adding performance config option to the AWS ChatBedrock component (#4777)
* adding performance config option to the AWS ChatBedrock component * Update AWSChatBedrock.ts * Update pnpm-lock.yaml --------- Co-authored-by: Henry Heng <henryheng@flowiseai.com>
This commit is contained in:
parent
bbf6970600
commit
0627693133
|
|
@ -23,7 +23,7 @@ class AWSChatBedrock_ChatModels implements INode {
|
||||||
constructor() {
|
constructor() {
|
||||||
this.label = 'AWS ChatBedrock'
|
this.label = 'AWS ChatBedrock'
|
||||||
this.name = 'awsChatBedrock'
|
this.name = 'awsChatBedrock'
|
||||||
this.version = 6.0
|
this.version = 6.1
|
||||||
this.type = 'AWSChatBedrock'
|
this.type = 'AWSChatBedrock'
|
||||||
this.icon = 'aws.svg'
|
this.icon = 'aws.svg'
|
||||||
this.category = 'Chat Models'
|
this.category = 'Chat Models'
|
||||||
|
|
@ -100,6 +100,16 @@ class AWSChatBedrock_ChatModels implements INode {
|
||||||
'Allow image input. Refer to the <a href="https://docs.flowiseai.com/using-flowise/uploads#image" target="_blank">docs</a> for more details.',
|
'Allow image input. Refer to the <a href="https://docs.flowiseai.com/using-flowise/uploads#image" target="_blank">docs</a> for more details.',
|
||||||
default: false,
|
default: false,
|
||||||
optional: true
|
optional: true
|
||||||
|
},
|
||||||
|
{
|
||||||
|
label: 'Latency Optimized',
|
||||||
|
name: 'latencyOptimized',
|
||||||
|
type: 'boolean',
|
||||||
|
description:
|
||||||
|
'Enable latency optimized configuration for supported models. Refer to the supported <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/latency-optimized-inference.html" target="_blank">latecny optimized models</a> for more details.',
|
||||||
|
default: false,
|
||||||
|
optional: true,
|
||||||
|
additionalParams: true
|
||||||
}
|
}
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
|
|
@ -122,6 +132,7 @@ class AWSChatBedrock_ChatModels implements INode {
|
||||||
const iMax_tokens_to_sample = nodeData.inputs?.max_tokens_to_sample as string
|
const iMax_tokens_to_sample = nodeData.inputs?.max_tokens_to_sample as string
|
||||||
const cache = nodeData.inputs?.cache as BaseCache
|
const cache = nodeData.inputs?.cache as BaseCache
|
||||||
const streaming = nodeData.inputs?.streaming as boolean
|
const streaming = nodeData.inputs?.streaming as boolean
|
||||||
|
const latencyOptimized = nodeData.inputs?.latencyOptimized as boolean
|
||||||
|
|
||||||
const obj: ChatBedrockConverseInput = {
|
const obj: ChatBedrockConverseInput = {
|
||||||
region: iRegion,
|
region: iRegion,
|
||||||
|
|
@ -131,6 +142,10 @@ class AWSChatBedrock_ChatModels implements INode {
|
||||||
streaming: streaming ?? true
|
streaming: streaming ?? true
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if (latencyOptimized) {
|
||||||
|
obj.performanceConfig = { latency: 'optimized' }
|
||||||
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Long-term credentials specified in LLM configuration are optional.
|
* Long-term credentials specified in LLM configuration are optional.
|
||||||
* Bedrock's credential provider falls back to the AWS SDK to fetch
|
* Bedrock's credential provider falls back to the AWS SDK to fetch
|
||||||
|
|
|
||||||
|
|
@ -38,7 +38,7 @@
|
||||||
"@google/generative-ai": "^0.24.0",
|
"@google/generative-ai": "^0.24.0",
|
||||||
"@huggingface/inference": "^2.6.1",
|
"@huggingface/inference": "^2.6.1",
|
||||||
"@langchain/anthropic": "0.3.14",
|
"@langchain/anthropic": "0.3.14",
|
||||||
"@langchain/aws": "0.1.4",
|
"@langchain/aws": "^0.1.11",
|
||||||
"@langchain/baidu-qianfan": "^0.1.0",
|
"@langchain/baidu-qianfan": "^0.1.0",
|
||||||
"@langchain/cohere": "^0.0.7",
|
"@langchain/cohere": "^0.0.7",
|
||||||
"@langchain/community": "^0.3.29",
|
"@langchain/community": "^0.3.29",
|
||||||
|
|
|
||||||
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue