Skip to main content

Quick Start

Get started with Reeflect in just a few minutes with this quick start guide.

Basic Setup​

from reeflect import Reeflect
from reeflect.adapters.openai import OpenAIAdapter

# Initialize with OpenAI adapter
memory = Reeflect(
    adapter=OpenAIAdapter(
        api_key="your_openai_api_key",
        embedding_model="text-embedding-3-small",
        completion_model="gpt-4-turbo-preview"
    ),
    storage_config={
        "type": "local",
        "path": "./memory_storage"
    }
)

Storing Memories​

# Store a simple memory
memory_id = memory.create(
    content="The user prefers dark mode in all applications.",
    namespace="user_preferences",
    importance=0.8
)

# Store multiple memories in batch
memory_ids = memory.batch_create([
    {
        "content": "The user is allergic to peanuts.",
        "namespace": "user_health",
        "importance": 0.9
    },
    {
        "content": "The user's favorite color is blue.",
        "namespace": "user_preferences",
        "importance": 0.6
    }
])

Retrieving Memories​

# Retrieve a specific memory by ID
memory_obj = memory.retrieve(memory_id)

# Search memories by semantic similarity
results = memory.search(
    query="What are the user's color preferences?",
    namespace="user_preferences",
    limit=5
)

for memory_obj, similarity in results:
    print(f"Memory: {memory_obj.content} (Score: {similarity:.2f})")

Enhancing LLM Prompts​

# Enhance a prompt with relevant memories
enhanced_prompt = memory.enhance_prompt(
    prompt="What theme should I use for the dashboard?",
    namespace="user_preferences",
    max_memories=3
)

# Generate a response using OpenAI with the enhanced prompt
client = memory.adapter.client
response = client.chat.completions.create(
    model="gpt-4-turbo-preview",
    messages=[
        {"role": "system", "content": "You are a helpful assistant with memory."},
        {"role": "user", "content": enhanced_prompt}
    ]
)

print(response.choices[0].message.content)

Complete Examples​

Check out our complete example applications to see Reeflect in action:

Next Steps​

Now that you understand the basics, learn about Basic Concepts to gain a deeper understanding of Reeflect's architecture and capabilities.