mirror of https://github.com/hwchase17/langchain
docs: updated `Anyscale` page (#16107)
- added description - fixed broken links - added setting instructions - added the Chat model referencepull/16116/head
parent
4df14a61fc
commit
f974eb5b8b
@ -1,17 +1,34 @@
|
||||
# Anyscale
|
||||
|
||||
This page covers how to use the Anyscale ecosystem within LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific Anyscale wrappers.
|
||||
>[Anyscale](https://www.anyscale.com) is a platform to run, fine tune and scale LLMs via production-ready APIs.
|
||||
> [Anyscale Endpoints](https://docs.anyscale.com/endpoints/overview) serve many open-source models in a cost-effective way.
|
||||
|
||||
`Anyscale` also provides [an example](https://docs.anyscale.com/endpoints/model-serving/examples/langchain-integration)
|
||||
how to setup `LangChain` with `Anyscale` for advanced chat agents.
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
- Get an Anyscale Service URL, route and API key and set them as environment variables (`ANYSCALE_SERVICE_URL`,`ANYSCALE_SERVICE_ROUTE`, `ANYSCALE_SERVICE_TOKEN`).
|
||||
- Please see [the Anyscale docs](https://docs.anyscale.com/productionize/services-v2/get-started) for more details.
|
||||
- Please see [the Anyscale docs](https://www.anyscale.com/get-started) for more details.
|
||||
|
||||
We have to install the `openai` package:
|
||||
|
||||
```bash
|
||||
pip install openai
|
||||
```
|
||||
|
||||
## LLM
|
||||
|
||||
See a [usage example](/docs/integrations/llms/anyscale).
|
||||
|
||||
```python
|
||||
from langchain_community.llms.anyscale import Anyscale
|
||||
```
|
||||
|
||||
## Wrappers
|
||||
## Chat Models
|
||||
|
||||
### LLM
|
||||
See a [usage example](/docs/integrations/chat/anyscale).
|
||||
|
||||
There exists an Anyscale LLM wrapper, which you can access with
|
||||
```python
|
||||
from langchain_community.llms import Anyscale
|
||||
from langchain_community.chat_models.anyscale import ChatAnyscale
|
||||
```
|
||||
|
Loading…
Reference in New Issue