mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-19 14:01:50 +00:00
cab55e9bc1
- chat vertex async - vertex stream - vertex full generation info - vertex use server-side stopping - model garden async - update docs for all the above in follow up will add [] chat vertex full generation info [] chat vertex retries [] scheduled tests
37 lines
1.2 KiB
Plaintext
37 lines
1.2 KiB
Plaintext
---
|
|
sidebar_position: 1
|
|
sidebar_class_name: hidden
|
|
---
|
|
|
|
# Chat models
|
|
|
|
import DocCardList from "@theme/DocCardList";
|
|
|
|
## Features (natively supported)
|
|
All `ChatModel`s implement the LCEL `Runnable` interface, meaning they all expose functioning `invoke`, `ainvoke`, `stream`, and `astream` (and `batch`, `abatch`) methods.
|
|
*That is, they all have functioning sync, async and streaming generation methods.*
|
|
|
|
This table highlights specifically those integrations that **natively support** streaming and asynchronous generation (meaning these features are built into the 3rd-party integration).
|
|
|
|
Model|Generate|Async generate|Stream|Async stream
|
|
:-|:-:|:-:|:-:|:-:
|
|
AzureChatOpenAI|✅|✅|✅|✅
|
|
BedrockChat|✅|❌|✅|❌
|
|
ChatAnthropic|✅|✅|✅|✅
|
|
ChatAnyscale|✅|✅|✅|✅
|
|
ChatGooglePalm|✅|✅|❌|❌
|
|
ChatJavelinAIGateway|✅|✅|❌|❌
|
|
ChatKonko|✅|❌|❌|❌
|
|
ChatLiteLLM|✅|✅|✅|✅
|
|
ChatMLflowAIGateway|✅|❌|❌|❌
|
|
ChatOllama|✅|❌|✅|❌
|
|
ChatOpenAI|✅|✅|✅|✅
|
|
ChatVertexAI|✅|✅|✅|❌
|
|
ErnieBotChat|✅|❌|❌|❌
|
|
JinaChat|✅|✅|✅|✅
|
|
MiniMaxChat|✅|✅|❌|❌
|
|
PromptLayerChatOpenAI|✅|❌|❌|❌
|
|
QianfanChatEndpoint|✅|✅|✅|✅
|
|
|
|
<DocCardList />
|