Search document summaries

Perform a search query on the automatically generated document summaries in the system.

POST /api/r2r/v3/documents/search

Search document summaries

cURL

curl --request POST \
  --url https://api.intelligence.io.solutions/api/r2r/v3/documents/search \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "search_settings": {
    "use_hybrid_search": false,
    "use_semantic_search": true,
    "use_fulltext_search": false,
    "filters": "<string>",
    "limit": 10,
    "offset": "0",
    "include_metadatas": true,
    "include_scores": true,
    "search_strategy": "vanilla",
    "hybrid_settings": {
      "full_text_weight": 1,
      "semantic_weight": 5,
      "full_text_limit": 200,
      "rrf_k": 50
    },
    "chunk_settings": {
      "probes": 10,
      "ef_search": 40,
      "enabled": true
    },
    "graph_settings": {
      "limits": "<array>",
      "enabled": true
    },
    "num_sub_queries": 5
  }
}
'

import requests

url = "https://api.intelligence.io.solutions/api/r2r/v3/documents/search"

payload = {
    "query": "<string>",
    "search_settings": {
        "use_hybrid_search": False,
        "use_semantic_search": True,
        "use_fulltext_search": False,
        "filters": "<string>",
        "limit": 10,
        "offset": "0",
        "include_metadatas": True,
        "include_scores": True,
        "search_strategy": "vanilla",
        "hybrid_settings": {
            "full_text_weight": 1,
            "semantic_weight": 5,
            "full_text_limit": 200,
            "rrf_k": 50
        },
        "chunk_settings": {
            "probes": 10,
            "ef_search": 40,
            "enabled": True
        },
        "graph_settings": {
            "limits": "<array>",
            "enabled": True
        },
        "num_sub_queries": 5
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query: '<string>',
    search_settings: {
      use_hybrid_search: false,
      use_semantic_search: true,
      use_fulltext_search: false,
      filters: '<string>',
      limit: 10,
      offset: '0',
      include_metadatas: true,
      include_scores: true,
      search_strategy: 'vanilla',
      hybrid_settings: {full_text_weight: 1, semantic_weight: 5, full_text_limit: 200, rrf_k: 50},
      chunk_settings: {probes: 10, ef_search: 40, enabled: true},
      graph_settings: {limits: '<array>', enabled: true},
      num_sub_queries: 5
    }
  })
};

fetch('https://api.intelligence.io.solutions/api/r2r/v3/documents/search', 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://api.intelligence.io.solutions/api/r2r/v3/documents/search",
  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([
    'query' => '<string>',
    'search_settings' => [
        'use_hybrid_search' => false,
        'use_semantic_search' => true,
        'use_fulltext_search' => false,
        'filters' => '<string>',
        'limit' => 10,
        'offset' => '0',
        'include_metadatas' => true,
        'include_scores' => true,
        'search_strategy' => 'vanilla',
        'hybrid_settings' => [
                'full_text_weight' => 1,
                'semantic_weight' => 5,
                'full_text_limit' => 200,
                'rrf_k' => 50
        ],
        'chunk_settings' => [
                'probes' => 10,
                'ef_search' => 40,
                'enabled' => true
        ],
        'graph_settings' => [
                'limits' => '<array>',
                'enabled' => true
        ],
        'num_sub_queries' => 5
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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://api.intelligence.io.solutions/api/r2r/v3/documents/search"

