Hermes Pipeline
2382525f81
Extracted from: https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git Score: 1.0
100 lines
4.0 KiB
Markdown
100 lines
4.0 KiB
Markdown
---
|
|
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
|