Basic Usage

This guide covers creating documents, building vector indexes, and performing semantic search with Endee and LlamaIndex.

Creating Documents

Create documents with metadata for filtering and organization:


from llama_index.core import Document
 
# Create sample documents with different categories and metadata
documents = [
    Document(
        text="Python is a high-level, interpreted programming language known for its readability and simplicity.",
        metadata={"category": "programming", "language": "python", "difficulty": "beginner"}
    ),
    Document(
        text="JavaScript is a scripting language that enables interactive web pages and is an essential part of web applications.",
        metadata={"category": "programming", "language": "javascript", "difficulty": "intermediate"}
    ),
    Document(
        text="Machine learning is a subset of artificial intelligence that provides systems the ability to automatically learn and improve from experience.",
        metadata={"category": "ai", "field": "machine_learning", "difficulty": "advanced"}
    ),
    Document(
        text="Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning.",
        metadata={"category": "ai", "field": "deep_learning", "difficulty": "advanced"}
    ),
    Document(
        text="Vector databases are specialized database systems designed to store and query high-dimensional vectors for similarity search.",
        metadata={"category": "database", "type": "vector", "difficulty": "intermediate"}
    ),
    Document(
        text="Endee is a vector database that provides secure and private vector search capabilities.",
        metadata={"category": "database", "type": "vector", "product": "endee", "difficulty": "intermediate"}
    )
]
 
print(f"Created {len(documents)} sample documents")

Creating a Vector Index

Build a searchable vector index from your documents:


from llama_index.core import VectorStoreIndex
from llama_index.embeddings.openai import OpenAIEmbedding
 
embed_model = OpenAIEmbedding()
 
# Create a vector index
index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context,
    embed_model=embed_model
)
 
print("Vector index created successfully")

Basic Retrieval with Query Engine

Create a query engine and perform semantic search:


# Create a query engine
query_engine = index.as_query_engine()
 
# Ask a question
response = query_engine.query("What is Python?")
 
print("Query: What is Python?")
print("Response:")
print(response)

Example Output:


Query: What is Python?
Response:
Python is a high-level, interpreted programming language known for its readability and simplicity.

Saving and Loading Indexes

Your vectors are stored in the cloud. Reconnect to your index in future sessions:


# To reconnect to an existing index in a future session:
def reconnect_to_index(api_token, index_name):
    # Initialize the vector store with existing index
    vector_store = EndeeVectorStore.from_params(
        api_token=api_token,
        index_name=index_name
    )
    
    # Create storage context
    storage_context = StorageContext.from_defaults(vector_store=vector_store)
    
    # Load the index
    index = VectorStoreIndex.from_vector_store(
        vector_store,
        embed_model=OpenAIEmbedding()
    )
    
    return index
 
# Example usage
reconnected_index = reconnect_to_index(endee_api_token, index_name)
query_engine = reconnected_index.as_query_engine()
response = query_engine.query("What is Endee?")
print(response)

Important: Save your index_name to reconnect to your data later.

Cleanup

Delete the index when you’re done to free up resources:


# Uncomment to delete your index
endee.delete_index(index_name)
print(f"Index {index_name} deleted")

Warning: Deleting an index permanently removes all stored vectors and cannot be undone.