Skip to Content
Python SDKQuickstart

Python SDK Quickstart

Get started with the Endee Python SDK to build powerful vector search applications. This guide will walk you through installation, setup, and creating your first index.

Requirements

  • Python 3.8 or higher
  • Endee Local server running (see Quick Start)

New to Endee? Set up your local environment first by following the Quick Start Guide.

Installation

Install the Endee Python SDK using pip:

pip install endee

Setup Endee and Create Index

Initialize the Client

The Endee client is the main interface for all vector operations. Initialize it to connect to your local server:

from endee import Endee
 
# Connect to local Endee server (defaults to localhost:8080)
client = Endee()

Using Authentication? If your server has NDD_AUTH_TOKEN set, pass the same token when initializing:

client = Endee("your-auth-token")

See Authentication for details.

Create a Dense Index

Create a vector index for semantic similarity search:

from endee import Precision
 
client.create_index(
    name="my_vectors",
    dimension=384,
    space_type="cosine",
    precision=Precision.INT8D
)

Dense Index Parameters:

ParameterDescription
nameUnique name for your index
dimensionVector dimensionality (must match your embedding model’s output)
space_typeDistance metric - "cosine", "l2", or "ip" (inner product)
MGraph connectivity - higher values increase recall but use more memory (default: 16)
ef_conConstruction-time parameter - higher values improve index quality (default: 128)
precisionQuantization precision (default: Precision.INT8D)

Create a Hybrid Index

Hybrid indexes combine dense vector search with sparse vector search for improved retrieval. Add the sparse_dim parameter to enable hybrid search:

from endee import Precision
 
client.create_index(
    name="my_hybrid_index",
    dimension=384,           # Dense vector dimension
    sparse_dim=30000,        # Sparse vector dimension (vocabulary size)
    space_type="cosine",
    precision=Precision.INT8D
)

Additional Hybrid Parameter:

ParameterDescription
sparse_dimSparse vector dimension (e.g., vocabulary size for SPLADE)

List and Access Indexes

# List all indexes
indexes = client.list_indexes()
 
# Get reference to an existing index
index = client.get_index(name="my_vectors")
 
# Delete an index
client.delete_index(name="my_vectors")

Complete Example

Here’s a complete example putting it all together:

from endee import Endee, Precision
 
# Initialize client
client = Endee()
 
# Create a dense index
client.create_index(
    name="documents",
    dimension=384,
    space_type="cosine",
    precision=Precision.INT8D
)
 
# Get the index
index = client.get_index(name="documents")
 
# Add vectors
index.upsert([
    {
        "id": "doc1",
        "vector": [0.1, 0.2, ...],  # 384-dimensional vector
        "meta": {"title": "First Document"},
        "filter": {"category": "tech"}
    },
    {
        "id": "doc2",
        "vector": [0.3, 0.4, ...],
        "meta": {"title": "Second Document"},
        "filter": {"category": "science"}
    }
])
 
# Query the index
results = index.query(
    vector=[0.15, 0.25, ...],
    top_k=5
)
 
for item in results:
    print(f"ID: {item['id']}, Similarity: {item['similarity']}")

Next Steps

Now that you have your index set up, learn how to:

ConceptsUsage