langchain-ai/langchain · error · ValueError

Expected {package} version to be <= {lte_version}. Received

Error message

Expected {package} version to be <= {lte_version}. Received {imported_version}.

What it means

Raised by `check_package_version` in `langchain_core.utils.utils` for the inclusive upper bound: the installed `package` version is strictly greater than `lte_version`. This is the same ceiling guard as the `<` variant, but the boundary version itself is allowed (e.g. `lte_version="1.2.3"` accepts 1.2.3, rejects 1.2.4+). It fails at import/first use of the guarded integration.

Source

Thrown at libs/core/langchain_core/utils/utils.py:178

        gte_version: The version must be greater than or equal to this.


    Raises:
        ValueError: If the package version does not meet the requirements.
    """
    imported_version = parse(version(package))
    if lt_version is not None and imported_version >= parse(lt_version):
        msg = (
            f"Expected {package} version to be < {lt_version}. Received "
            f"{imported_version}."
        )
        raise ValueError(msg)
    if lte_version is not None and imported_version > parse(lte_version):
        msg = (
            f"Expected {package} version to be <= {lte_version}. Received "
            f"{imported_version}."
        )
        raise ValueError(msg)
    if gt_version is not None and imported_version <= parse(gt_version):
        msg = (
            f"Expected {package} version to be > {gt_version}. Received "
            f"{imported_version}."
        )
        raise ValueError(msg)
    if gte_version is not None and imported_version < parse(gte_version):
        msg = (
            f"Expected {package} version to be >= {gte_version}. Received "
            f"{imported_version}."
        )
        raise ValueError(msg)


def get_pydantic_field_names(pydantic_cls: Any) -> set[str]:
    """Get field names, including aliases, for a pydantic class.

    Args:

View on GitHub (pinned to e32fa9a52e)

Solutions

  1. Pin the dependency at or below the boundary from the message (`pip install "pkg<=X"`), or better, exact-pin to the lockfile version.
  2. Upgrade the LangChain integration package to a release compatible with the newer dependency.
  3. In monorepos, run `uv sync` against the committed lockfile instead of resolving fresh.

Example fix

# before
# ValueError: Expected openai version to be <= 1.40.0. Received 1.55.1.

# after (terminal)
# pip install "openai<=1.40.0"
# or: pip install -U langchain-openai  (integration supporting newer openai)
Defensive patterns

Strategy: validation

Validate before calling

from packaging.version import Version

def version_lte(pkg: str, ceiling: str) -> bool:
    return Version(importlib.metadata.version(pkg)) <= Version(ceiling)

if not version_lte("openai", "1.40.0"):
    raise RuntimeError("openai too new for this integration; pin or upgrade integration")

Try / catch

try:
    check_package_version(pkg, lte_version=ceiling)
except ValueError as e:
    raise RuntimeError(f"dependency ceiling violated: {e}") from e

Prevention

When it happens

Trigger: `check_package_version(pkg, lte_version=X)` runs with an installed version above X — typically after upgrading the dependency (e.g. `openai` SDK or `pydantic`) past the last version the installed LangChain integration was validated against.

Common situations: Fresh environments installing newest dependency versions alongside older pinned LangChain releases; Dependabot-style automated upgrades; local development on the dependency's new major while the integration expects the previous one.

Related errors

AI-assisted analysis of langchain-ai/langchain@e32fa9a52e (2026-08-14). Data as JSON: /api/errors/4428c9f6dd6e15ff. Report an issue: GitHub.