docs: installation nits (#24484)

This commit is contained in:
Bagatur 2024-09-02 18:05:08 -07:00 committed by GitHub
parent 4833375200
commit f872c50b3f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 29 additions and 14 deletions

View File

@ -9,7 +9,7 @@ functionality to install.
## Official release
To install the main LangChain package, run:
To install the main `langchain` package, run:
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
@ -26,8 +26,7 @@ import CodeBlock from "@theme/CodeBlock";
While this package acts as a sane starting point to using LangChain,
much of the value of LangChain comes when integrating it with various model providers, datastores, etc.
By default, the dependencies needed to do that are NOT installed. You will need to install the dependencies for specific integrations separately.
We'll show how to do that in the next sections of this guide.
By default, the dependencies needed to do that are NOT installed. You will need to install the dependencies for specific integrations separately, which we show below.
## Ecosystem packages
@ -41,14 +40,6 @@ When installing a package, you do not need to explicitly install that package's
However, you may choose to if you are using a feature only available in a certain version of that dependency.
If you do, you should make sure that the installed or pinned version is compatible with any other integration packages you use.
### From source
If you want to install from source, you can do so by cloning the repo and be sure that the directory is `PATH/TO/REPO/langchain/libs/langchain` running:
```bash
pip install -e .
```
### LangChain core
The `langchain-core` package contains base abstractions that the rest of the LangChain ecosystem uses, along with the LangChain Expression Language. It is automatically installed by `langchain`, but can also be used separately. Install with:
@ -56,8 +47,18 @@ The `langchain-core` package contains base abstractions that the rest of the Lan
pip install langchain-core
```
### LangChain community
The `langchain-community` package contains third-party integrations. Install with:
### Integration packages
Certain integrations like OpenAI and Anthropic have their own packages.
Any integrations that require their own package will be documented as such in the [Integration docs](/docs/integrations/platforms/).
You can see a list of all integration packages in the [API reference](https://api.python.langchain.com) under the "Partner libs" dropdown.
To install one of these run:
```bash
pip install langchain-openai
```
Any integrations that haven't been split out into their own packages will live in the `langchain-community` package. Install with:
```bash
pip install langchain-community
@ -89,7 +90,7 @@ pip install "langserve[all]"
```
for both client and server dependencies. Or `pip install "langserve[client]"` for client code, and `pip install "langserve[server]"` for server code.
## LangChain CLI
### LangChain CLI
The LangChain CLI is useful for working with LangChain templates and other LangServe projects.
Install with:
@ -105,3 +106,13 @@ If you are not using LangChain, you can install it with:
```bash
pip install langsmith
```
### From source
If you want to install a package from source, you can do so by cloning the [main LangChain repo](https://github.com/langchain-ai/langchain), enter the directory of the package you want to install `PATH/TO/REPO/langchain/libs/{package}`, and run:
```bash
pip install -e .
```
LangGraph, LangSmith SDK, and certain integration packages live outside the main LangChain repo. You can see [all repos here](https://github.com/langchain-ai).

View File

@ -4,6 +4,10 @@
"ignoreCommand": "bash ignore-step.sh",
"trailingSlash": true,
"rewrites": [
{
"source": "/v0.2/docs/integrations(/?)",
"destination": "/v0.2/docs/integrations/platforms/"
},
{
"source": "/v0.1",
"destination": "https://langchain-v01.vercel.app/v0.1"