CrewAI Quickstart

Build AI agent systems with persistent vector memory using Endee and CrewAI. This integration enables your CrewAI agents to store, retrieve, and manage vector-based knowledge efficiently.

Features

Vector-based memory for CrewAI — Use Endee as a backend for short-term and entity memory
High-performance search — Approximate Nearest Neighbor (ANN) searches for fast retrieval
Metadata & filtering support — Store rich metadata and filter queries
Embeddings integration — Supports any embedding provider (OpenAI, Google Gemini, Cohere, HuggingFace)

Requirements

Python 3.8 or higher
An Endee account (sign up at Endee Dashboard )
API key for your chosen embedding provider

Installation

Install the Endee CrewAI integration package:


pip install endee-crewai

Install CrewAI and your preferred embedding provider:


pip install crewai crewai-tools google-genai

Environment Variables

Create a .env file to store your API credentials:


ENDEE_API_TOKEN=your_endee_api_token
GOOGLE_API_KEY=your_google_api_key
OPENAI_API_KEY=your_openai_api_key
COHERE_API_KEY=your_cohere_api_key

Note: You can use any embedding provider (OpenAI, Google, Cohere, HuggingFace). Supply the API key for the provider you use and omit the rest. However, ENDEE_API_TOKEN is required to access your Endee vector database.

Initialize Endee Vector Store

Set up the Endee vector store with your preferred embedding provider:


from endee_crewai import EndeeVectorStore
import time
 
# Embedding function (e.g., using Cohere)
embedder_config = {
    "provider": "cohere",
    "config": {"model_name": "small", "api_key": "<COHERE_API_KEY>"}
}
 
# Create Endee store
memory_store = EndeeVectorStore(
    type="my_index",
    api_token="<ENDEE_API_TOKEN>",
    embedder_config=embedder_config,
    space_type="cosine",
    crew=None,
)
 
# Reset index if needed
memory_store.reset()
time.sleep(2)  # Wait for reset
 
print("Endee vector store initialized successfully")

Embedding Provider Examples

OpenAI:


embedder_config = {
    "provider": "openai",
    "config": {"model_name": "text-embedding-3-small", "api_key": "<OPENAI_API_KEY>"}
}

Google:


embedder_config = {
    "provider": "google",
    "config": {"model_name": "models/embedding-001", "api_key": "<GOOGLE_API_KEY>"}
}

Cohere:


embedder_config = {
    "provider": "cohere",
    "config": {"model_name": "small", "api_key": "<COHERE_API_KEY>"}
}

Next Steps

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