LlamaIndex Quickstart

Build powerful RAG applications with Endee vector database and LlamaIndex. This guide will walk you through installation, setup, and creating your first vector index.

Requirements

Python 3.8 or higher
An Endee account (sign up at Endee Dashboard )
OpenAI API key (for embeddings)

Installation

Install the Endee LlamaIndex integration package:


pip install endee-llamaindex

Note: This will automatically install endee and llama-index as dependencies.

Setting up Credentials

Configure your API credentials for Endee and OpenAI:


import os
from llama_index.embeddings.openai import OpenAIEmbedding
 
# Set API keys
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
endee_api_token = "your-endee-api-token"

Tip: Store your API keys in environment variables for production use.

Initialize Endee Vector Store

Set up the Endee vector store and connect it to LlamaIndex:


from endee_llamaindex import EndeeVectorStore
from llama_index.core import StorageContext
import time
 
# Create a unique index name
timestamp = int(time.time())
index_name = f"llamaindex_demo_{timestamp}"
 
# Set up the embedding model
embed_model = OpenAIEmbedding()
 
# Initialize the Endee vector store
vector_store = EndeeVectorStore.from_params(
    api_token=endee_api_token,
    index_name=index_name,
    dimension=1536,        # OpenAI's default embedding dimension
    space_type="cosine"    # Can be "cosine", "l2", or "ip"
)
 
# Create storage context with our vector store
storage_context = StorageContext.from_defaults(vector_store=vector_store)
 
print(f"Initialized Endee vector store with index: {index_name}")

Configuration Options

Parameter	Type	Description	Default
`api_token`	`str`	Your Endee API token	Required
`index_name`	`str`	Name of the index	Required
`dimension`	`int`	Vector dimension	Required
`space_type`	`str`	Distance metric	`"cosine"`
`batch_size`	`int`	Vectors per API call	`100`

Distance Metrics

Metric	Best For
`cosine`	Text embeddings, normalized vectors
`l2`	Image features, spatial data
`ip`	Recommendation systems, dot product similarity

Next Steps

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