run-llama/llama_index · critical · ImportError

`llama-index-embeddings-clip` package not found, please run

Error message

`llama-index-embeddings-clip` package not found, please run `pip install llama-index-embeddings-clip` and `pip install git+https://github.com/openai/CLIP.git`

What it means

Passing an embed_model string starting with 'clip' (e.g. 'clip:ViT-B/32') makes resolve_embed_model build a ClipEmbedding for multi-modal image embedding. That class lives in the optional llama-index-embeddings-clip integration plus OpenAI's CLIP repo, neither bundled with core — an ImportError is raised telling you exactly what to install.

Source

Thrown at llama-index-core/llama_index/core/embeddings/utils.py:87

                "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"):
        try:
            from llama_index.embeddings.clip import ClipEmbedding  # pants: no-infer-dep

            clip_model_name = (
                embed_model.split(":")[1] if ":" in embed_model else "ViT-B/32"
            )
            embed_model = ClipEmbedding(model_name=clip_model_name)
        except ImportError as e:
            raise ImportError(
                "`llama-index-embeddings-clip` package not found, "
                "please run `pip install llama-index-embeddings-clip` and `pip install git+https://github.com/openai/CLIP.git`"
            )

    if isinstance(embed_model, str):
        try:
            from llama_index.embeddings.huggingface import (
                HuggingFaceEmbedding,
            )  # pants: no-infer-dep

            splits = embed_model.split(":", 1)
            is_local = splits[0]
            model_name = splits[1] if len(splits) > 1 else None
            if is_local != "local":
                raise ValueError(
                    "embed_model must start with str 'local' or of type BaseEmbedding"
                )

View on GitHub (pinned to afd0fef371)

Solutions

1. pip install llama-index-embeddings-clip && pip install git+https://github.com/openai/CLIP.git
2. Alternatively switch to another multimodal embedding you already have installed and pass it as an instance
3. Pin CLIP install in requirements.txt so CI reproduces it

Example fix

// before
Settings.embed_model = "clip:ViT-B/32"  # ImportError

// after
# pip install llama-index-embeddings-clip
# pip install git+https://github.com/openai/CLIP.git
Settings.embed_model = "clip:ViT-B/32"

try:
    import llama_index.embeddings.clip  # noqa: F401
    has_clip = True
except ImportError:
    has_clip = False
embed_model = "clip:ViT-B/32" if has_clip else "local:BAAI/bge-small-en-v1.5"

try:
    Settings.embed_model = "clip:ViT-B/32"
except ImportError as e:
    if "llama-index-embeddings-clip" in str(e):
        raise RuntimeError("pip install llama-index-embeddings-clip and CLIP, or choose another model") from e
    raise

When it happens

Trigger: Settings.embed_model = 'clip' or 'clip:ViT-L/14' (or LlamaParse multimodal defaults using CLIP) without llama-index-embeddings-clip installed; fresh environment cloned from a project that relied on CLIP.

Common situations: Following multi-modal retrieval examples on a slim install; CI missing the extra; the CLIP git dependency failing to install on some platforms.

Related errors

• `llama-index-embeddings-openai` package not found, please ru
• `llama-index-embeddings-huggingface` package not found, plea
• `llama-index-embeddings-langchain` package not found, please
• Invalid Embedding name: {name}
• Unhandled shape {array.shape}.

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/9011b5988206b667. Report an issue: GitHub.