Train Neo4J Text

Start a knowledge graph training task using raw text input.

POST /v4/knowledge_graph/neo4j/text/

Train Neo4J Text

cURL

curl --request POST \
  --url https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/ \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "rag_id": "654c602a46c3b6d4e28741b0",
  "text": "The main product is Gemini. It is an AI model.",
  "schema_prompt": "Focus only on products and models as nodes."
}
'

import requests

url = "https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/"

payload = {
    "rag_id": "654c602a46c3b6d4e28741b0",
    "text": "The main product is Gemini. It is an AI model.",
    "schema_prompt": "Focus only on products and models as nodes."
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    rag_id: '654c602a46c3b6d4e28741b0',
    text: 'The main product is Gemini. It is an AI model.',
    schema_prompt: 'Focus only on products and models as nodes.'
  })
};

fetch('https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'rag_id' => '654c602a46c3b6d4e28741b0',
    'text' => 'The main product is Gemini. It is an AI model.',
    'schema_prompt' => 'Focus only on products and models as nodes.'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/"

	payload := strings.NewReader("{\n  \"rag_id\": \"654c602a46c3b6d4e28741b0\",\n  \"text\": \"The main product is Gemini. It is an AI model.\",\n  \"schema_prompt\": \"Focus only on products and models as nodes.\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"rag_id\": \"654c602a46c3b6d4e28741b0\",\n  \"text\": \"The main product is Gemini. It is an AI model.\",\n  \"schema_prompt\": \"Focus only on products and models as nodes.\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/text/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"rag_id\": \"654c602a46c3b6d4e28741b0\",\n  \"text\": \"The main product is Gemini. It is an AI model.\",\n  \"schema_prompt\": \"Focus only on products and models as nodes.\"\n}"

response = http.request(request)
puts response.read_body

200

"Task successfully started."

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

x-api-key · string · header · required

Body

application/json

rag_id · string · required

The ID of the RAG system to train the knowledge graph for (e.g., a 24-character hex string).

Example:

"654c602a46c3b6d4e28741b0"

text · string · required

The raw text content to be processed and used for knowledge graph generation.

Example:

"Albert Einstein was born in Germany. He developed the theory of relativity."

schema_prompt · string | null

Allowed nodes and relationships for the knowledge graph (optional prompt for the LLM).

extra_info · object | null

Additional information or configuration for the task, provided as a JSON object.

Example:

{}

Response

200

application/json

Successful Response (Training task started).

The response is of type string.

Example:

"Task successfully started."