langchain-ai/langchain · error · ValueError

Loading {config_type} prompt not supported

Error message

Loading {config_type} prompt not supported

What it means

`load_prompt_from_config` looks up the config's `_type` key in `type_to_loader_dict`, which only contains `prompt`, `few_shot`, and `chat`. Any other `_type` (or a typo) raises `ValueError: Loading {config_type} prompt not supported`. Note the loader set is intentionally small in core; richer prompt types were supported by legacy `langchain` loaders.

Source

Thrown at libs/core/langchain_core/prompts/loading.py:80

        allow_dangerous_paths: If `False` (default), file paths in the
            config (such as `template_path`, `examples`, and
            `example_prompt_path`) are validated to reject absolute paths
            and directory traversal (`..`) sequences. Set to `True` only
            if you trust the source of the config.

    Returns:
        A `PromptTemplate` object.

    Raises:
        ValueError: If the prompt type is not supported.
    """
    if "_type" not in config:
        logger.warning("No `_type` key found, defaulting to `prompt`.")
    config_type = config.pop("_type", "prompt")

    if config_type not in type_to_loader_dict:
        msg = f"Loading {config_type} prompt not supported"
        raise ValueError(msg)

    prompt_loader = type_to_loader_dict[config_type]
    return prompt_loader(config, allow_dangerous_paths=allow_dangerous_paths)


def _load_template(
    var_name: str, config: dict[str, Any], *, allow_dangerous_paths: bool = False
) -> dict[str, Any]:
    """Load template from the path if applicable."""
    # Check if template_path exists in config.
    if f"{var_name}_path" in config:
        # If it does, make sure template variable doesn't also exist.
        if var_name in config:
            msg = f"Both `{var_name}_path` and `{var_name}` cannot be provided."
            raise ValueError(msg)
        # Pop the template path from the config.
        template_path = Path(config.pop(f"{var_name}_path"))
        if not allow_dangerous_paths:

View on GitHub (pinned to e32fa9a52e)

Solutions

1. Change `_type` to one of the supported values: `prompt`, `few_shot`, or `chat`.
2. Rebuild the prompt programmatically (e.g. `PromptTemplate.from_template(...)` or `ChatPromptTemplate.from_messages(...)`) and serialize with `dumpd`/`dumps` from `langchain_core.load` instead.
3. If the config came from the deprecated Hub format, re-create it on LangSmith Hub and pull from there.

Example fix

# before
# config.json: {"_type": "prompt_with_format", "template": "Hi {name}"}
load_prompt('config.json')  # ValueError

# after
# config.json: {"_type": "prompt", "template": "Hi {name}", "input_variables": ["name"]}
load_prompt('config.json')

import json
SUPPORTED = {'prompt', 'few_shot', 'chat'}
config = json.loads(Path('prompt.json').read_text())
if config.get('_type', 'prompt') not in SUPPORTED:
    raise ValueError(f"unsupported _type {config.get('_type')!r}; expected one of {SUPPORTED}")
load_prompt('prompt.json')

def is_supported_prompt_type(config: dict) -> bool:
    return config.get('_type', 'prompt') in {'prompt', 'few_shot', 'chat'}

When it happens

Trigger: Loading a config JSON with `"_type": "prompt_with_format"`, `"_type": "pipeline"`, or any string not in {prompt, few_shot, chat}. Also triggered when `_type` is missing — it defaults to `prompt` only via a warning, but an explicit unknown value always fails.

Common situations: Loading prompt files exported from old langchain versions or the Hub that used extended types; hand-written configs with guessed type names; team configs that assumed legacy loader support.

Related errors

• Both `{var_name}_path` and `{var_name}` cannot be provided.
• Unsupported template file format: '{resolved_path.suffix}'.
• Invalid examples format. Only list or string are supported.
• Unsupported output parser {output_parser_type}
• Only one of example_prompt and example_prompt_path should be

AI-assisted analysis of langchain-ai/langchain@e32fa9a52e (2026-08-14). Data as JSON: /api/errors/fb3e71f2dd511840. Report an issue: GitHub.