mem0ai/mem0 · error · ValueError

Unknown provider_override '{explicit_provider}'. Valid provi

Error message

Unknown provider_override '{explicit_provider}'. Valid providers: {', '.join(PROVIDERS)}

What it means

Raised by extract_provider() when config.provider_override (or the explicit_provider argument) is set to a string not in the module's PROVIDERS allowlist (ai21, amazon, anthropic, cohere, meta, mistral, stability, writer, deepseek, gpt-oss, perplexity, snowflake, titan, command, j2, llama, minimax). The override exists to disambiguate model IDs; an unrecognized value is rejected before any AWS call.

Source

Thrown at mem0/llms/aws_bedrock.py:30

from mem0.configs.llms.aws_bedrock import AWSBedrockConfig
from mem0.configs.llms.base import BaseLlmConfig
from mem0.llms.base import LLMBase
from mem0.memory.utils import extract_json

logger = logging.getLogger(__name__)

PROVIDERS = [
    "ai21", "amazon", "anthropic", "cohere", "meta", "mistral", "stability", "writer",
    "deepseek", "gpt-oss", "perplexity", "snowflake", "titan", "command", "j2", "llama",
    "minimax",
]


def extract_provider(model: str, explicit_provider: Optional[str] = None) -> str:
    """Extract provider from model identifier, or return explicit_provider when set."""
    if explicit_provider:
        if explicit_provider not in PROVIDERS:
            raise ValueError(
                f"Unknown provider_override '{explicit_provider}'. Valid providers: {', '.join(PROVIDERS)}"
            )
        return explicit_provider
    for provider in PROVIDERS:
        if re.search(rf"\b{re.escape(provider)}\b", model):
            return provider
    raise ValueError(f"Unknown provider in model: {model}")


class AWSBedrockLLM(LLMBase):
    """
    AWS Bedrock LLM integration for Mem0.

    Supports all available Bedrock models with automatic provider detection.
    """

    def __init__(self, config: Optional[Union[AWSBedrockConfig, BaseLlmConfig, Dict]] = None):
        """

View on GitHub (pinned to 001c235229)

Solutions

1. Use the exact lowercase provider key from the error message's valid list (e.g. anthropic, amazon, mistral)
2. Remove provider_override entirely and let automatic detection infer the provider from the model ID prefix
3. Upgrade mem0ai if the provider you need was added in a later version of the allowlist

Example fix

// before
{"llm": {"provider": "aws_bedrock", "config": {"model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "provider_override": "Anthropic"}}}  # ValueError

# after
{"llm": {"provider": "aws_bedrock", "config": {"model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "provider_override": "anthropic"}}}

PROVIDERS = {"ai21","amazon","anthropic","cohere","meta","mistral","stability","writer",
             "deepseek","gpt-oss","perplexity","snowflake","titan","command","j2","llama","minimax"}
override = llm_config.get("provider_override")
if override is not None:
    assert override.lower() in PROVIDERS, f"provider_override must be one of {sorted(PROVIDERS)}"

PROVIDERS = {"ai21","amazon","anthropic","cohere","meta","mistral","stability","writer",
             "deepseek","gpt-oss","perplexity","snowflake","titan","command","j2","llama","minimax"}

def is_valid_provider_override(p: str) -> bool:
    return p in PROVIDERS

try:
    llm = AWSBedrockLLM(config)
except ValueError as e:
    if "provider_override" in str(e):
        config["provider_override"] = config["provider_override"].lower()
        llm = AWSBedrockLLM(config)  # retry with normalized casing
    else:
        raise

When it happens

Trigger: Setting provider_override: "Anthropic" (wrong case), "bedrock", "openai", or a typo like "anthrpoic" in the LLM config; passing an unsupported new provider name before this mem0 version's allowlist includes it.

Common situations: Copy-pasting provider names from AWS console ARNs; case-sensitive mismatch; expecting a provider added in a newer mem0 release while running an older one.

Related errors

• Unknown provider in model: {model}
• The 'boto3' library is required. Please install it using 'pi
• AWS credentials not found. Please set AWS_ACCESS_KEY_ID, AWS
• Unauthorized access to Bedrock. Please ensure your AWS crede
• AWS Bedrock error: {e}

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/8d8ed627035cc55a. Report an issue: GitHub.