Skip to main content

​
Prerequisites

1

Sign Up

Create your account at console.moorcheh.ai
2

Get Your API Key

Navigate to the API Keys section in your dashboard and generate a new API key
Store your API key securely. Never commit it to version control or share it publicly.

​
Base URL

All API endpoints are accessible at: 
https://api.moorcheh.ai/v1

​
Authentication

The Moorcheh API uses API key authentication. Include your API key in the x-api-key header with every request.

​
Install the SDK

pip install moorcheh-sdk

​
Initialize the Client

from moorcheh_sdk import MoorchehClient

# Initialize client
client = MoorchehClient(
    api_key="your-api-key-here",
    base_url="https://api.moorcheh.ai/v1"
)

​
Create a Namespace

# Create a vector namespace
client.create_namespace(
    namespace_name="my-vectors",
    type="vector",
    vector_dimension=1536
)

​
Upload Vectors

# Upload vector embeddings
vectors = [
    {
        "id": "vec-1",
        "vector": [0.1, 0.2, 0.3, ...],  # 1536-dimensional vector
        "source": "document-1",
        "index": 0
    },
    {
        "id": "vec-2",
        "vector": [0.4, 0.5, 0.6, ...],
        "source": "document-2",
        "index": 1
    }
]

result = client.upload_vectors(
    namespace_name="my-vectors",
    vectors=vectors
)
print(f"Uploaded {result['processed']} vectors")

# Perform vector similarity search
query_vector = [0.1, 0.2, 0.3, ...]  # Your query vector

results = client.search(
    namespaces=["my-vectors"],
    query=query_vector,
    top_k=5
)

# Display results
for match in results["matches"]:
    print(f"ID: {match['id']}, Score: {match['score']}")

​
Next Steps

API Reference

Explore the complete API documentation

Python SDK

Learn more about the Python SDK

Integrations

Integrate with LangChain, LlamaIndex, and more

Support

Get help from our team

​
Common Issues

Error: 401 UnauthorizedSolution:
  • Verify your API key is correct
  • Ensure you’re using the header x-api-key (all lowercase)
  • Check that your API key hasn’t been disabled
Error: 404 Namespace not foundSolution:
  • Create the namespace first using the create namespace endpoint
  • Verify the namespace name matches exactly (case-sensitive)
Error: 400 Vector dimension mismatchSolution:
  • Ensure all vectors match the dimension specified when creating the namespace
  • Verify your embedding model output dimension