Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Hermes Pipeline
|
a2433251cd |
@@ -0,0 +1,81 @@
|
||||
---
|
||||
name: conditional-request-routing-workflow
|
||||
version: 1.0.0
|
||||
description: Collect a request, classify it via branching logic, and route to an approval
|
||||
or rejection handler to produce a final result
|
||||
inputs:
|
||||
- name: request
|
||||
type: string
|
||||
description: The input text or request to be evaluated and routed
|
||||
steps:
|
||||
- node: Start
|
||||
agent_type: input
|
||||
description: Prompt user and capture the request into state field 'request'
|
||||
next: Classify
|
||||
- node: Classify
|
||||
agent_type: branching
|
||||
description: Evaluate the request and set 'decision' field, routing to Approve on
|
||||
success or Reject on failure
|
||||
input_fields:
|
||||
- request
|
||||
output_field: decision
|
||||
next_node: Approve
|
||||
on_failure: Reject
|
||||
- node: Approve
|
||||
agent_type: default
|
||||
description: Format and output an approval message containing the request
|
||||
input_fields:
|
||||
- request
|
||||
output_field: result
|
||||
prompt: 'Request approved: {request}'
|
||||
- node: Reject
|
||||
agent_type: default
|
||||
description: Format and output a rejection message containing the request
|
||||
input_fields:
|
||||
- request
|
||||
output_field: result
|
||||
prompt: 'Request rejected: {request}'
|
||||
outputs:
|
||||
- name: result
|
||||
type: string
|
||||
description: Final formatted message indicating the outcome (approved or rejected)
|
||||
- name: decision
|
||||
type: string
|
||||
description: Routing decision produced by the branching node
|
||||
tags: []
|
||||
metadata:
|
||||
source_repo: https://github.com/jwwelbor/AgentMap.git
|
||||
extracted_at: ''
|
||||
confidence: 0.92
|
||||
---
|
||||
|
||||
# conditional-request-routing-workflow
|
||||
|
||||
Collect a request, classify it via branching logic, and route to an approval or rejection handler to produce a final result
|
||||
|
||||
## Steps
|
||||
|
||||
1. {'node': 'Start', 'agent_type': 'input', 'description': "Prompt user and capture the request into state field 'request'", 'next': 'Classify'}
|
||||
2. {'node': 'Classify', 'agent_type': 'branching', 'description': "Evaluate the request and set 'decision' field, routing to Approve on success or Reject on failure", 'input_fields': ['request'], 'output_field': 'decision', 'next_node': 'Approve', 'on_failure': 'Reject'}
|
||||
3. {'node': 'Approve', 'agent_type': 'default', 'description': 'Format and output an approval message containing the request', 'input_fields': ['request'], 'output_field': 'result', 'prompt': 'Request approved: {request}'}
|
||||
4. {'node': 'Reject', 'agent_type': 'default', 'description': 'Format and output a rejection message containing the request', 'input_fields': ['request'], 'output_field': 'result', 'prompt': 'Request rejected: {request}'}
|
||||
|
||||
## Inputs
|
||||
|
||||
- {'name': 'request', 'type': 'string', 'description': 'The input text or request to be evaluated and routed'}
|
||||
|
||||
## Outputs
|
||||
|
||||
- {'name': 'result', 'type': 'string', 'description': 'Final formatted message indicating the outcome (approved or rejected)'}
|
||||
- {'name': 'decision', 'type': 'string', 'description': 'Routing decision produced by the branching node'}
|
||||
|
||||
## Failure Modes
|
||||
|
||||
- Empty or missing request input prevents meaningful classification
|
||||
- Branching node fails to resolve a valid route and defaults to rejection path
|
||||
- Prompt template variable missing causes malformed output
|
||||
|
||||
## Source
|
||||
|
||||
Extracted from: [https://github.com/jwwelbor/AgentMap.git](https://github.com/jwwelbor/AgentMap.git)
|
||||
Confidence: 0.92
|
||||
@@ -0,0 +1,6 @@
|
||||
# Commands: conditional-request-routing-workflow
|
||||
|
||||
## Available Commands
|
||||
|
||||
- `/skill conditional-request-routing-workflow` — Load this skill
|
||||
- `/run conditional-request-routing-workflow` — Execute workflow
|
||||
@@ -0,0 +1,10 @@
|
||||
# Examples: conditional-request-routing-workflow
|
||||
|
||||
## Usage Example
|
||||
|
||||
```python
|
||||
# How to use this skill
|
||||
# Inputs: {'name': 'request', 'type': 'string', 'description': 'The input text or request to be evaluated and routed'}
|
||||
# Process: {'node': 'Start', 'agent_type': 'input', 'description': "Prompt user and capture the request into state field 'request'", 'next': 'Classify'} → {'node': 'Classify', 'agent_type': 'branching', 'description': "Evaluate the request and set 'decision' field, routing to Approve on success or Reject on failure", 'input_fields': ['request'], 'output_field': 'decision', 'next_node': 'Approve', 'on_failure': 'Reject'} → {'node': 'Approve', 'agent_type': 'default', 'description': 'Format and output an approval message containing the request', 'input_fields': ['request'], 'output_field': 'result', 'prompt': 'Request approved: {request}'}
|
||||
# Outputs: {'name': 'result', 'type': 'string', 'description': 'Final formatted message indicating the outcome (approved or rejected)'}, {'name': 'decision', 'type': 'string', 'description': 'Routing decision produced by the branching node'}
|
||||
```
|
||||
@@ -0,0 +1,72 @@
|
||||
{
|
||||
"name": "conditional-request-routing-workflow",
|
||||
"version": "1.0.0",
|
||||
"goal": "Collect a request, classify it via branching logic, and route to an approval or rejection handler to produce a final result",
|
||||
"inputs": [
|
||||
{
|
||||
"name": "request",
|
||||
"type": "string",
|
||||
"description": "The input text or request to be evaluated and routed"
|
||||
}
|
||||
],
|
||||
"steps": [
|
||||
{
|
||||
"node": "Start",
|
||||
"agent_type": "input",
|
||||
"description": "Prompt user and capture the request into state field 'request'",
|
||||
"next": "Classify"
|
||||
},
|
||||
{
|
||||
"node": "Classify",
|
||||
"agent_type": "branching",
|
||||
"description": "Evaluate the request and set 'decision' field, routing to Approve on success or Reject on failure",
|
||||
"input_fields": [
|
||||
"request"
|
||||
],
|
||||
"output_field": "decision",
|
||||
"next_node": "Approve",
|
||||
"on_failure": "Reject"
|
||||
},
|
||||
{
|
||||
"node": "Approve",
|
||||
"agent_type": "default",
|
||||
"description": "Format and output an approval message containing the request",
|
||||
"input_fields": [
|
||||
"request"
|
||||
],
|
||||
"output_field": "result",
|
||||
"prompt": "Request approved: {request}"
|
||||
},
|
||||
{
|
||||
"node": "Reject",
|
||||
"agent_type": "default",
|
||||
"description": "Format and output a rejection message containing the request",
|
||||
"input_fields": [
|
||||
"request"
|
||||
],
|
||||
"output_field": "result",
|
||||
"prompt": "Request rejected: {request}"
|
||||
}
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "result",
|
||||
"type": "string",
|
||||
"description": "Final formatted message indicating the outcome (approved or rejected)"
|
||||
},
|
||||
{
|
||||
"name": "decision",
|
||||
"type": "string",
|
||||
"description": "Routing decision produced by the branching node"
|
||||
}
|
||||
],
|
||||
"failure_modes": [
|
||||
"Empty or missing request input prevents meaningful classification",
|
||||
"Branching node fails to resolve a valid route and defaults to rejection path",
|
||||
"Prompt template variable missing causes malformed output"
|
||||
],
|
||||
"confidence": 0.92,
|
||||
"explanation": "Extracted from the ReviewFlow CSV example in the AgentMap README. This is a declarative, CSV-defined LangGraph workflow demonstrating the reusable pattern of input -> branching classification -> conditional handling paths. It can be generalized for ticket triage, content moderation, or any route-by-condition use case.",
|
||||
"source_repo": "https://github.com/jwwelbor/AgentMap.git",
|
||||
"score": 1.0
|
||||
}
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
# Tests: langgraph-multi-agent-sequential
|
||||
# Tests: conditional-request-routing-workflow
|
||||
|
||||
## Test Checklist
|
||||
|
||||
@@ -1,99 +0,0 @@
|
||||
---
|
||||
name: langgraph-multi-agent-sequential
|
||||
version: 1.0.0
|
||||
description: Orchestrate a sequence of specialized agents to perform multi-step tasks
|
||||
like research, data processing, and final output generation
|
||||
inputs:
|
||||
- BedrockModel with temperature=0.3, top_p=0.8
|
||||
