Rodrigo Rodriguez (Pragmatismo) 94107f828e - New docds.

2025-11-22 16:12:32 -03:00

5.8 KiB

Raw Blame History

REMEMBER

Store information in bot's long-term memory for future conversations.

Syntax

REMEMBER key, value

Parameters

Parameter	Type	Description
`key`	String	Memory key/identifier
`value`	String	Information to remember

Description

The REMEMBER keyword stores information persistently across conversations. Unlike session variables that expire, remembered data persists:

Across multiple conversations
Between user sessions
After bot restarts
Indefinitely until explicitly forgotten

This enables bots to build user profiles, track preferences, and maintain context over time.

Examples

Store User Preferences

name = HEAR "What's your name?"
REMEMBER "user_name", name
TALK "Nice to meet you, " + name + ". I'll remember that!"

Remember User Choices

language = HEAR "Preferred language? (English/Spanish/French)"
REMEMBER "preferred_language", language
TALK "I'll communicate in " + language + " from now on"

Build User Profile

REMEMBER "signup_date", TODAY()
REMEMBER "user_tier", "premium"
REMEMBER "last_contact", NOW()
REMEMBER "interaction_count", interaction_count + 1

Store Complex Information

' Store JSON-like data
preferences = "{theme: 'dark', notifications: true, timezone: 'EST'}"
REMEMBER "user_preferences", preferences

' Store lists
interests = "technology, science, sports"
REMEMBER "interests", interests

Retrieval

Use RECALL to retrieve remembered information:

' In a future conversation
name = RECALL("user_name")
IF name != "" THEN
    TALK "Welcome back, " + name + "!"
ELSE
    TALK "Hello! I don't think we've met before."
END IF

Memory Scope

Memories are scoped by:

User ID (each user has separate memory)
Bot ID (memories don't cross bots)
Optional namespace (for organizing memories)

Memory Management

List All Memories

memories = GET_ALL_MEMORIES()
FOR EACH memory IN memories
    PRINT memory.key + ": " + memory.value
NEXT

Forget Specific Memory

FORGET "temporary_data"

Clear All Memories

CLEAR_ALL_MEMORIES()
TALK "Memory wiped clean!"

Memory with Expiration

' Remember for 30 days
REMEMBER_TEMP "trial_status", "active", 30

Use Cases

Customer Service

' Remember customer issues
issue = HEAR "What problem are you experiencing?"
REMEMBER "last_issue", issue
REMEMBER "issue_date", TODAY()

' In follow-up conversation
last_issue = RECALL("last_issue")
IF last_issue != "" THEN
    TALK "Following up on your issue: " + last_issue
END IF

Personal Assistant

' Remember important dates
birthday = HEAR "When is your birthday?"
REMEMBER "birthday", birthday

' Check on birthday
IF TODAY() = RECALL("birthday") THEN
    TALK "Happy Birthday! 🎉"
END IF

Learning System

' Track user corrections
correction = HEAR "Actually, that's not correct..."
REMEMBER "correction_" + topic, correction
corrections_count = RECALL("total_corrections") + 1
REMEMBER "total_corrections", corrections_count

Preferences Tracking

' Remember communication preferences
IF time_of_day = "morning" AND response_time < 5 THEN
    REMEMBER "active_time", "morning"
END IF

preferred_channel = GET_CHANNEL()
REMEMBER "preferred_channel", preferred_channel

Performance Considerations

Memories are indexed for fast retrieval
Large values (>1MB) should be stored as files
Frequently accessed memories are cached
Memory operations are asynchronous

Privacy and Security

Data Protection

Memories are encrypted at rest
PII should be marked as sensitive
Comply with data retention policies
Support user data deletion requests

' Allow users to export their data
IF request = "export_my_data" THEN
    data = EXPORT_USER_MEMORIES()
    SEND_MAIL user_email, "Your Data", data
END IF

' Allow users to delete their data
IF request = "forget_me" THEN
    DELETE_USER_MEMORIES()
    TALK "Your data has been deleted"
END IF

Best Practices

Use descriptive keys: Make memory keys self-documenting
Validate before storing: Check data quality
Handle missing memories: Always check if memory exists
Organize with namespaces: Group related memories
Clean up old data: Remove outdated memories
Respect privacy: Ask permission for sensitive data
Document memories: Keep track of what's stored

Advanced Features

Structured Memory

' Store structured data
user_profile = CREATE_MAP()
user_profile["name"] = name
user_profile["age"] = age
user_profile["interests"] = interests
REMEMBER "profile", JSON_STRINGIFY(user_profile)

' Retrieve and parse
profile_json = RECALL("profile")
profile = JSON_PARSE(profile_json)

Memory Search

' Search memories by pattern
matching_memories = SEARCH_MEMORIES("pref_*")
FOR EACH mem IN matching_memories
    PRINT mem.key + ": " + mem.value
NEXT

Memory Analytics

' Track memory usage
stats = GET_MEMORY_STATS()
PRINT "Total memories: " + stats.count
PRINT "Storage used: " + stats.size_mb + "MB"
PRINT "Oldest memory: " + stats.oldest_date

Error Handling

TRY
    REMEMBER "important_data", data
CATCH "storage_full"
    ' Clean up old memories
    DELETE_OLD_MEMORIES(30)  ' Delete memories older than 30 days
    RETRY
CATCH "invalid_data"
    LOG "Cannot store invalid data"
END TRY

GET_BOT_MEMORY - Session-scoped memory
SET_BOT_MEMORY - Temporary memory
SET_USER - Set user context
SET_CONTEXT - Set conversation context

Implementation

Located in src/basic/keywords/remember.rs

Uses persistent storage (PostgreSQL) with caching layer (Redis) for performance.

5.8 KiB Raw Blame History