chroma-core/chroma · error · ValueError

The langchain_core python package is not installed. Please i

Error message

The langchain_core python package is not installed. Please install it with `pip install langchain-core`

What it means

ChromaLangchainEmbeddingFunction.__init__ imports langchain_core.embeddings to obtain the Embeddings interface used for the isinstance check; on ImportError it raises ValueError suggesting `pip install langchain-core`. langchain-core is an optional dependency — chromadb only requires it for this bridge adapter.

Source

Thrown at chromadb/utils/embedding_functions/chroma_langchain_embedding_function.py:46

class ChromaLangchainEmbeddingFunction(EmbeddingFunction[Embeddable]):
    """
    This class is used as bridge between langchain embedding functions and custom chroma embedding functions.
    """

    def __init__(self, embedding_function: Any) -> None:
        """
        Initialize the ChromaLangchainEmbeddingFunction

        Args:
            embedding_function: The embedding function implementing Embeddings from langchain_core.
        """
        try:
            import langchain_core.embeddings

            LangchainEmbeddings = langchain_core.embeddings.Embeddings
        except ImportError:
            raise ValueError(
                "The langchain_core python package is not installed. Please install it with `pip install langchain-core`"
            )

        if not isinstance(embedding_function, LangchainEmbeddings):
            raise ValueError(
                "The embedding_function must implement the Embeddings interface from langchain_core."
            )

        self.embedding_function = embedding_function

        # Store the class name for serialization
        self._embedding_function_class = embedding_function.__class__.__name__

    def embed_documents(self, documents: Sequence[str]) -> List[List[float]]:
        """
        Embed documents using the langchain embedding function.

        Args:

View on GitHub (pinned to aecdd12c8a)

Solutions

pip install langchain-core in the running environment.
Add langchain-core (and your provider package, e.g. langchain-openai) to pinned project dependencies.
If pip says it is installed, check `python -c "import langchain_core"` in the exact interpreter to rule out shadowing or a broken install.

Example fix

# before
from chromadb.utils.embedding_functions import create_langchain_embedding
ef = create_langchain_embedding(my_fn)  # ValueError: langchain_core not installed

# after (pip install langchain-core)
from langchain_openai import OpenAIEmbeddings
ef = create_langchain_embedding(OpenAIEmbeddings(model="text-embedding-3-large"))

Defensive patterns

Strategy: validation

Validate before calling

import importlib.util

if importlib.util.find_spec("langchain_core") is None:
    raise SystemExit("langchain-core required: pip install langchain-core")
ef = create_langchain_embedding(my_embeddings)

Try / catch

try:
    ef = create_langchain_embedding(my_embeddings)
except ValueError as e:
    if "langchain_core" in str(e):
        raise SystemExit("Install langchain-core (pip install langchain-core)") from e
    raise

Prevention

Pin langchain-core (plus provider packages) in requirements when using the bridge.
Check optional imports at startup rather than at first collection call.
Keep one package manager (pip or conda) per environment to avoid split installs.

When it happens

Trigger: Constructing ChromaLangchainEmbeddingFunction(embedding_function) or calling create_langchain_embedding(fn) where langchain_core is not importable in the current interpreter.

Common situations: Environments that installed only langchain-community or a full langchain meta-package version that dropped langchain-core; fresh venvs with just chromadb; prod images trimmed of optional deps.

Related errors

AI-assisted analysis of chroma-core/chroma@aecdd12c8a (2026-08-16). Data as JSON: /api/errors/2fbd11b3abe8b362. Report an issue: GitHub.