Help with pipeline and reindex and search using E5 embedding model

Elastic Stack Elasticsearch
1

Hi all,
I have uploaded a tsv file with chunked information, this information is divided in this columns: "document_name", "page_number" and "text".
I did this many times but using elser_v2, now I have to use the built-in E5.
I have been trying to create a pipeline and a correct way to reindex this file from the original index to the embedded one, also the way to RAG search using E5 and I can't find the right way to do it.

Also, I think I had achieve this reindex successfully but they way to do a search (I think I have to embed the query too, not like elser) always gives me an error

Does anyone have a similar use case?

2 
PUT _ingest/pipeline/e5-small-ingest-pipeline
{
  "description": "e5-small",
  "processors": [
    {
      "inference": {
        "model_id": ".multilingual-e5-small_linux-x86_64",
        "input_output": [
          {
            "input_field": "name",
            "output_field": "name_embedding"
          },
          {
            "input_field": "text",
            "output_field": "text_embedding"
          }
        ]
      }
    }
  ],
  "on_failure": [
    {
      "set": {
        "description": "Index document to 'failed-<index>'",
        "field": "_index",
        "value": "failed-{{{_index}}}"
      }
    },
    {
      "set": {
        "description": "Set error message",
        "field": "ingest.failure",
        "value": "{{_ingest.on_failure_message}}"
      }
    },
    {
      "set": {
        "field": "error.pipeline",
        "value": "{{ _ingest.pipeline }}"
      }
    }
  ]
}