Load Node Results

Retrieve simulation results from specific nodes within your GraphorLM flows. This endpoint provides access to the output data generated during node simulation (not from deployed flow execution) with pagination support.

Overview

Load simulation data from individual flow nodes for debugging, analysis, or testing purposes. Each node type returns different data structures based on their simulated processing function.

Method: POST
URL: https://{flow_name}.flows.graphorlm.com/nodes/results
Authentication: Required (API Token)

Authentication

All requests must include a valid API token in the Authorization header:

Authorization: Bearer YOUR_API_TOKEN

Learn how to generate API tokens in the API Tokens guide.

Request Format

Headers

Header	Value	Required
`Authorization`	`Bearer YOUR_API_TOKEN`	Yes
`Content-Type`	`application/json`	Yes

Request Body

The request body should be a JSON object with the following fields:

Field	Type	Required	Description
`node_id`	string	Yes	The unique identifier of the node to load data from
`page`	integer	No	Page number for pagination (starts from 1)
`page_size`	integer	No	Number of items per page (default: 10, max: 100)

Example Request

{
  "node_id": "chunking-1748287628685",
  "page": 1,
  "page_size": 20
}

Response Format

Success Response (200 OK)

{
  "success": true,
  "message": "Node simulation data loaded successfully for 'chunking-1748287628685'",
  "items": [
    {
      "id": "chunk-001",
      "content": "Machine learning is a subset of artificial intelligence that enables computers to learn and improve from experience without being explicitly programmed.",
      "metadata": {
        "chunk_index": 0,
        "source_file": "ml-basics.pdf",
        "page_number": 1,
        "chunk_size": 150,
        "embedding_model": "text-embedding-3-small"
      },
      "embedding": [0.1234, -0.5678, 0.9101, "..."],
      "score": 0.95
    },
    {
      "id": "chunk-002", 
      "content": "Supervised learning algorithms learn from labeled training data to make predictions on new, unseen data.",
      "metadata": {
        "chunk_index": 1,
        "source_file": "ml-basics.pdf",
        "page_number": 1,
        "chunk_size": 105,
        "embedding_model": "text-embedding-3-small"
      },
      "embedding": [0.2345, -0.6789, 0.1234, "..."],
      "score": 0.89
    }
  ],
  "total": 420,
  "page": 1,
  "page_size": 20,
  "total_pages": 21
}

Response Structure

Field	Type	Description
`success`	boolean	Whether the simulation data loading operation was successful
`message`	string	Human-readable message about the operation result
`items`	array	Array of simulation data objects from the specified node
`total`	integer	Total number of items available across all pages
`page`	integer	Current page number (if pagination was used)
`page_size`	integer	Number of items per page (if pagination was used)
`total_pages`	integer	Total number of pages available

Node Data Structures by Type

The structure of items varies based on the node type:

Chunking Node Data

{
  "id": "chunk-001",
  "content": "Chunk content...",
  "metadata": {
    "source_file": "document.pdf",
    "chunk_size": 1000,
    "embedding_model": "text-embedding-3-small"
  },
  "embedding": [0.1234, -0.5678, "..."]
}

LLM Node Data

{
  "id": "answer-001",
  "content": "Generated response...",
  "metadata": {
    "question": "What is machine learning?",
    "model": "gpt-4",
    "generation_time": 2.34
  }
}

Code Examples

JavaScript/Node.js

async function loadNodeResults(flowName, nodeId, options = {}, apiToken) {
  const url = `https://${flowName}.flows.graphorlm.com/nodes/results`;
  
  const payload = {
    node_id: nodeId,
    ...(options.page && { page: options.page }),
    ...(options.pageSize && { page_size: options.pageSize })
  };

  const response = await fetch(url, {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${apiToken}`,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify(payload)
  });

  if (!response.ok) {
    const errorData = await response.json();
    throw new Error(`Failed to load node results: ${errorData.detail}`);
  }

  return await response.json();
}

// Usage - Load simulation results from a node
loadNodeResults('my-rag-pipeline', 'chunking-123', { page: 1, pageSize: 20 }, 'YOUR_API_TOKEN')
  .then(results => {
    console.log(`Total simulation items: ${results.total}`);
    console.log(`Simulation items on this page: ${results.items.length}`);
  })
  .catch(error => console.error('Error:', error));

Python

import requests

def load_node_results(flow_name, node_id, api_token, page=None, page_size=None):
    url = f"https://{flow_name}.flows.graphorlm.com/nodes/results"
    
    payload = {"node_id": node_id}
    if page is not None:
        payload["page"] = page
    if page_size is not None:
        payload["page_size"] = page_size
    
    headers = {
        "Authorization": f"Bearer {api_token}",
        "Content-Type": "application/json"
    }
    
    response = requests.post(url, headers=headers, json=payload)
    response.raise_for_status()
    
    return response.json()

