Retrieve User Memory

Find relevant user memories using semantic search and knowledge graph.

This endpoint performs parallel searches:

1. Semantic search in Weaviate across all stored user memories
2. Entity-based search in the knowledge graph for memory entities

Results from both sources are combined and ranked by relevance to provide comprehensive memory retrieval.

Hit the Try it button to try this API now in our playground. It’s the best way to check the full request and response in one place, customize your parameters, and generate ready-to-use code snippets.

Examples

API Request

curl -X POST "https://api.cortex.com/user_memory/retrieve_user_memory?tenant_id=company_123&sub_tenant_id=engineering_team&max_count=5" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "authentication preferences",
    "user_name": "John Doe"
  }'

Overview

The Retrieve User Memory endpoint performs semantic search through a user’s stored memories to find the most relevant information based on a query. This is the primary endpoint for accessing user memories in your AI applications, enabling context-aware responses and personalized interactions.

Functionality

• Semantic Search: Uses advanced vector search to find memories that are semantically similar to your query
• Relevance Ranking: Returns memories ranked by relevance to the search query
• Configurable Results: Control the number of memories returned with the max_count parameter
• Intelligent Selection: When max_count is set to 0, Cortex intelligently selects the best memories based on relevance and context
• Context-Aware: Finds memories that are contextually relevant, not just keyword matches
• Personalization: Optional user_name parameter enhances personalization by providing user context for more targeted memory retrieval

How Semantic Search Works

Unlike traditional keyword search, semantic search understands the meaning and context of your query. For example:

• Query: “authentication preferences”
• Will find memories about: “JWT tokens”, “login methods”, “security settings”, etc.
• Even if the exact words don’t match

Use Cases

• Context Retrieval: Get relevant user context before generating AI responses
• Personalization: Find user preferences and past interactions for tailored experiences
• Memory-Based Chat: Enable AI to reference past conversations and user history
• Recommendation Systems: Use user memories to provide personalized recommendations
• Customer Support: Access user history and preferences for better support

Response

{
  "success": true,
  "user_memories": [
    {
      "source_id": "mem_001_abc123",
      "source_content": "User prefers JWT tokens over session-based authentication for microservices"
    },
    {
      "source_id": "mem_002_def456", 
      "source_content": "User values stateless authentication approaches"
    },
    {
      "source_id": "mem_003_ghi789",
      "source_content": "User understands the importance of rate limiting for security"
    }
  ]
}

Advanced Usage: Context-Aware AI Response

# First, retrieve relevant memories
curl -X POST "https://api.cortex.com/user_memory/retrieve_user_memory?tenant_id=company_123&sub_tenant_id=product_team&max_count=3" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "user onboarding feedback",
    "user_name": "Sarah Johnson"
  }'

# Then use these memories to generate a personalized response

Different Query Examples

# Find communication preferences
curl -X POST "https://api.cortex.com/user_memory/retrieve_user_memory?tenant_id=company_123&sub_tenant_id=marketing_team&max_count=2" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "communication style preferences",
    "user_name": "Mike Chen"
  }'

# Find technical expertise areas  
curl -X POST "https://api.cortex.com/user_memory/retrieve_user_memory?tenant_id=company_123&sub_tenant_id=engineering_team&max_count=5" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "technical skills and experience",
    "user_name": "Alex Rodriguez"
  }'

# Find project-related memories
curl -X POST "https://api.cortex.com/user_memory/retrieve_user_memory?tenant_id=company_123&sub_tenant_id=product_team&max_count=3" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "current project work",
    "user_name": "Emma Wilson"
  }'

### Intelligent Selection (max_count=0)

When you want Cortex to intelligently select the most relevant memories without specifying a count:

```bash
curl -X POST "https://api.cortex.com/user_memory/retrieve_user_memory?tenant_id=company_123&sub_tenant_id=engineering_team&max_count=0" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "authentication preferences",
    "user_name": "David Kim"
  }'

With max_count=0, Cortex will analyze all available memories and return only the most relevant ones based on semantic similarity and contextual relevance, automatically determining the optimal number of memories to return.

Important Notes

Automatic Tenant Provisioning: If you receive an error stating “Tenant-id/sub-tenant-id combination either does not exist or is not provisioned for user memory”, this means the tenant/sub-tenant combination hasn’t been set up for user memory functionality yet. This will be automatically provisioned when you add or generate your first user memory for this combination.

Empty Results: If no relevant memories are found, the endpoint returns an empty array. This is normal for new users or when searching for topics not covered in existing memories.

Query Optimization:

• Be specific about the type of information you’re looking for
• Consider using synonyms or related terms if initial queries don’t return results
• Shorter, focused queries often work better than long, complex ones
• Include the user_name parameter for enhanced personalization and more targeted memory retrieval

Pro Tip: This API is most powerful when used in combination with other user memory APIs. Use Generate User Memory to create memories from user interactions, then use this API to retrieve relevant context for future interactions.

Error Responses

All endpoints return consistent error responses following the standard format. For detailed error information, see our Error Responses documentation.

Authorizations

Authorization · string · header · required

Query Parameters

tenant_id · string · required

Example:

sub_tenant_id · string · default: ""

Example:

max_count · integer · default: 5

Required range: 0 <= x <= 50

Example:

Body

application/json

query · string · required

Example:

user_name · string · default: ""

Example:

Response

200

application/json

success · boolean · required

Example:

retrieved_user_memories · UserMemory · object[]

Show child attributes

Example:

relations · ScoredPathResponse · object[]

Show child attributes

Example: