crewAIInc/crewAI · error · ImportError

sqlalchemy is not installed. Please install it with `pip ins

Error message

sqlalchemy is not installed. Please install it with `pip install crewai-tools[sqlalchemy]`

What it means

NL2SQLTool depends on SQLAlchemy to introspect the database; the module probes for it at import time (SQLALCHEMY_AVAILABLE) and raises this ImportError in model_post_init when the probe failed. The message points at the crewai-tools[sqlalchemy] extra rather than plain sqlalchemy because the extra pins a tested version.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/nl2sql/nl2sql_tool.py:267

    tables: list[dict[str, Any]] = Field(default_factory=list)
    columns: dict[str, list[dict[str, Any]] | str] = Field(default_factory=dict)
    args_schema: type[BaseModel] = NL2SQLToolInput

    @model_validator(mode="after")
    def _apply_env_override(self) -> Self:
        """Allow CREWAI_NL2SQL_ALLOW_DML=true to override allow_dml at runtime."""
        if os.environ.get("CREWAI_NL2SQL_ALLOW_DML", "").strip().lower() == "true":
            if not self.allow_dml:
                logger.warning(
                    "NL2SQLTool: CREWAI_NL2SQL_ALLOW_DML env var is set — "
                    "DML/DDL operations are enabled. Ensure this is intentional."
                )
            self.allow_dml = True
        return self

    def model_post_init(self, __context: Any) -> None:
        if not SQLALCHEMY_AVAILABLE:
            raise ImportError(
                "sqlalchemy is not installed. Please install it with "
                "`pip install crewai-tools[sqlalchemy]`"
            )

        if self.allow_dml:
            logger.warning(
                "NL2SQLTool: allow_dml=True — write operations (INSERT/UPDATE/"
                "DELETE/DROP/…) are permitted. Use with caution."
            )

        data: dict[str, list[dict[str, Any]] | str] = {}
        result = self._fetch_available_tables()
        if isinstance(result, str):
            raise RuntimeError(f"Failed to fetch tables: {result}")
        tables: list[dict[str, Any]] = result

        for table in tables:
            table_columns = self._fetch_all_available_columns(table["table_name"])

View on GitHub (pinned to 754d7323be)

Solutions

1. Install the extra: `pip install "crewai-tools[sqlalchemy]"` (or `uv add 'crewai-tools[sqlalchemy]'`)
2. Failing that, `pip install sqlalchemy` — then verify `python -c "import sqlalchemy"`
3. Add the extra to your pyproject/requirements so rebuilds keep it

Example fix

# before
tool = NL2SQLTool(db_uri="mysql+pymysql://u:p@h/db")  # ImportError

# after
# pip install "crewai-tools[sqlalchemy]"
tool = NL2SQLTool(db_uri="mysql+pymysql://u:p@h/db")

def sqlalchemy_available() -> bool:
    try:
        import sqlalchemy  # noqa: F401
        return True
    except ImportError:
        return False

assert sqlalchemy_available(), 'pip install "crewai-tools[sqlalchemy]"'

try:
    tool = NL2SQLTool(db_uri=uri)
except ImportError as e:
    if "sqlalchemy" in str(e):
        raise SystemExit('Install: pip install "crewai-tools[sqlalchemy]"') from e
    raise

When it happens

Trigger: Constructing NL2SQLTool(db_uri=...) without sqlalchemy installed; a broken/partial sqlalchemy install that fails import; installing crewai-tools without extras in a slim container.

Common situations: Minimal Docker images; adding crewai-tools to an existing project without the sql extras; sqlalchemy uninstalled accidentally by a dependency resolver conflict.

Related errors

• The 'tavily-python' package is required. 'click' and 'subpro
• The 'tavily-python' package is required. 'click' and 'subpro
• The 'tavily-python' package is required. 'click' and 'subpro
• The 'tavily-python' package is required. 'click' and 'subpro
• This subcommand requires the full crewai package. Install it

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/59f40d39b8ae1fcd. Report an issue: GitHub.