RAG Text Chunker — Text in überlappende Chunks teilen und eine Ollama-Anfrage an /api/embed für RAG erstellen

Führen Sie ihn auf einem Rechner aus, der Ollama erreichen kann. Die Antwort enthält einen Vektor pro Chunk, in dieser Reihenfolge.

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
}'

Chunks

3 Chunks. Der längste hat 294 Zeichen.

1. #0 · 294 Zeichen · beginnt bei Offset 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 Zeichen · beginnt bei Offset 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 Zeichen · beginnt bei Offset 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
}