OpenAI as default

[pjbruno327]

How do I remove OpenAI as the default for LLM and embeddings?

[dosubot[bot]]

🤖

Hey @pjbruno327, long time no see! Hope you're doing awesome. 😄

To unset OpenAI as the default for LLM and embeddings in LlamaIndex, you need to modify the resolve_embed_model function in the llama_index/core/embeddings/utils.py file.

Currently, the function sets OpenAI as the default embedding model when embed_model is set to "default". You can change this by setting a different embedding model as the default.

For example, if you want to set HuggingFace as the default, you can modify the function as follows:

def resolve_embed_model(
    embed_model: Optional[EmbedType] = None,
    callback_manager: Optional[CallbackManager] = None,
) -> BaseEmbedding:
    """Resolve embed model."""
    from llama_index.core.settings import Settings

    try:
        from llama_index.core.bridge.langchain import Embeddings as LCEmbeddings
    except ImportError:
        LCEmbeddings = None  # type: ignore

    if embed_model == "default":
        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"
                )

            cache_folder = os.path.join(get_cache_dir(), "models")
            os.makedirs(cache_folder, exist_ok=True)

            embed_model = HuggingFaceEmbedding(
                model_name=model_name, cache_folder=cache_folder
            )
        except ImportError:
            raise ImportError(
                "`llama-index-embeddings-huggingface` package not found, "
                "please run `pip install llama-index-embeddings-huggingface`"
            )
    # rest of the function

This modification will set HuggingFace as the default embedding model when embed_model is set to "default". Please ensure that you have the necessary HuggingFace package installed and the model you want to use is available.

You can find the resolve_embed_model function in the llama_index/core/embeddings/utils.py file in the LlamaIndex repository.

Sources

• llama-index-core/llama_index/core/embeddings/utils.py
• llama-index-core/llama_index/core/settings.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[pjbruno327]

@dosu-bot Can this be done with ollama and what would that look like