Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Python agentagentic-aiagentic-frameworkagentic-workflowaiautomationclaudedeepseekgenaigptllmlow-codemcpnextjsno-codeopenaipythonskillsworkflow
app:
description: 'Workflow with LLM node for testing auto-mock'
icon: 🤖
icon_background: '#FFEAD5'
mode: workflow
name: llm-simple
use_icon_as_answer_icon: false
dependencies: []
kind: app
version: 0.3.1
workflow:
conversation_variables: []
environment_variables: []
features:
file_upload:
enabled: false
opening_statement: ''
retriever_resource:
enabled: false
sensitive_word_avoidance:
enabled: false
speech_to_text:
enabled: false
suggested_questions: []
suggested_questions_after_answer:
enabled: false
text_to_speech:
enabled: false
graph:
edges:
- data:
isInIteration: false
isInLoop: false
sourceType: start
targetType: llm
id: start-to-llm
source: 'start_node'
sourceHandle: source
target: 'llm_node'
targetHandle: target
type: custom
zIndex: 0
- data:
isInIteration: false
isInLoop: false
sourceType: llm
targetType: end
id: llm-to-end
source: 'llm_node'
sourceHandle: source
target: 'end_node'
targetHandle: target
type: custom
zIndex: 0
nodes:
- data:
desc: ''
selected: false
title: Start
type: start
variables:
- label: query
max_length: null
options: []
required: true
type: text-input
variable: query
height: 90
id: 'start_node'
position:
x: 30
y: 227
positionAbsolute:
x: 30
y: 227
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
desc: 'LLM Node for testing'
title: LLM
type: llm
model:
provider: openai
name: gpt-3.5-turbo
mode: chat
prompt_template:
- role: system
text: You are a helpful assistant.
- role: user
text: '{{#start_node.query#}}'
vision:
enabled: false
configs:
variable_selector: []
memory:
enabled: false
window:
enabled: false
size: 50
context:
enabled: false
variable_selector: []
structured_output:
enabled: false
retry_config:
enabled: false
max_retries: 1
retry_interval: 1000
exponential_backoff:
enabled: false
multiplier: 2
max_interval: 10000
height: 90
id: 'llm_node'
position:
x: 334
y: 227
positionAbsolute:
x: 334
y: 227
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
- data:
desc: ''
outputs:
- value_selector:
- 'llm_node'
- text
value_type: string
variable: answer
selected: false
title: End
type: end
height: 90
id: 'end_node'
position:
x: 638
y: 227
positionAbsolute:
x: 638
y: 227
selected: false
sourcePosition: right
targetPosition: left
type: custom
width: 244
viewport:
x: 0
y: 0
zoom: 0.7