- Researcher agent with system prompt for destination research (places, history, accommodations,
|
||||
food, web pages)
|
||||
- Travel Guide Generator agent with system prompt for structuring travel guides into
|
||||
labeled sections
|
||||
- Writer agent with system prompt for formatting professional client responses
|
||||
steps:
|
||||
- Researcher agent gathers raw destination facts (top 5 attractions, historical facts,
|
||||
best areas, local foods, suggested web pages) using BedrockModel
|
||||
- Travel Guide Generator agent structures the raw facts into a comprehensive travel
|
||||
guide with clearly labeled sections
|
||||
- Writer agent formats the structured guide into a professional client-facing response
|
||||
with the full guide and highlighted web pages
|
||||
outputs:
|
||||
- Raw research data (JSON string containing destination facts and categories)
|
||||
- Structured travel guide content (markdown with sections for attractions, history,
|
||||
accommodations, cuisine, and web pages)
|
||||
- Final client response (formatted travel guide ready for delivery)
|
||||
tags: []
|
||||
metadata:
|
||||
source_repo: https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git
|
||||
extracted_at: ''
|
||||
confidence: 0.95
|
||||
---
|
||||
|
||||
# langgraph-multi-agent-sequential
|
||||
|
||||
Orchestrate a sequence of specialized agents to perform multi-step tasks like research, data processing, and final output generation
|
||||
|
||||
## Setup
|
||||
|
||||
**Dependencies:**
|
||||
|
||||
```text
|
||||
pip install langchain langgraph bedrock-model pydantic
|
||||
```
|
||||
|
||||
**Setup steps:**
|
||||
|
||||
1. Install langchain and langgraph packages
|
||||
1. Configure BedrockModel with temperature=0.3 and top_p=0.8
|
||||
1. Create three Agent instances with appropriate system prompts and tools
|
||||
1. Deploy the FastAPI server with the LangGraph application
|
||||
|
||||
## Key Files
|
||||
|
||||
- `agents/langchain_langgraph/08-langgraph-multi-agents-sequential-pattern/agent.py`
|
||||
- `agents/langchain_langgraph/08-langgraph-multi-agents-sequential-pattern/app.py`
|
||||
|
||||
## Steps
|
||||
|
||||
1. Researcher agent gathers raw destination facts (top 5 attractions, historical facts, best areas, local foods, suggested web pages) using BedrockModel
|
||||
2. Travel Guide Generator agent structures the raw facts into a comprehensive travel guide with clearly labeled sections
|
||||
3. Writer agent formats the structured guide into a professional client-facing response with the full guide and highlighted web pages
|
||||
|
||||
## Implementation Details
|
||||
|
||||
```python
|
||||
Researcher agent with system_prompt for destination research and tools=[calculator, current_time]
|
||||
```
|
||||
|
||||
```python
|
||||
Travel Guide Generator agent with system_prompt requiring structured sections (attractions, history, accommodations, cuisine, web pages)
|
||||
```
|
||||
|
||||
```python
|
||||
Writer agent with system_prompt for client-facing response formatting
|
||||
```
|
||||
|
||||
## Inputs
|
||||
|
||||
- BedrockModel with temperature=0.3, top_p=0.8
|
||||
- Researcher agent with system prompt for destination research (places, history, accommodations, food, web pages)
|
||||
- Travel Guide Generator agent with system prompt for structuring travel guides into labeled sections
|
||||
- Writer agent with system prompt for formatting professional client responses
|
||||
|
||||
## Outputs
|
||||
|
||||
- Raw research data (JSON string containing destination facts and categories)
|
||||
- Structured travel guide content (markdown with sections for attractions, history, accommodations, cuisine, and web pages)
|
||||
- Final client response (formatted travel guide ready for delivery)
|
||||
|
||||
## Failure Modes
|
||||
|
||||
- Researcher agent fails to retrieve sufficient information, causing downstream agents to receive incomplete or empty data
|
||||
- Travel Guide Generator fails to structure data properly, resulting in unorganized or malformed output
|
||||
- Writer agent fails to format the final response correctly, producing garbled or incomplete output
|
||||
- Model timeouts or errors in any agent step causing the entire pipeline to fail
|
||||
|
||||