# Usage - Load simulation results from a node
try:
    results = load_node_results("my-rag-pipeline", "chunking-123", "YOUR_API_TOKEN", page=1, page_size=20)
    print(f"Total simulation items: {results['total']}")
    print(f"Simulation items on this page: {len(results['items'])}")
except Exception as e:
    print(f"Error: {e}")

cURL

curl -X POST "https://my-rag-pipeline.flows.graphorlm.com/nodes/results" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "node_id": "chunking-123",
    "page": 1,
    "page_size": 20
  }'

Error Responses

Common Error Codes

Status Code	Description	Common Causes
400	Bad Request	Invalid node ID, malformed pagination parameters
401	Unauthorized	Invalid or missing API token
404	Not Found	Flow not found, node not found in the specified flow
500	Internal Server Error	Node data loading failed, processing error

Error Response Format

{
  "detail": "Error message describing what went wrong"
}

Example Error Responses

Flow Not Found

{
  "detail": "Flow with name 'my-rag-flow' not found"
}

Node Not Found

{
  "detail": "Node with id 'invalid-node-id' not found in flow 'my-rag-flow'"
}

Invalid Pagination

{
  "detail": "page_size must be between 1 and 100"
}

Simulation Data Loading Failed

{
  "detail": "Failed to load node simulation data"
}

Use Cases

Simulation Data Analysis

Examine the simulation output data from different node types to validate processing logic and data structures.

Debug Node Issues

Identify problems in individual nodes by examining their simulation results before deploying the flow.

Testing and Validation

Extract simulation data to test node configurations and validate processing logic before production deployment.

Best Practices

Pagination: Use appropriate page sizes (20-100 items) for optimal performance
Error Handling: Implement proper error handling for API failures
Data Validation: Validate expected data structures from different node types
Security: Secure API token storage and rotation

Troubleshooting

Node Simulation Data Loading Failed

Empty Simulation Results Returned

Authentication Issues

Next Steps

After loading node simulation results, you can:

Analyze Simulation Results

Analyze and validate your node simulation data before deployment

Update Node Configuration

Optimize node settings based on simulation analysis

Deploy Flow

Deploy your flow after validating simulation results

Flow Overview

Learn about complete flow management and all node types

The Load Node Results API provides access to simulation data from your flow nodes with pagination support, enabling testing, debugging, and validation of node configurations before deployment.

Get Started

Sources

Flows

Overview

Authentication

Request Format

Headers

Request Body

Example Request

Response Format

Success Response (200 OK)

Response Structure

Node Data Structures by Type

Chunking Node Data

LLM Node Data

Code Examples

JavaScript/Node.js

Python

cURL

Error Responses

Common Error Codes

Error Response Format

Example Error Responses

Flow Not Found

Node Not Found

Simulation Data Loading Failed

Use Cases

Simulation Data Analysis

Debug Node Issues

Testing and Validation

Best Practices

Troubleshooting

Next Steps

Analyze Simulation Results

Update Node Configuration

Deploy Flow

Flow Overview

Get Started

Sources

Flows

​Overview

​Authentication

​Request Format

​Headers

​Request Body

​Example Request

​Response Format

​Success Response (200 OK)

​Response Structure

​Node Data Structures by Type

​Chunking Node Data

​LLM Node Data

​Code Examples

​JavaScript/Node.js

​Python

​cURL

​Error Responses

​Common Error Codes

​Error Response Format

​Example Error Responses

​Flow Not Found

​Node Not Found

​Invalid Pagination

​Simulation Data Loading Failed

​Use Cases

​Simulation Data Analysis

​Debug Node Issues

​Testing and Validation

​Best Practices

​Troubleshooting

​Next Steps

Analyze Simulation Results

Update Node Configuration

Deploy Flow

Flow Overview

Overview

Authentication

Request Format

Headers

Request Body

Example Request

Response Format

Success Response (200 OK)

Response Structure

Node Data Structures by Type

Chunking Node Data

LLM Node Data

Code Examples

JavaScript/Node.js

Python

cURL

Error Responses

Common Error Codes

Error Response Format

Example Error Responses

Flow Not Found

Node Not Found

Invalid Pagination

Simulation Data Loading Failed

Use Cases

Simulation Data Analysis

Debug Node Issues

Testing and Validation

Best Practices

Troubleshooting

Next Steps