run-llama/llama_index · critical · ImportError

`llama-index-embeddings-openai` package not found, please ru

Error message

`llama-index-embeddings-openai` package not found, please run `pip install llama-index-embeddings-openai`

What it means

resolve_embed_model() falls back to OpenAIEmbedding when embed_model is None or the string 'default'. That requires the optional integration llama-index-embeddings-openai; since llama-index v0.10 the OpenAI integration is no longer a core dependency, so a bare install raises this ImportError telling you to install it.

Source

Thrown at llama-index-core/llama_index/core/embeddings/utils.py:60

    if embed_model == "default":
        if os.getenv("IS_TESTING"):
            embed_model = MockEmbedding(embed_dim=8)
            embed_model.callback_manager = callback_manager or Settings.callback_manager
            return embed_model

        try:
            from llama_index.embeddings.openai import (
                OpenAIEmbedding,
            )  # pants: no-infer-dep

            from llama_index.embeddings.openai.utils import (
                validate_openai_api_key,
            )  # pants: no-infer-dep

            embed_model = OpenAIEmbedding()
            validate_openai_api_key(embed_model.api_key)  # type: ignore
        except ImportError:
            raise ImportError(
                "`llama-index-embeddings-openai` package not found, "
                "please run `pip install llama-index-embeddings-openai`"
            )
        except ValueError as e:
            raise ValueError(
                "\n******\n"
                "Could not load OpenAI embedding model. "
                "If you intended to use OpenAI, please check your OPENAI_API_KEY.\n"
                "Original error:\n"
                f"{e!s}"
                "\nConsider using embed_model='local'.\n"
                "Visit our documentation for more embedding options: "
                "https://developers.llamaindex.ai/python/framework/module_guides/"
                "models/embeddings/"
                "\n******"
            )
    # for image multi-modal embeddings
    elif isinstance(embed_model, str) and embed_model.startswith("clip"):

View on GitHub (pinned to afd0fef371)

Solutions

1. pip install llama-index-embeddings-openai (or the meta-package pip install llama-index)
2. Or run fully offline: pass embed_model='local:BAAI/bge-small-en-v1.5' with llama-index-embeddings-huggingface installed
3. Or pass any explicit BaseEmbedding instance (e.g. HuggingFaceEmbedding) so the OpenAI default is never reached

Example fix

// before
index = VectorStoreIndex.from_documents(docs)  # ImportError: package not found

// after
# pip install llama-index-embeddings-openai
index = VectorStoreIndex.from_documents(docs)
# or offline:
# pip install llama-index-embeddings-huggingface
index = VectorStoreIndex.from_documents(docs, embed_model="local:BAAI/bge-small-en-v1.5")

try:
    import llama_index.embeddings.openai  # noqa: F401
    has_openai = True
except ImportError:
    has_openai = False
if not has_openai and embed_model is None:
    embed_model = "local:BAAI/bge-small-en-v1.5"  # explicit, no default surprise

try:
    index = VectorStoreIndex.from_documents(docs)
except ImportError as e:
    if "llama-index-embeddings-openai" in str(e):
        raise RuntimeError("pip install llama-index-embeddings-openai or set embed_model") from e
    raise

When it happens

Trigger: Constructing any index/retriever (VectorStoreIndex.from_documents(...)) without an embed_model argument on an environment where llama-index-embeddings-openai is not installed; a fresh pip install llama-index-core only.

Common situations: Installing the modular llama-index post-0.10 without integration extras; CI or Docker images slimmed to core only; upgrading from llama_index<=0.9 (bundled OpenAI) to the split packages.

Related errors

• `llama-index-embeddings-clip` package not found, please run
• `llama-index-embeddings-huggingface` package not found, plea
• `llama-index-embeddings-langchain` package not found, please
• Invalid Embedding name: {name}
• ****** Could not load OpenAI embedding model. If you intend

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/955720201afaa04f. Report an issue: GitHub.