run-llama/llama_index · error · 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

Error "`llama-index-embeddings-openai` package not found, please run `pip install llama-index-embeddings-openai`" thrown in run-llama/llama_index.

Source

Thrown at llama-index-core/llama_index/core/node_parser/text/semantic_splitter.py:107

        sentence_splitter: Optional[Callable[[str], List[str]]] = None,
        original_text_metadata_key: str = DEFAULT_OG_TEXT_METADATA_KEY,
        include_metadata: bool = True,
        include_prev_next_rel: bool = True,
        callback_manager: Optional[CallbackManager] = None,
        id_func: Optional[Callable[[int, Document], str]] = None,
    ) -> "SemanticSplitterNodeParser":
        callback_manager = callback_manager or CallbackManager([])

        sentence_splitter = sentence_splitter or split_by_sentence_tokenizer()
        if embed_model is None:
            try:
                from llama_index.embeddings.openai import (
                    OpenAIEmbedding,
                )  # pants: no-infer-dep

                embed_model = embed_model or OpenAIEmbedding()
            except ImportError:
                raise ImportError(
                    "`llama-index-embeddings-openai` package not found, "
                    "please run `pip install llama-index-embeddings-openai`"
                )

        id_func = id_func or default_id_func

        return cls(
            embed_model=embed_model,
            breakpoint_percentile_threshold=breakpoint_percentile_threshold,
            buffer_size=buffer_size,
            sentence_splitter=sentence_splitter,
            original_text_metadata_key=original_text_metadata_key,
            include_metadata=include_metadata,
            include_prev_next_rel=include_prev_next_rel,
            callback_manager=callback_manager,
            id_func=id_func,
        )

View on GitHub (pinned to afd0fef371)

Solutions

1. Install the package: `pip install llama-index-embeddings-openai`.
2. Pass a different embed_model that does not require the OpenAI embeddings integration.

When it happens

Trigger: Thrown at llama-index-core/llama_index/core/node_parser/text/semantic_splitter.py:107 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/e7f11fcfe3d50b88. Report an issue: GitHub.