Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Hermes Pipeline
|
e20b5370e1 |
@@ -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
|
||||
}
|
||||
@@ -0,0 +1,77 @@
|
||||
---
|
||||
name: literature-review-with-traceable-ai-evidence
|
||||
version: 1.0.0
|
||||
description: Enable researchers to ingest documents, asynchronously index them, and
|
||||
interact with multi-agent AI to answer questions with verifiable citations to original
|
||||
text.
|
||||
inputs:
|
||||
- Documents in PDF, Office, image, or text formats
|
||||
- Research questions or topics of interest
|
||||
- 'Optional: user model configuration via .env or settings'
|
||||
steps:
|
||||
- Upload documents to a project (via desktop app or web UI)
|
||||
- System asynchronously converts Office docs to PDF if needed, runs OCR to extract
|
||||
text with coordinates, chunks and embeds into vector store
|
||||
- User starts a main research session or creates exploration branches without waiting
|
||||
for indexing to finish
|
||||
- Leader agent receives query and delegates subtasks to researcher, reviewer, writer
|
||||
subagents
|
||||
- Subagents perform hybrid retrieval and rerank to find relevant chunks with source
|
||||
coordinates
|
||||
- Agents synthesize answers and return evidence with clickable citations that highlight
|
||||
original pages
|
||||
- User verifies conclusions by navigating to cited source locations and can save notes
|
||||
to research memory or mind map
|
||||
outputs:
|
||||
- AI-generated answers with traceable evidence (coordinates, page highlights)
|
||||
- Research session history with branches
|
||||
- Indexed document library for future queries
|
||||
- Mind maps or structured notes
|
||||
- Persistent run events for resuming sessions
|
||||
tags: []
|
||||
metadata:
|
||||
source_repo: https://github.com/0verL1nk/PaperSage.git
|
||||
extracted_at: ''
|
||||
confidence: 0.85
|
||||
---
|
||||
|
||||
# literature-review-with-traceable-ai-evidence
|
||||
|
||||
Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.
|
||||
|
||||
## Steps
|
||||
|
||||
1. Upload documents to a project (via desktop app or web UI)
|
||||
2. System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store
|
||||
3. User starts a main research session or creates exploration branches without waiting for indexing to finish
|
||||
4. Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents
|
||||
5. Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates
|
||||
6. Agents synthesize answers and return evidence with clickable citations that highlight original pages
|
||||
7. User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map
|
||||
|
||||
## Inputs
|
||||
|
||||
- Documents in PDF, Office, image, or text formats
|
||||
- Research questions or topics of interest
|
||||
- Optional: user model configuration via .env or settings
|
||||
|
||||
## Outputs
|
||||
|
||||
- AI-generated answers with traceable evidence (coordinates, page highlights)
|
||||
- Research session history with branches
|
||||
- Indexed document library for future queries
|
||||
- Mind maps or structured notes
|
||||
- Persistent run events for resuming sessions
|
||||
|
||||
## Failure Modes
|
||||
|
||||
- Missing local Office/LibreOffice converter causes document conversion failure
|
||||
- First-time model download may be slow or require network
|
||||
- OCR may have low confidence on poor quality scans
|
||||
- Retrieval might miss context if chunking splits semantics
|
||||
- Multi-agent coordination could produce conflicting intermediate results
|
||||
|
||||
## Source
|
||||
|
||||
Extracted from: [https://github.com/0verL1nk/PaperSage.git](https://github.com/0verL1nk/PaperSage.git)
|
||||
Confidence: 0.85
|
||||
@@ -0,0 +1,6 @@
|
||||
# Commands: literature-review-with-traceable-ai-evidence
|
||||
|
||||
## Available Commands
|
||||
|
||||
- `/skill literature-review-with-traceable-ai-evidence` — Load this skill
|
||||
- `/run literature-review-with-traceable-ai-evidence` — Execute workflow
|
||||
@@ -0,0 +1,10 @@
|
||||
# Examples: literature-review-with-traceable-ai-evidence
|
||||
|
||||
## Usage Example
|
||||
|
||||
```python
|
||||
# How to use this skill
|
||||
# Inputs: Documents in PDF, Office, image, or text formats, Research questions or topics of interest, Optional: user model configuration via .env or settings
|
||||
# Process: Upload documents to a project (via desktop app or web UI) → System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store → User starts a main research session or creates exploration branches without waiting for indexing to finish
|
||||
# Outputs: AI-generated answers with traceable evidence (coordinates, page highlights), Research session history with branches, Indexed document library for future queries, Mind maps or structured notes, Persistent run events for resuming sessions
|
||||
```
|
||||
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"name": "literature-review-with-traceable-ai-evidence",
|
||||
"version": "1.0.0",
|
||||
"goal": "Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.",
|
||||
"inputs": [
|
||||
"Documents in PDF, Office, image, or text formats",
|
||||
"Research questions or topics of interest",
|
||||
"Optional: user model configuration via .env or settings"
|
||||
],
|
||||
"steps": [
|
||||
"Upload documents to a project (via desktop app or web UI)",
|
||||
"System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store",
|
||||
"User starts a main research session or creates exploration branches without waiting for indexing to finish",
|
||||
"Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents",
|
||||
"Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates",
|
||||
"Agents synthesize answers and return evidence with clickable citations that highlight original pages",
|
||||
"User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map"
|
||||
],
|
||||
"outputs": [
|
||||
"AI-generated answers with traceable evidence (coordinates, page highlights)",
|
||||
"Research session history with branches",
|
||||
"Indexed document library for future queries",
|
||||
"Mind maps or structured notes",
|
||||
"Persistent run events for resuming sessions"
|
||||
],
|
||||
"failure_modes": [
|
||||
"Missing local Office/LibreOffice converter causes document conversion failure",
|
||||
"First-time model download may be slow or require network",
|
||||
"OCR may have low confidence on poor quality scans",
|
||||
"Retrieval might miss context if chunking splits semantics",
|
||||
"Multi-agent coordination could produce conflicting intermediate results"
|
||||
],
|
||||
"confidence": 0.85,
|
||||
"explanation": "The README describes PaperSage's core workflow: asynchronous document ingestion with OCR/indexing, followed by multi-agent question answering with cited evidence. This process is not tied to the specific codebase and can be reused as a general literature review methodology for any document-centric research using RAG and agent collaboration.",
|
||||
"source_repo": "https://github.com/0verL1nk/PaperSage.git",
|
||||
"score": 1.0
|
||||
}
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
# Tests: langgraph-multi-agent-sequential
|
||||
# Tests: literature-review-with-traceable-ai-evidence
|
||||
|
||||
## Test Checklist
|
||||
|
||||
Reference in New Issue
Block a user