Description

The documentation shows this import statement under Example: Use Custom Memory Instances e.g FAISS as the VectorDB:

from crewai.memory.storage import LTMSQLiteStorage, RAGStorage

Which is incorrect and results in an import error.

Looking at the storage code, the correct imports should be:

from crewai.memory.storage.rag_storage import RAGStorage
from crewai.memory.storage.ltm_sqlite_storage.py import LTMSQLiteStorage

Steps to Reproduce

Attempt to import the classes using the example in the documentation:

from crewai.memory.storage import LTMSQLiteStorage, RAGStorage

Run your app and observe an import error.

Expected behavior

The app starts without import errors.

Screenshots/Code snippets

from crewai.memory.storage import RAGStorage

short_term_memory = ShortTermMemory(
    storage = RAGStorage(
            embedder_config={
                "provider": "openai",
                "config": {
                    "model": 'text-embedding-3-small'
                }
            },
            type="short_term",
            path="/my_crew1/"
        )
    ),
),

Operating System

Ubuntu 24.04

Python Version

3.12

crewAI Version

0.108

crewAI Tools Version

NA

Virtual Environment

Venv

Evidence

Possible Solution

Update the docs to show the correct import path.

Additional context

NA