Nebius Embeddings¶

This notebook demonstrates how to use Nebius AI Studio Embeddings with LlamaIndex. Nebius AI Studio implements all state-of-the-art embeddings models, available for commercial use.

First, let's install LlamaIndex and dependencies of Nebius AI Studio.

In [ ]:

%pip install llama-index-embeddings-nebius

%pip install llama-index-embeddings-nebius

In [ ]:

!pip install llama-index

!pip install llama-index

Insert your Nebius AI Studio key below. You can get it by registering for free at Nebius AI Studio and issuing the key at API Keys section."

In [ ]:

NEBIUS_API_KEY = ""

NEBIUS_API_KEY = ""

Now let's get embeddings using Nebius AI Studio

In [ ]:

from llama_index.embeddings.nebius import NebiusEmbedding

embed_model = NebiusEmbedding(api_key=NEBIUS_API_KEY)

from llama_index.embeddings.nebius import NebiusEmbedding embed_model = NebiusEmbedding(api_key=NEBIUS_API_KEY)

Basic usage¶

In [ ]:

text = "Everyone loves justice at another person's expense"
embeddings = embed_model.get_text_embedding(text)
assert len(embeddings) == 4096
print(len(embeddings), embeddings[:5], sep="\n")

text = "Everyone loves justice at another person's expense" embeddings = embed_model.get_text_embedding(text) assert len(embeddings) == 4096 print(len(embeddings), embeddings[:5], sep="\n")

4096
[-0.002410888671875, 0.0083770751953125, -0.00542449951171875, 0.007366180419921875, -0.022216796875]

Asynchronous usage¶

In [ ]:

text = "Everyone loves justice at another person's expense"
embeddings = await embed_model.aget_text_embedding(text)
assert len(embeddings) == 4096
print(len(embeddings), embeddings[:5], sep="\n")

text = "Everyone loves justice at another person's expense" embeddings = await embed_model.aget_text_embedding(text) assert len(embeddings) == 4096 print(len(embeddings), embeddings[:5], sep="\n")

4096
[-0.002410888671875, 0.0083770751953125, -0.00542449951171875, 0.007366180419921875, -0.022216796875]

Batched usage¶

In [ ]:

texts = [
    "As the hours pass",
    "I will let you know",
    "That I need to ask",
    "Before I'm alone",
]

embeddings = embed_model.get_text_embedding_batch(texts)
assert len(embeddings) == 4
assert len(embeddings[0]) == 4096
print(*[x[:3] for x in embeddings], sep="\n")

texts = [ "As the hours pass", "I will let you know", "That I need to ask", "Before I'm alone", ] embeddings = embed_model.get_text_embedding_batch(texts) assert len(embeddings) == 4 assert len(embeddings[0]) == 4096 print(*[x[:3] for x in embeddings], sep="\n")

[-0.0003886222839355469, 0.0004887580871582031, 0.011199951171875]
[-0.003734588623046875, 0.01143646240234375, 0.008758544921875]
[0.005901336669921875, 0.005161285400390625, 0.00142669677734375]
[-0.00946807861328125, -0.0048675537109375, 0.004817962646484375]

Async batched usage¶

In [ ]:

texts = [
    "As the hours pass",
    "I will let you know",
    "That I need to ask",
    "Before I'm alone",
]

embeddings = await embed_model.aget_text_embedding_batch(texts)
assert len(embeddings) == 4
assert len(embeddings[0]) == 4096
print(*[x[:3] for x in embeddings], sep="\n")

texts = [ "As the hours pass", "I will let you know", "That I need to ask", "Before I'm alone", ] embeddings = await embed_model.aget_text_embedding_batch(texts) assert len(embeddings) == 4 assert len(embeddings[0]) == 4096 print(*[x[:3] for x in embeddings], sep="\n")

[-0.0003886222839355469, 0.0004887580871582031, 0.011199951171875]
[-0.003734588623046875, 0.01143646240234375, 0.008758544921875]
[0.005901336669921875, 0.005161285400390625, 0.00142669677734375]
[-0.00946807861328125, -0.0048675537109375, 0.004817962646484375]