mem0ai/mem0 · error · ImportError

langchain is not installed. Please install it using `pip ins

Error message

langchain is not installed. Please install it using `pip install langchain`

What it means

mem0/embeddings/langchain.py imports langchain.embeddings.base.Embeddings inside try/except ImportError and re-raises with a pip hint when LangChain is missing. langchain is an optional dependency; selecting embedder provider='langchain' (or merely importing this module via the registry) without it fails at import time. Note the import path is the legacy langchain package — langchain-core alone may not satisfy it depending on version.

Source

Thrown at mem0/embeddings/langchain.py:9

from typing import Literal, Optional

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

try:
    from langchain.embeddings.base import Embeddings
except ImportError:
    raise ImportError("langchain is not installed. Please install it using `pip install langchain`")


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

        if self.config.model is None:
            raise ValueError("`model` parameter is required")

        if not isinstance(self.config.model, Embeddings):
            raise ValueError("`model` must be an instance of Embeddings")

        self.langchain_model = self.config.model

    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
        """
        Get the embedding for the given text using Langchain.

View on GitHub (pinned to 001c235229)

Solutions

1. pip install langchain
2. If you deliberately use only split packages, install the meta-package anyway (it re-exports Embeddings) or upgrade mem0ai where the import path may target langchain_core.embeddings
3. Verify in the runtime interpreter: <python> -c 'from langchain.embeddings.base import Embeddings'

Example fix

# before: ImportError at import time

# after
# shell:
pip install langchain

try:
    from langchain.embeddings.base import Embeddings  # noqa: F401
except ImportError:
    raise RuntimeError("langchain embedder requires: pip install langchain")

def is_langchain_embeddings(obj: object) -> bool:
    try:
        from langchain.embeddings.base import Embeddings
        return isinstance(obj, Embeddings)
    except ImportError:
        return False

When it happens

Trigger: embedder={'provider': 'langchain', 'config': {'model': SomeEmbeddings()}} without langchain installed; having only langchain-core or langchain-community installed; venv mismatch between install and run.

Common situations: Projects that migrated to the split langchain packages (langchain-core/community/openai) and no longer depend on the meta-package; CI caching an old env; poetry group not exported to requirements.

Related errors

• The 'boto3' library is required. Please install it using 'pi
• FastEmbed is not installed. Please install it using `pip in
• The 'upstash_vector' library is required. Please install it
• The 'langchain_community' library is required. Please instal
• Langchain embedder provider requires an initialized Langchai

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/3f40786f6c543af2. Report an issue: GitHub.