mem0ai/mem0 · error · ImportError

google-auth is required for GCP authentication. Install with

Error message

google-auth is required for GCP authentication. Install with: pip install google-auth

What it means

Raised at import time of mem0.utils.gcp_auth when the google-auth package is not installed. The module unconditionally imports google.oauth2.service_account and google.auth in a try/except and converts ImportError into this actionable message. Anything that pulls in a GCP-related provider (Vertex AI embedder, Vertex AI vector search, Gemini via service account) will fail at import with this error.

Source

Thrown at mem0/utils/gcp_auth.py:10

import os
import json
from typing import Optional, Dict, Any

try:
    from google.oauth2 import service_account
    from google.auth import default
    import google.auth.credentials
except ImportError:
    raise ImportError("google-auth is required for GCP authentication. Install with: pip install google-auth")


class GCPAuthenticator:
    """
    Centralized GCP authentication handler that supports multiple credential methods.

    Priority order:
    1. service_account_json (dict) - In-memory service account credentials
    2. credentials_path (str) - Path to service account JSON file
    3. Environment variables (GOOGLE_APPLICATION_CREDENTIALS)
    4. Default credentials (for environments like GCE, Cloud Run, etc.)
    """

    @staticmethod
    def get_credentials(
        service_account_json: Optional[Dict[str, Any]] = None,
        credentials_path: Optional[str] = None,
        scopes: Optional[list] = None

View on GitHub (pinned to 001c235229)

Solutions

pip install google-auth in the active environment
Better: install the provider's full extra, e.g. pip install 'mem0ai[google]' or add google-auth to requirements.txt alongside the vertexai packages
Verify with python -c "import google.oauth2.service_account"
If using Docker, rebuild the image after adding the dependency

Example fix

# before: ImportError: google-auth is required ...
from mem0 import Memory

# after
# pip install google-auth google-cloud-aiplatform
from mem0 import Memory

Defensive patterns

Strategy: validation

Validate before calling

import importlib.util
if importlib.util.find_spec('google.oauth2.service_account') is None:
    raise ConfigError('google-auth missing — pip install google-auth before using GCP providers')

Try / catch

try:
    from mem0.utils import gcp_auth
except ImportError as e:
    if 'google-auth is required' in str(e):
        raise ConfigError('add google-auth to requirements') from e
    raise

Prevention

Declare google-auth (and vertexai/genai) in requirements whenever GCP providers are configured
Fail dependency checks at container build time, not request time
Keep one requirements file per deployment target so extras are not forgotten

When it happens

Trigger: Importing mem0.embeddings.vertexai or mem0.vector_stores.vertex_ai_vector_search (which transitively import gcp_auth) in an environment without google-auth; a fresh install of mem0ai without extras; a CI image that only installs the core package.

Common situations: Using Vertex AI config without installing GCP extras; dependency conflicts where pip resolved google-auth out; multiple virtualenvs and running from the wrong one.

Understand the failure class

Authentication and authorization failures — expired tokens, bad credentials, and missing scopes.

Related errors

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/f763f5b0ec846511. Report an issue: GitHub.