mem0ai/mem0 · error · ImportError

FastEmbed is not installed. Please install it using `pip in

Error message

FastEmbed is not installed.  Please install it using `pip install fastembed`

What it means

mem0/embeddings/fastembed.py imports fastembed.TextEmbedding inside try/except ImportError and re-raises with a pip hint. fastembed is an optional dependency (installable via the mem0ai[fastembed] extra or directly), so selecting provider='fastembed' without the package fails at import time — before any config validation runs.

Source

Thrown at mem0/embeddings/fastembed.py:9

from typing import Literal, Optional

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

try:
    from fastembed import TextEmbedding
except ImportError:
    raise ImportError("FastEmbed is not installed.  Please install it using `pip install fastembed`")

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

        self.config.model = self.config.model or "thenlper/gte-large"
        self.dense_model = TextEmbedding(model_name=self.config.model)

        if not self.config.embedding_dims:
            self.config.embedding_dims = self.dense_model.embedding_size

    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
        """
        Convert the text to embeddings using FastEmbed running in the Onnx runtime
        Args:
            text (str): The text to embed.
            memory_action (optional): The type of embedding to use. Must be one of "add", "search", or "update". Defaults to None.
        Returns:

View on GitHub (pinned to 001c235229)

Solutions

1. pip install fastembed
2. Install via the extra: pip install 'mem0ai[fastembed]' so the pairing stays consistent
3. Verify in the runtime interpreter: <python> -c 'import fastembed'

Example fix

# before: ImportError at import time

# after
# shell:
pip install fastembed

try:
    from fastembed import TextEmbedding  # noqa: F401
except ImportError:
    raise RuntimeError("fastembed embedder requires: pip install fastembed")

When it happens

Trigger: embedder={'provider': 'fastembed', ...} with fastembed not installed; installing with pip but running under a different Python (e.g. system python vs venv); a fresh clone where only mem0ai core was installed.

Common situations: pip install mem0ai does not include fastembed; onnxruntime/platform wheels missing on ARM or slim images making fastembed uninstallable; uv/poetry lockfile without the extra.

Related errors

• The 'boto3' library is required. Please install it using 'pi
• langchain is not installed. Please install it using `pip ins
• The 'upstash_vector' library is required. Please install it
• Unsupported FastEmbed model "${config.model}". Supported mod
• FastEmbed embed() returned no embeddings

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/2511dc564404d949. Report an issue: GitHub.