## Source
|
||||
|
||||
Extracted from: [https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git](https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git)
|
||||
Confidence: 0.95
|
||||
@@ -1,6 +0,0 @@
|
||||
# Commands: langgraph-multi-agent-sequential
|
||||
|
||||
## Available Commands
|
||||
|
||||
- `/skill langgraph-multi-agent-sequential` — Load this skill
|
||||
- `/run langgraph-multi-agent-sequential` — Execute workflow
|
||||
@@ -1,10 +0,0 @@
|
||||
# Examples: langgraph-multi-agent-sequential
|
||||
|
||||
## Usage Example
|
||||
|
||||
```python
|
||||
# How to use this skill
|
||||
# Inputs: BedrockModel with temperature=0.3, top_p=0.8, Researcher agent with system prompt for destination research (places, history, accommodations, food, web pages), Travel Guide Generator agent with system prompt for structuring travel guides into labeled sections, Writer agent with system prompt for formatting professional client responses
|
||||
# Process: Researcher agent gathers raw destination facts (top 5 attractions, historical facts, best areas, local foods, suggested web pages) using BedrockModel → Travel Guide Generator agent structures the raw facts into a comprehensive travel guide with clearly labeled sections → Writer agent formats the structured guide into a professional client-facing response with the full guide and highlighted web pages
|
||||
# Outputs: Raw research data (JSON string containing destination facts and categories), Structured travel guide content (markdown with sections for attractions, history, accommodations, cuisine, and web pages), Final client response (formatted travel guide ready for delivery)
|
||||
```
|
||||
@@ -1,31 +0,0 @@
|
||||
{
|
||||
"name": "langgraph-multi-agent-sequential",
|
||||
"version": "1.0.0",
|
||||
"goal": "Orchestrate a sequence of specialized agents to perform multi-step tasks like research, data processing, and final output generation",
|
||||
"inputs": [
|
||||
"BedrockModel with temperature=0.3, top_p=0.8",
|
||||
"Researcher agent with system prompt for destination research (places, history, accommodations, food, web pages)",
|
||||
"Travel Guide Generator agent with system prompt for structuring travel guides into labeled sections",
|
||||
"Writer agent with system prompt for formatting professional client responses"
|
||||
],
|
||||
"steps": [
|
||||
"Researcher agent gathers raw destination facts (top 5 attractions, historical facts, best areas, local foods, suggested web pages) using BedrockModel",
|
||||
"Travel Guide Generator agent structures the raw facts into a comprehensive travel guide with clearly labeled sections",
|
||||
"Writer agent formats the structured guide into a professional client-facing response with the full guide and highlighted web pages"
|
||||
],
|
||||
"outputs": [
|
||||
"Raw research data (JSON string containing destination facts and categories)",
|
||||
"Structured travel guide content (markdown with sections for attractions, history, accommodations, cuisine, and web pages)",
|
||||
"Final client response (formatted travel guide ready for delivery)"
|
||||
],
|
||||
"failure_modes": [
|
||||
"Researcher agent fails to retrieve sufficient information, causing downstream agents to receive incomplete or empty data",
|
||||
"Travel Guide Generator fails to structure data properly, resulting in unorganized or malformed output",
|
||||
"Writer agent fails to format the final response correctly, producing garbled or incomplete output",
|
||||
"Model timeouts or errors in any agent step causing the entire pipeline to fail"
|
||||
],
|
||||
"confidence": 0.95,
|
||||
"explanation": "This workflow demonstrates a reusable LangGraph pattern where three specialized agents work sequentially: a Researcher agent gathers raw destination facts, a Travel Guide Generator agent structures those facts into a travel guide, and a Writer agent formats the final output for clients. The pattern is modular and can be adapted to other multi-step tasks by swapping agent roles and prompts while maintaining the same pipeline structure.",
|
||||
"source_repo": "https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git",
|
||||
"score": 1.0
|
||||
}
|
||||
Reference in New Issue
Block a user