	payload := strings.NewReader("{\n  \"query\": \"<string>\",\n  \"search_settings\": {\n    \"use_hybrid_search\": false,\n    \"use_semantic_search\": true,\n    \"use_fulltext_search\": false,\n    \"filters\": \"<string>\",\n    \"limit\": 10,\n    \"offset\": \"0\",\n    \"include_metadatas\": true,\n    \"include_scores\": true,\n    \"search_strategy\": \"vanilla\",\n    \"hybrid_settings\": {\n      \"full_text_weight\": 1,\n      \"semantic_weight\": 5,\n      \"full_text_limit\": 200,\n      \"rrf_k\": 50\n    },\n    \"chunk_settings\": {\n      \"probes\": 10,\n      \"ef_search\": 40,\n      \"enabled\": true\n    },\n    \"graph_settings\": {\n      \"limits\": \"<array>\",\n      \"enabled\": true\n    },\n    \"num_sub_queries\": 5\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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://api.intelligence.io.solutions/api/r2r/v3/documents/search")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query\": \"<string>\",\n  \"search_settings\": {\n    \"use_hybrid_search\": false,\n    \"use_semantic_search\": true,\n    \"use_fulltext_search\": false,\n    \"filters\": \"<string>\",\n    \"limit\": 10,\n    \"offset\": \"0\",\n    \"include_metadatas\": true,\n    \"include_scores\": true,\n    \"search_strategy\": \"vanilla\",\n    \"hybrid_settings\": {\n      \"full_text_weight\": 1,\n      \"semantic_weight\": 5,\n      \"full_text_limit\": 200,\n      \"rrf_k\": 50\n    },\n    \"chunk_settings\": {\n      \"probes\": 10,\n      \"ef_search\": 40,\n      \"enabled\": true\n    },\n    \"graph_settings\": {\n      \"limits\": \"<array>\",\n      \"enabled\": true\n    },\n    \"num_sub_queries\": 5\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.intelligence.io.solutions/api/r2r/v3/documents/search")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query\": \"<string>\",\n  \"search_settings\": {\n    \"use_hybrid_search\": false,\n    \"use_semantic_search\": true,\n    \"use_fulltext_search\": false,\n    \"filters\": \"<string>\",\n    \"limit\": 10,\n    \"offset\": \"0\",\n    \"include_metadatas\": true,\n    \"include_scores\": true,\n    \"search_strategy\": \"vanilla\",\n    \"hybrid_settings\": {\n      \"full_text_weight\": 1,\n      \"semantic_weight\": 5,\n      \"full_text_limit\": 200,\n      \"rrf_k\": 50\n    },\n    \"chunk_settings\": {\n      \"probes\": 10,\n      \"ef_search\": 40,\n      \"enabled\": true\n    },\n    \"graph_settings\": {\n      \"limits\": \"<array>\",\n      \"enabled\": true\n    },\n    \"num_sub_queries\": 5\n  }\n}"

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

200

{
  "results": [
    {
      "id": "123e4567-e89b-12d3-a456-426614174000",
      "collection_ids": [
        "123e4567-e89b-12d3-a456-426614174000"
      ],
      "owner_id": "123e4567-e89b-12d3-a456-426614174000",
      "document_type": "pdf",
      "metadata": {
        "title": "Sample Document"
      },
      "version": "1.0",
      "title": "Sample Document",
      "size_in_bytes": 123456,
      "ingestion_status": "pending",
      "extraction_status": "pending",
      "created_at": "2021-01-01T00:00:00Z",
      "updated_at": "2021-01-01T00:00:00Z",
      "ingestion_attempt_number": 0,
      "summary": "A summary of the document",
      "summary_embedding": [
        0.1,
        0.2,
        0.3
      ],
      "total_tokens": 1000
    }
  ]
}

{}

""

This endpoint allows for complex filtering of search results using PostgreSQL-based queries. Filters can be applied to various fields such as document_id, and internal metadata values.

Allowed operators include eq, neq, gt, gte, lt, lte, like, ilike, in, and nin.

Authorizations

Authorization · string · header · required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json

query · string · required

The search query to perform.

search_mode · enum<string>

Default value of custom allows full control over search settings. Pre-configured search modes: basic: A simple semantic-based search. advanced: A more powerful hybrid search combining semantic and full-text. custom: Full control via search_settings. If filters or limit are provided alongside basic or advanced, they will override the default settings for that mode.

Available options: basic, advanced, custom

search_settings · object

Settings for document search

Show child attributes

Response

200

application/json

200

results · object[]

Show child attributes