mem0ai/mem0 · error · ImportError

The 'boto3' library is required. Please install it using…

Error message

The 'boto3' library is required. Please install it using 'pip install boto3'.

What it means

mem0/embeddings/aws_bedrock.py wraps its boto3 import in try/except ImportError and re-raises with install instructions when boto3 is absent. This is a hard import-time failure: merely importing the module (e.g. via mem0's embeddings registry) fails without the AWS SDK. boto3 is an optional dependency, not installed with the core mem0ai package.

Solutions

pip install boto3 in the interpreter that runs the app
Add boto3 to your dependency manifest (requirements.txt / pyproject) so deploys install it
For Docker, ensure the RUN pip install step includes boto3 in the final image stage

Example fix

# before: ImportError raised at import

# after
# shell:
pip install boto3

Defensive patterns

Strategy: validation

Validate before calling

try:
    import boto3  # noqa: F401
except ImportError:
    raise RuntimeError("aws_bedrock embedder requires: pip install boto3")

Prevention

Pin boto3 in requirements alongside mem0ai when using aws_bedrock
Run a startup dependency check for every provider you configure

When it happens

Trigger: Configuring embedder={'provider': 'aws_bedrock'} without pip install boto3; running in a slim Docker image without the AWS SDK; a different virtualenv being active at runtime than at install time.

Common situations: CI pipelines installing only requirements.txt that lacks boto3; conda vs pip environment mismatch; local boto3 present but production image missing it.

Related errors

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/a22b9a945221e554. Report an issue: GitHub.

Appendix: source

Thrown at mem0/embeddings/aws_bedrock.py:8

import json
import os
from typing import Literal, Optional

try:
    import boto3
except ImportError:
    raise ImportError("The 'boto3' library is required. Please install it using 'pip install boto3'.")

import numpy as np

from mem0.configs.embeddings.base import BaseEmbedderConfig
from mem0.embeddings.base import EmbeddingBase


class AWSBedrockEmbedding(EmbeddingBase):
    """AWS Bedrock embedding implementation.

    This class uses AWS Bedrock's embedding models.
    """

    def __init__(self, config: Optional[BaseEmbedderConfig] = None):
        super().__init__(config)

        self.config.model = self.config.model or "amazon.titan-embed-text-v1"

View on GitHub (pinned to 001c235229)