Ollama로 임베딩 만들기: 검색과 RAG의 기본

Ollama에 접근할 수 있는 컴퓨터에서 실행하세요. 응답에는 청크마다 벡터가 하나씩 이 순서로 들어 있습니다.

curl http://localhost:11434/api/embed -d '{
  "model": "embeddinggemma",
  "input": [
    "Embeddings turn text into numeric vectors. You can store them in a vector database and search them with cosine similarity, or use them in a RAG pipeline.\n\nThe length of each vector depends on the embedding model. Use the same model when you index your documents and when you embed a question.\n\n",
    "Ollama'\''s /api/embed endpoint takes a single string or an array of strings. By default, input that is longer than the model'\''s context window is truncated. Set truncate to false to get an error instead.\n\n",
    "Split long documents into smaller chunks before you embed them, so that each chunk fits in the context window and a search can return the part that answers the question."
  ],
  "truncate": false
}'

청크

청크 3개. 가장 긴 청크는 294자입니다.

1. #0 · 294자 · 오프셋 0에서 시작

   Embeddings turn text into numeric vectors. You can store them in a vector database and search them with cosine similarity, or use them in a RAG pipeline. The length of each vector depends on the embedding model. Use the same model when you index your documents and when you embed a question.

2. #1 · 202자 · 오프셋 294에서 시작

   Ollama's /api/embed endpoint takes a single string or an array of strings. By default, input that is longer than the model's context window is truncated. Set truncate to false to get an error instead.

3. #2 · 169자 · 오프셋 496에서 시작

   Split long documents into smaller chunks before you embed them, so that each chunk fits in the context window and a search can return the part that answers the question.

{
  "model": "embeddinggemma",
  "input": [
    "Embeddings turn text into numeric vectors. You can store them in a vector database and search them with cosine similarity, or use them in a RAG pipeline.\n\nThe length of each vector depends on the embedding model. Use the same model when you index your documents and when you embed a question.\n\n",
    "Ollama's /api/embed endpoint takes a single string or an array of strings. By default, input that is longer than the model's context window is truncated. Set truncate to false to get an error instead.\n\n",
    "Split long documents into smaller chunks before you embed them, so that each chunk fits in the context window and a search can return the part that answers the question."
  ],
  "truncate": false
}

코사인 유사도 순위

#0 How do I keep a model loaded in Ollama?와(과) 비교한 결과입니다. 값이 클수록 더 비슷합니다.

코사인 유사도 행렬

각 칸은 행의 벡터와 열의 벡터를 비교한 값입니다.

벡터