mem0ai/mem0 · critical · ImportError
langchain_aws is not installed. Please install it using pip
Error message
langchain_aws is not installed. Please install it using pip install langchain_aws
What it means
Import-time ImportError from the Neptune Analytics vector store module: it needs langchain_aws (which provides NeptuneAnalyticsGraph) and the import guard fires the moment the module is loaded without it. No AWS call is made; the backend simply cannot be constructed.
Source
Thrown at mem0/vector_stores/neptune_analytics.py:12
import logging
import re
import time
import uuid
from typing import Any, Dict, List, Optional
from pydantic import BaseModel
try:
from langchain_aws import NeptuneAnalyticsGraph
except ImportError:
raise ImportError("langchain_aws is not installed. Please install it using pip install langchain_aws")
from mem0.vector_stores.base import VectorStoreBase
logger = logging.getLogger(__name__)
_SAFE_FILTER_KEY = re.compile(r"^[a-zA-Z_~][a-zA-Z0-9_]*$")
_VALID_IDENTIFIER = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
def _validate_filter(key: str, value: Any) -> None:
if not isinstance(key, str) or not _SAFE_FILTER_KEY.match(key):
raise ValueError(f"Invalid filter key: {key!r}")
if not isinstance(value, (str, int, float, bool)):
raise ValueError(
f"Filter value for {key!r} must be str, int, float, or bool, "
f"got {type(value).__name__}"
)
View on GitHub (pinned to 001c235229)
Solutions
- pip install langchain-aws
- Verify the package actually resolves (pip show langchain-aws) and pin it in the deploy environment
- If Neptune is not intended, switch the vector store provider in the Mem0 config back to the one you use
Example fix
# before pip install mem0ai # provider neptune_analytics -> ImportError # after pip install mem0ai langchain-aws
Defensive patterns
Strategy: validation
Validate before calling
try:
from langchain_aws import NeptuneAnalyticsGraph # noqa
except ImportError:
raise SystemExit("langchain-aws required: pip install langchain-aws") Prevention
- Install langchain-aws in the deploy image when Neptune Analytics is configured
- Add a config-driven dependency check to CI (provider -> required package matrix)
- Keep a lockfile entry for langchain-aws so pruning tools cannot drop it
When it happens
Trigger: Setting vector_store.provider to neptune_analytics ("neptune" family config) without langchain_aws installed; importing mem0.vector_stores.neptune_analytics in tooling/tests on an environment missing the extra.
Common situations: Base pip install mem0ai plus a Neptune config copied from docs; lambda/container images that prune 'unused' deps; version drift where langchain_aws was replaced by langchain-aws variants or removed from requirements.
Related errors
- The 'boto3' library is required. Please install it using 'pi
- Neptune Analytics vector store requires graphIdentifier or e
- Neptune Analytics HTTPS endpoints require graphIdentifier; p
- ${key} filter value must be an array.
- $not filter value must be an array.
AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15).
Data as JSON: /api/errors/ffe3c41a165f48c3.
Report an issue: GitHub.