임베딩

export VOYAGE_API_KEY="<your secret key>"

pip install -U voyageai

import voyageai

vo = voyageai.Client()
# 이것은 자동으로 환경 변수 VOYAGE_API_KEY를 사용합니다.
# 또는 vo = voyageai.Client(api_key="<your secret key>")를 사용할 수 있습니다

texts = ["Sample text 1", "Sample text 2"]

result = vo.embed(texts, model="voyage-3.5", input_type="document")
print(result.embeddings[0])
print(result.embeddings[1])

curl https://api.voyageai.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VOYAGE_API_KEY" \
  -d '{
    "input": ["Sample text 1", "Sample text 2"],
    "model": "voyage-3.5"
  }'

{
  "object": "list",
  "data": [
    {
      "embedding": [-0.013131560757756233, 0.019828535616397858 /* ... */],
      "index": 0
    },
    {
      "embedding": [-0.0069352793507277966, 0.020878976210951805 /* ... */],
      "index": 1
    }
  ],
  "model": "voyage-3.5",
  "usage": {
    "total_tokens": 10
  }
}

documents = [
    "The Mediterranean diet emphasizes fish, olive oil, and vegetables, believed to reduce chronic diseases.",
    "Photosynthesis in plants converts light energy into glucose and produces essential oxygen.",
    "20th-century innovations, from radios to smartphones, centered on electronic advancements.",
    "Rivers provide water, irrigation, and habitat for aquatic species, vital for ecosystems.",
    "Apple's conference call to discuss fourth fiscal quarter results and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.",
    "Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature.",
]

import voyageai

vo = voyageai.Client()

# 문서 임베딩
doc_embds = vo.embed(documents, model="voyage-3.5", input_type="document").embeddings

query = "When is Apple's conference call scheduled?"

import numpy as np

# 쿼리 임베딩
query_embd = vo.embed([query], model="voyage-3.5", input_type="query").embeddings[0]

# 유사성 계산
# Voyage 임베딩은 길이 1로 정규화되므로 내적과
# 코사인 유사성은 동일합니다.
similarities = np.dot(doc_embds, query_embd)

retrieved_id = np.argmax(similarities)
print(documents[retrieved_id])