I'm looking to create Settings.embed

At a glance

The community member is looking to set Settings.embed_model=bm25 but based on the provided knowledge sources, there is no information about using bm25 as an embedding model in LlamaIndex. The examples provided use different embedding models such as HuggingFaceEmbedding, GradientEmbedding, and OpenAIEmbedding. The community members suggest checking the official LlamaIndex documentation or reaching out to their support for more information on how to properly configure a different embedding model like bm25.

ddkatz123

I'm looking to create Settings.embed_model=bm25. How would I do that?

5 comments

kkapa.ai

Please stand by @dkatz123 as I search the knowledge base. I normally take about 20 seconds or so. :wave:

kkapa.ai

----------------------
I'm sorry, but based on the provided knowledge sources, there's no information about setting Settings.embed_model to bm25 in LlamaIndex. The examples provided use different embedding models such as HuggingFaceEmbedding, GradientEmbedding, and OpenAIEmbedding.

Here's an example of how to set Settings.embed_model using HuggingFaceEmbedding:

Plain Text

from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.core import Settings

Settings.embed_model = HuggingFaceEmbedding(
    model_name="BAAI/bge-small-en-v1.5"
)

source ()

If you're looking to use a different embedding model like bm25, you would need to check if LlamaIndex supports it and how to properly configure it. I recommend checking the official LlamaIndex documentation or reaching out to their support for more accurate information.
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------

ddkatz123

@kapa.ai Right. I'm trying to include bm25 as a HuggingFaceEmbedding model.

kkapa.ai

Let me check the knowledge base for you. One moment! :books:

kkapa.ai

----------------------
I'm sorry, but based on the provided knowledge sources, there's no information about using bm25 as a HuggingFaceEmbedding model in LlamaIndex. The examples provided use different HuggingFace models such as BAAI/bge-small-en-v1.5.

Here's an example of how to set a HuggingFace model with HuggingFaceEmbedding:

Plain Text

from llama_index.embeddings.huggingface import HuggingFaceEmbedding

embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

source ()

If you're looking to use a different HuggingFace model like bm25, you would need to check if it's available on HuggingFace and how to properly configure it. I recommend checking the official HuggingFace model hub or reaching out to their support for more accurate information.
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------

Add a reply

Find answers from the community

I'm looking to create Settings.embed_model=bm25. How would I do that?