​
Get Started with Vedaya

Follow this guide to quickly set up and start using the Vedaya API for document processing, knowledge graph creation, and RAG-powered applications.

​
Prerequisites

Before you begin, make sure you have:

  1. A Vedaya account (sign up at app.vedaya.ai if you don’t have one)
  2. An API key (available in your Vedaya dashboard)
  3. Python 3.8+ installed (for using the Python examples)

​
Installation

You can use the Vedaya API with any programming language that can make HTTP requests. For Python users, we recommend using the requests library:

pip install requests

​
Authentication

All API requests require authentication with your API key:

headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}

Replace YOUR_API_KEY with your actual API key from the Vedaya dashboard.

​
Basic Workflow

The typical workflow for using Vedaya consists of these steps:

  1. Upload Documents: Ingest documents through file upload or cloud integration
  2. Process Documents: Extract text, chunk content, and generate embeddings
  3. Build Knowledge Graph: Extract entities and relationships
  4. Query Knowledge: Retrieve information and generate answers

Let’s implement each of these steps.

​
Step 1: Upload Documents

import requests

url = "https://vedaya-backend.fly.dev/api/data-ingestion/upload-files"

# Prepare files and parameters
files = [
    ('files', ('document.pdf', open('document.pdf', 'rb'), 'application/pdf'))
]
data = {
    'chunk_size': 500,
    'overlap_pct': 10
}

# Add your API key
headers = {
    'Authorization': 'Bearer YOUR_API_KEY'
}

# Send request
response = requests.post(url, headers=headers, files=files, data=data)
file_id = response.json()['file_ids'][0]
print(f"Uploaded document with ID: {file_id}")

​
Step 2: Check Processing Status

import requests
import time

url = f"https://vedaya-backend.fly.dev/api/data-ingestion/status/{file_id}"

headers = {
    'Authorization': 'Bearer YOUR_API_KEY'
}

# Poll status until processing completes
while True:
    response = requests.get(url, headers=headers)
    status = response.json()['status']
    print(f"Processing status: {status}")
    
    if status in ['completed', 'failed']:
        break
        
    time.sleep(5)  # Wait 5 seconds before checking again

​
Step 3: Detect Entities

import requests
import json

url = "https://vedaya-backend.fly.dev/api/knowledge-graph/detect-entities"

payload = json.dumps({
    "document_ids": [file_id]
})

headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
}

response = requests.post(url, headers=headers, data=payload)
print("Entity detection started")

# Check entity detection status
url = "https://vedaya-backend.fly.dev/api/knowledge-graph/entity-detection-status"
while True:
    response = requests.get(url, headers=headers)
    status = response.json()['status']
    print(f"Entity detection status: {status}")
    
    if status in ['completed', 'failed']:
        break
        
    time.sleep(5)

​
Step 4: Query Your Knowledge Base

import requests
import json

url = "https://vedaya-backend.fly.dev/api/retrieval/query"

payload = json.dumps({
    "query": "What are the main topics covered in the document?",
    "top_k": 3,
    "model": "gpt-4"
})

headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
}

response = requests.post(url, headers=headers, data=payload)
result = response.json()

print("Generated Answer:")
print(result['answer'])
print("\nRetrieved Chunks:")
for i, chunk in enumerate(result['chunks']):
    print(f"Chunk {i+1}: {chunk['text'][:100]}... (Score: {chunk['score']})")

​
Next Steps

Congratulations! You’ve completed the basic workflow for using the Vedaya API. From here, you can:

  1. Explore the Data Ingestion Guide for more upload options
  2. Learn about Knowledge Graph visualization and management
  3. Dive into Vector Indexing to understand how embeddings work
  4. Implement Retrieval & RAG in your applications

​
API Reference

For detailed API documentation, check out: