Advanced Retrieval

What is Advanced Retrieval?

Advanced Retrieval gives you precise control over how memories are found and ranked. While basic search uses semantic similarity, these advanced options help you find exactly what you need, when you need it.

Search Enhancement Options

Reranking

Reorders results using deep semantic understanding to put the most relevant memories first.

When to Use
How it Works
Performance

Need the most relevant result at the top
Result order is critical for your application
Want consistent quality across different queries
Building user-facing features where accuracy matters

Python

# Get the most relevant travel plans first
results = client.search(
    query="What are my upcoming travel plans?",
    rerank=True,
    filters={"user_id": "user123"},
)

# Before reranking:        After reranking:
# 1. "Went to Paris"   →   1. "Tokyo trip next month"
# 2. "Tokyo trip next" →   2. "Need to book hotel in Tokyo"  
# 3. "Need hotel"      →   3. "Went to Paris last year"

Real-World Use Cases

Personal AI Assistant
Customer Support
Healthcare AI
Learning Platform

Python

# Smart home assistant finding device preferences
results = client.search(
    query="How do I like my bedroom temperature?",
    rerank=True,           # Closest-matching preferences first
    filters={"user_id": "user123"},
)

# Finds: "Keep bedroom at 68°F", "Too cold last night at 65°F", etc.

Python

# Find specific product issues with high precision
results = client.search(
    query="Problems with premium subscription billing",
    filters={"user_id": "customer456"},
)

# Returns only relevant billing problems, not general questions

Python

# Critical medical information needs perfect accuracy
results = client.search(
    query="Patient allergies and contraindications",
    rerank=True,            # Most important info first
    filters={"user_id": "patient789"},
)

# Ensures critical allergy info appears first

Python

# Find learning progress for specific topics
results = client.search(
    query="Python programming progress and difficulties",
    rerank=True,           # Closest-matching progress notes first
    filters={"user_id": "student123"},
)

# Gets comprehensive view of Python learning journey

Choosing the Right Configuration

Recommended Configurations

rerank is the only lever here that changes result order. filters, top_k, and threshold change which memories come back, not how they’re ordered. The two functions below send the same query and filters; the only difference is the rerank flag.

# Fast path - use for exploratory search, or anywhere the user scans a list
# of results instead of trusting result #1 (dashboards, "show me everything
# about X" style queries). No reranking overhead.
def quick_search(query, user_id):
    return client.search(
        query=query,
        filters={"user_id": user_id},
    )

# Precision path - use when only the top result reaches the user, e.g. an
# agent that injects a single fact into a prompt. Reranking (see above)
# re-scores every match and moves the closest one to position 1, at the
# cost of ~150-200ms added latency.
def standard_search(query, user_id):
    return client.search(
        query=query,
        rerank=True,
        filters={"user_id": user_id},
    )

// Fast path - use for exploratory search, or anywhere the user scans a list
// of results instead of trusting result #1 (dashboards, "show me everything
// about X" style queries). No reranking overhead.
function quickSearch(query, userId) {
    return client.search(query, {
        filters: { user_id: userId },
    });
}

// Precision path - use when only the top result reaches the user, e.g. an
// agent that injects a single fact into a prompt. Reranking (see above)
// re-scores every match and moves the closest one to position 1, at the
// cost of ~150-200ms added latency.
function standardSearch(query, userId) {
    return client.search(query, {
        filters: { user_id: userId },
        rerank: true,
    });
}

What changes in the response: both calls return the same fields on each memory (see the Search Memories API reference for the full response shape). The only difference is the order of the results array, the same effect shown in the Reranking example above: quick_search returns results ranked by raw similarity, standard_search returns the reranked order.

Best Practices

Do

Start simple with basic search and measure impact before enabling reranking
Use reranking when the top result quality matters most
Monitor latency and adjust based on your application’s needs
Handle empty results gracefully

Don’t

Enable reranking by default without measuring necessity
Ignore latency impact in real-time applications
Use advanced retrieval for simple, fast lookup scenarios

Performance Guidelines

Latency Expectations

Python

# Performance monitoring example
import time

start_time = time.time()
results = client.search(
    query="user preferences",
    rerank=True,         # +150ms
    filters={"user_id": "user123"},
)
latency = time.time() - start_time
print(f"Search completed in {latency:.2f}s")

Optimization Tips

Cache frequent queries to avoid repeated advanced processing
Use session-specific search with run_id to reduce search space
Implement fallback logic when search returns empty results
Monitor and alert on search latency patterns

Discord

Join our community

GitHub

Ask questions on GitHub

Support

Talk to founders

Getting Started

Core Concepts

Features

Support

Migration

Advanced Retrieval

What is Advanced Retrieval?

Search Enhancement Options

Reranking

Real-World Use Cases

Choosing the Right Configuration

Recommended Configurations

Best Practices

Do

Don’t

Performance Guidelines

Latency Expectations

Optimization Tips

Discord

GitHub

Support

​What is Advanced Retrieval?

​Search Enhancement Options

​Reranking

​Real-World Use Cases

​Choosing the Right Configuration

​Recommended Configurations

​Best Practices

​Do

​Don’t

​Performance Guidelines

​Latency Expectations

​Optimization Tips

Discord

GitHub

Support

What is Advanced Retrieval?

Search Enhancement Options

Reranking

Real-World Use Cases

Choosing the Right Configuration

Recommended Configurations

Best Practices

Do

Don’t

Performance Guidelines

Latency Expectations

Optimization Tips