RAG Text Chunker — Découpez du texte en morceaux chevauchants pour le RAG et créez une requête /api/embed d'Ollama

Exécutez-la sur une machine qui peut joindre Ollama. La réponse contient un vecteur par morceau, dans cet ordre.

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
}'

Morceaux

3 morceaux. Le plus long compte 294 caractères.

1. #0 · 294 caractères · commence à la position 0

   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 · 202 caractères · commence à la position 294

   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 · 169 caractères · commence à la position 496

   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
}