chroma-core/chroma · error · ValueError

Missing 'api_key_env_var' or 'api_base' in configuration for

Error message

Missing 'api_key_env_var' or 'api_base' in configuration for BasetenEmbeddingFunction.

What it means

When a "baseten" embedding function is rebuilt from a persisted config, build_from_config requires both the "api_key_env_var" and "api_base" keys to be present (non-None); if either is missing it raises this ValueError naming both. Note that ef.get_config() always returns both keys, so a faithful round-trip never fails — the error indicates a hand-written, edited, or schema-drifted config dict.

Source

Thrown at chromadb/utils/embedding_functions/baseten_embedding_function.py:87

    def get_config(self) -> Dict[str, Any]:
        return {"api_base": self.api_base, "api_key_env_var": self.api_key_env_var}

    @staticmethod
    def build_from_config(config: Dict[str, Any]) -> "BasetenEmbeddingFunction":
        """
        Build the BasetenEmbeddingFunction from a configuration dictionary.

        Args:
            config (Dict[str, Any]): A dictionary containing the configuration parameters.
                                     Expected keys: 'api_key', 'api_base', 'api_key_env_var'.

        Returns:
            BasetenEmbeddingFunction: An instance of BasetenEmbeddingFunction.
        """
        api_key_env_var = config.get("api_key_env_var")
        api_base = config.get("api_base")
        if api_key_env_var is None or api_base is None:
            raise ValueError(
                "Missing 'api_key_env_var' or 'api_base' in configuration for BasetenEmbeddingFunction."
            )

        # Note: We rely on the __init__ method to handle potential missing api_key
        # by checking the environment variable if the config value is None.
        # However, api_base must be present either in config or have a default.
        if api_base is None:
            raise ValueError(
                "Missing 'api_base' in configuration for BasetenEmbeddingFunction."
            )

        return BasetenEmbeddingFunction(
            api_key=None,  # Pass None if not in config, __init__ will check env var
            api_base=api_base,
            api_key_env_var=api_key_env_var,
        )

    @staticmethod

View on GitHub (pinned to aecdd12c8a)

Solutions

1. Always generate the config via ef.get_config() and re-attach the name — it emits exactly the keys build_from_config expects.
2. If hand-writing, include both: {"name": "baseten", "config": {"api_base": "https://...", "api_key_env_var": "CHROMA_BASETEN_API_KEY"}}.
3. Validate the two required keys before calling and raise your own descriptive error.

Example fix

# before: ValueError "Missing 'api_key_env_var' or 'api_base' in configuration for BasetenEmbeddingFunction."
ef = config_to_embedding_function({"name": "baseten", "config": {"api_base": "https://app.baseten.co/..."}})

# after
ef = config_to_embedding_function({
    "name": "baseten",
    "config": {"api_base": "https://app.baseten.co/...", "api_key_env_var": "CHROMA_BASETEN_API_KEY"},
})

REQUIRED = {"api_key_env_var", "api_base"}

def validate_baseten_config(cfg: dict) -> None:
    missing = REQUIRED - set(cfg)
    if missing:
        raise ValueError(f"baseten config missing required keys: {sorted(missing)}")

validate_baseten_config(inner_cfg)
ef = config_to_embedding_function({"name": "baseten", "config": inner_cfg})

def is_complete_baseten_config(cfg: object) -> bool:
    return (
        isinstance(cfg, dict)
        and isinstance(cfg.get("api_base"), str)
        and isinstance(cfg.get("api_key_env_var"), str)
    )

from chromadb.utils.embedding_functions import config_to_embedding_function
try:
    ef = config_to_embedding_function(cfg)
except ValueError as e:
    if "Missing 'api_key_env_var' or 'api_base'" in str(e):
        cfg.setdefault("config", {}).setdefault("api_key_env_var", "CHROMA_BASETEN_API_KEY")
        ef = config_to_embedding_function(cfg)  # api_base still required from real config
    else:
        raise

When it happens

Trigger: config_to_embedding_function({"name": "baseten", "config": {"api_base": "..."}}) with api_key_env_var absent (or vice versa); configs from older versions or external stores missing the key.

Common situations: Hand-assembled config dicts; JSON configs edited by hand where one key was dropped; migrating persisted collection metadata between systems that trimmed fields.

Related errors

• Config must contain a 'name' field.
• Missing 'api_base' in configuration for BasetenEmbeddingFunc
• Unsupported embedding function: {name}
• The boto3 python package is not installed. Please install it
• The openai python package is not installed. Please install i

AI-assisted analysis of chroma-core/chroma@aecdd12c8a (2026-08-16). Data as JSON: /api/errors/064503d854b0bc5f. Report an issue: GitHub.