---
name: langgraph-csv-workflow
version: 1.0.0
description: Transform simple CSV files into powerful AI agent workflows using LangGraph
  orchestration
inputs:
- 'CSV workflow files with columns: graph_name, node_name, agent_type, next_node,
  on_failure, prompt, input_fields, output_field'
- LLM provider configuration (OpenAI, Anthropic, Google) in agentmap_config.yaml
- Storage configuration for CSV/JSON/Vector DBs in agentmap_config_storage.yaml
steps:
- Define workflow in CSV format specifying graph nodes, agent types, and data flow
  between them
- Configure LLM providers and storage backends in the agentmap configuration files
- Execute the workflow using the agentmap CLI or Python API
outputs:
- Executed workflow with agent decisions and state transitions
- Traced execution path through the graph nodes
- Logged agent interactions and output fields populated
tags: []
metadata:
  source_repo: https://github.com/jwwelbor/AgentMap.git
  extracted_at: ''
  confidence: 0.95
---

# langgraph-csv-workflow

Transform simple CSV files into powerful AI agent workflows using LangGraph orchestration

## Setup

**Dependencies:**

```text
pip install langgraph>=1.0.0 langchain-core>=0.3.0 pyyaml fastapi uvicorn
```

**Setup steps:**

1. Install agentmap: pip install agentmap[all]
1. Initialize configuration: agentmap init-config
1. Configure LLM providers in agentmap_config.yaml
1. Run workflow: agentmap run workflow.csv

## Key Files

- `agentmap_config.yaml - Main configuration for LLM providers and paths`
- `agentmap_config_storage.yaml - Storage configuration for CSV/JSON/Vector DBs`
- `hello_world.csv - Sample workflow definition`

## Steps

1. Define workflow in CSV format specifying graph nodes, agent types, and data flow between them
2. Configure LLM providers and storage backends in the agentmap configuration files
3. Execute the workflow using the agentmap CLI or Python API

## Implementation Details

```python
CSV format: graph_name,node_name,agent_type,next_node,on_failure,prompt,input_fields,output_field
```

```python
CLI command: agentmap run hello_world.csv --pretty
```

## Inputs

- CSV workflow files with columns: graph_name, node_name, agent_type, next_node, on_failure, prompt, input_fields, output_field
- LLM provider configuration (OpenAI, Anthropic, Google) in agentmap_config.yaml
- Storage configuration for CSV/JSON/Vector DBs in agentmap_config_storage.yaml

## Outputs

- Executed workflow with agent decisions and state transitions
- Traced execution path through the graph nodes
- Logged agent interactions and output fields populated

## Failure Modes

- Invalid CSV format causing parse errors during workflow loading
- Missing or misconfigured LLM provider credentials leading to runtime failures
- Incorrect agent configuration (e.g., missing input_fields) causing processing errors

## Source

Extracted from: [https://github.com/jwwelbor/AgentMap.git](https://github.com/jwwelbor/AgentMap.git)
Confidence: 0.95