Quick Start Guide
Welcome to Papr Memory! This guide will get you up and running with adding memory to your experience in just 15 minutes. Whether you're building an AI assistant, knowledge management system, or any AI app that needs intelligent memory capabilities, you're in the right place.
What You'll Learn
By the end of this guide, you'll know how to:
- Set up Papr Memory in your project
- Add memories to your knowledge base
- Retrieve memories using semantic + graph-based search
Get your API Key
Create a free account then get your API Key from settings.
Installation
# No installation needed for curl
# Just make sure curl is installed on your system
Authentication
Add PAPR_MEMORY_API_KEY to your .env file, then use it to authenticate:
# Set your API key as an environment variable
export PAPR_MEMORY_API_KEY='your_api_key_here'
Creating Users
Before adding memories, create users to associate with your memories. This enables:
- User-specific memory storage and retrieval
- Access control for memories
- Organizing memories by user
- Sharing of memories between users
Note: While creating users explicitly is recommended for better performance and control, you can also use
external_user_id
directly in memory operations without creating users first. Papr will automatically create users for you behind the scenes.
# Create a user
curl -X POST https://memory.papr.ai/v1/user \
-H "X-API-Key: $PAPR_MEMORY_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Client-Type: curl" \
-d '{
"external_id": "user123", # Your application's user identifier
"email": "user@example.com", # Optional
"metadata": {
"name": "John Doe", # Optional
"role": "developer" # Optional
}
}'
User ID Storage Best Practices
You have two options for associating memories with users:
Using external_user_id (Recommended for most cases)
- Use your application's existing user IDs
- No need to store additional IDs
- Automatic user creation behind the scenes
Using Papr-generated user_id (For advanced use cases)
- Pre-create users for better performance
- More control over user metadata and settings
- Requires storing the Papr user ID
# Example: Storing user ID in your database
def save_papr_user_id(app_user_id, papr_user_id):
# Your database code here
db.users.update_one(
{"id": app_user_id}, # Your application's internal user ID
{"$set": {"papr_user_id": papr_user_id}} # The Papr-generated ID (e.g., "usr_abc123")
)
# Example: Retrieving user ID from your database
def get_papr_user_id(app_user_id):
user = db.users.find_one({"id": app_user_id})
return user.get("papr_user_id") # Returns the Papr-generated ID
Performance Optimization with Batch User Creation
For applications with many users, pre-creating users in bulk can improve performance:
# Pre-create users in bulk
bulk_users = client.user.create_batch(
users=[
{"external_id": "user123", "email": "user123@example.com"},
{"external_id": "user456", "email": "user456@example.com"},
{"external_id": "user789", "email": "user789@example.com"}
]
)
Adding Memories
Add a new memory to your knowledge base, using either your external user ID or the Papr-generated user ID:
curl -X POST https://memory.papr.ai/v1/memory \
-H "X-API-Key: $PAPR_MEMORY_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Client-Type: curl" \
-d '{
"content": "Meeting notes from the product planning session",
"type": "text",
"metadata": {
"external_user_id": "user123", // Your application's user identifier
"createdAt": "2024-03-21T10:00:00Z"
}
}'
Searching Memories
Search through memories using natural language and either your external user ID or the Papr-generated user ID:
curl -X POST https://memory.papr.ai/v1/memory/search \
-H "X-API-Key: $PAPR_MEMORY_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept-Encoding: gzip" \
-H "X-Client-Type: curl" \
-d '{
"query": "What are the key points from our recent product planning?",
"external_user_id": "user123" // Your application's user identifier
}'
User-Specific vs. Global Search
You can choose whether to search memories for a specific user or across all accessible memories:
# Search only for a specific user's memories (using external_user_id)
user_specific_results = client.memory.search(
query="product planning",
external_user_id="user123" // Your application's user identifier
)
# Search across all accessible memories
global_results = client.memory.search(
query="product planning"
# No user filter means search all accessible memories
)
Getting a Specific Memory
Retrieve a specific memory by its ID to verify it was added correctly:
curl -X GET https://memory.papr.ai/v1/memory/mem_abc123 \
-H "X-API-Key: $PAPR_MEMORY_API_KEY" \
-H "Content-Type: application/json" \
-H "X-Client-Type: curl"
ACL and Memory Permissions
Note the acl
field in the response, which shows that the memory is accessible only to the user who created it. This is automatically set based on the Papr-generated user_id
in the metadata when creating the memory.
Papr as an Agentic Tool
Use Papr Memory directly as a tool in your AI applications for advanced memory capabilities:
import os
import aiohttp
from typing import Optional, Dict, Any
# Initialize with your API key from .env
PAPR_API_KEY = os.environ.get("PAPR_MEMORY_API_KEY")
async def search_papr_memory(query: str, user_id: Optional[str] = None):
"""Search through Papr memory with a natural language query."""
headers = {
"X-API-Key": PAPR_API_KEY,
"Content-Type": "application/json",
"Accept-Encoding": "gzip",
"X-Client-Type": "agent"
}
payload = {"query": query}
if user_id:
payload["metadata"] = {"user_id": user_id} # Papr-generated user ID
async with aiohttp.ClientSession() as session:
async with session.post(
"https://memory.papr.ai/v1/memory/search",
headers=headers,
json=payload
) as response:
return await response.json()
async def add_papr_memory(content: str, user_id: Optional[str] = None, metadata: Optional[Dict[str, Any]] = None, memory_type: str = "text"):
"""Add a new memory to Papr memory system."""
headers = {
"X-API-Key": PAPR_API_KEY,
"Content-Type": "application/json",
"X-Client-Type": "agent"
}
if metadata is None:
metadata = {}
if user_id:
metadata["user_id"] = user_id # Papr-generated user ID
payload = {
"content": content,
"type": memory_type,
"metadata": metadata
}
async with aiohttp.ClientSession() as session:
async with session.post(
"https://memory.papr.ai/v1/memory",
headers=headers,
json=payload
) as response:
return await response.json()
# Example usage with any LLM framework
async def agent_with_memory(user_query: str, user_id: str):
# Retrieve relevant context from memory using Papr-generated user ID
memory_response = await search_papr_memory(user_query, user_id)
memories = memory_response.get("data", {}).get("memories", [])
# Create context from memories
context = ""
if memories:
context = "Relevant information from memory:\n"
for memory in memories[:3]: # Top 3 memories
context += f"- {memory['content']}\n"
# Use context with your LLM of choice
llm_response = await your_llm_call(f"{context}\n\nUser query: {user_query}")
# Store the interaction in memory
await add_papr_memory(
content=f"User question: {user_query}\nAgent response: {llm_response}",
user_id=user_id, # Papr-generated user ID
metadata={"conversation_type": "agent_interaction"}
)
return llm_response
# Example usage
response = await search_papr_memory("Find information about our latest product meeting", "usr_abc123") # Papr-generated user ID
print(f"Found {len(response.get('data', {}).get('memories', []))} memories")
Next Steps
Congratulations! You've learned the basics of working with Papr Memory, including how to create users and associate memories with them. Here's what to explore next:
- Core Concepts - Learn about memory types, embeddings, and knowledge graphs
- Guides:
- Authentication - Secure your Memory API requests
- Content Ingestion - Add documents, images, and structured data
- Search Tuning - Optimize memory search for your use case
- Batch Operations - Process data efficiently at scale
- API Reference - View the complete API documentation
- Tutorials - Build complete projects with our step-by-step tutorials
- SDKs and Tools - Get started with the Python and Typscript SDKs, or use Papr with an AI agent or langchain via a tool call or MCP server.