@langchain/community`](https://github.com/langchain-ai/langchainjs/blob/main/libs/langchain-community)**: Third party integrations.
48
48
-**[`langchain`](https://github.com/langchain-ai/langchainjs/blob/main/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
49
49
-**[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.
50
50
51
51
Integrations may also be split into their own compatible packages.
`@langchain/core` contains the core abstractions and schemas of LangChain.js, including base classes for language models,
6
6
chat models, vectorstores, retrievers, and runnables.
7
7
8
8
## 💾 Quick Install
9
9
10
10
```bash
11
-
$ yarn add @langchain/core
11
+
yarn add @langchain/core
12
12
```
13
13
14
14
## 🤔 What is this?
@@ -21,7 +21,7 @@ The benefit of having these abstractions is that any provider can implement the
21
21
For example, you can install other provider-specific packages like this:
22
22
23
23
```bash
24
-
$ yarn add @langchain/openai
24
+
yarn add @langchain/openai
25
25
```
26
26
27
27
And use them as follows:
@@ -72,22 +72,6 @@ leigh
72
72
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`.
73
73
This means that you may need to install/resolve a specific version of `@langchain/core` that matches the dependencies of your used packages.
74
74
75
-
## 🔗 What is LangChain Expression Language?
76
-
77
-
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.
78
-
We call these sequences “runnables”.
79
-
80
-
All runnables expose the same interface with single-invocation, batch, streaming and async methods.
81
-
This design is useful because it is not enough to have a single sync interface when building an LLM application.
82
-
Batch is needed for efficient processing of many inputs.
83
-
Streaming (and streaming of intermediate steps) is needed to show the user that progress is being made.
84
-
Async interfaces are nice when moving into production.
85
-
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.
86
-
87
-
For more check out the [LCEL docs](https://js.langchain.com/docs/concepts/lcel).
Copy file name to clipboardExpand all lines: langchain/README.md
+2-4Lines changed: 2 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
⚡ Building applications with LLMs through composability ⚡
4
4
5
-
[](https://github.com/langchain-ai/langchainjs/actions/workflows/ci.yml)[](https://opensource.org/licenses/MIT)[](https://twitter.com/langchainai)[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs)
5
+
[](https://opensource.org/licenses/MIT)[](https://twitter.com/langchainai)[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchainjs)
6
6
[<imgsrc="https://github.com/codespaces/badge.svg"title="Open in Github Codespace"width="150"height="20">](https://codespaces.new/langchain-ai/langchainjs)
7
7
8
8
Looking for the Python version? Check out [LangChain](https://github.com/langchain-ai/langchain).
@@ -43,15 +43,13 @@ This framework consists of several parts.
43
43
44
44
The LangChain libraries themselves are made up of several different packages.
45
45
46
-
-**[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions and LangChain Expression Language.
46
+
-**[`@langchain/core`](https://github.com/langchain-ai/langchainjs/blob/main/langchain-core)**: Base abstractions.
47
47
-**[`@langchain/community`](https://github.com/langchain-ai/langchainjs/blob/main/libs/langchain-community)**: Third party integrations.
48
48
-**[`langchain`](https://github.com/langchain-ai/langchainjs/blob/main/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
49
49
-**[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.
50
50
51
51
Integrations may also be split into their own compatible packages.
0 commit comments