# Integrated API

## Find Match

<mark style="color:green;">`POST`</mark> `https://backend.alli.ai/webapi/find_match`

This API is for integrated search for fuzzy match, small talk, q\&a.

#### Headers

| Name                                      | Type   | Description                                                                                        |
| ----------------------------------------- | ------ | -------------------------------------------------------------------------------------------------- |
| API-KEY<mark style="color:red;">\*</mark> | string | Your cognitive search API key can be found in your dashboard Settings menu, under the General tab. |

#### Request Body

| Name                                     | Type    | Description                                                                                                  |
| ---------------------------------------- | ------- | ------------------------------------------------------------------------------------------------------------ |
| process\_order                           | array   | can be list of "exact\_match", "small\_talk", "faq", "mrc", default: \["exact\_match", "small\_talk", "faq"] |
| exact\_match\_list                       | array   | exact match list when using "exact\_match"                                                                   |
| exact\_match\_threshold                  | number  | default: 0.85                                                                                                |
| small\_talk\_threshold                   | number  | default: 0.85                                                                                                |
| faq\_threshold                           | number  | default:0. 90                                                                                                |
| faq\_direct\_answer\_mdethod             | string  | can be "adaptive", "simple". default: "adaptive"                                                             |
| faq\_direct\_answer\_adaptive\_thrdshold | number  | default: 0.4                                                                                                 |
| faq\_direct\_answer\_direct\_threshold   | string  | default: 0.9                                                                                                 |
| faq\_hashtags                            | array   | faq filtering hashtags                                                                                       |
| faq\_hashtags\_operator                  | string  | can be "and", "or", default: "or"                                                                            |
| faq\_count                               | number  | default: 5                                                                                                   |
| faq\_format                              | string  | can be "draftjs", "html", "text". default: "text"                                                            |
| mrc\_threshold                           | number  | default: 0.80                                                                                                |
| mrc\_hashtags                            | array   | mrc filtering hashtags                                                                                       |
| mrc\_hashtags\_operator                  | string  | can be "and", "or", default: "or"                                                                            |
| mrc\_count                               | string  | default: "5"                                                                                                 |
| mrc\_format                              | string  | can be "text", "html". default: "text"                                                                       |
| mrc\_return\_po                          | boolean | default: False                                                                                               |
| faq\_excluding\_hashtags                 | array   | faq filter-out hashtags                                                                                      |
| faq\_excluding\_hashtags\_operator       | string  | can be "and", "or", default: "or"                                                                            |

{% tabs %}
{% tab title="200 Successfully retrieved.
found: true/false
process: matching process name
error: error message

When process = exact\_match
result: exact match keyword

When process = faq
result\[].id: Q\&A id
result\[].question: Q\&A question
result\[].answer: Q\&A answer
" %}

```
{
  "found": true, 
  "result": [
    {
      "confidence": 0.8660902048311576, 
      "effectiveConfidence": 0.8660902048311576, 
      "question": "QA 게이트(GATE)", 
      "answer": "...", 
      "id": "RkFROjYwZDA3MGU5NWRjZDlkZTliMzFlNTI5MA==", 
      "lastUpdatedDate": "2021-06-21", 
      "createdDate": "2021-06-21", 
      "hashtags": ["실무용어"], 
      "userFeedback": {"positiveCount": 0, "negativeCount": 0}, 
      "agentFeedback": {"positiveCount": 0, "negativeCount": 0}
    }
  ], 
  "process": "faq", 
  "error": null
}
```

{% endtab %}
{% endtabs %}

### Request Example

Please replace YOUR API KEY with your one in example below, To get the api key, please see [getting-api-key](https://docs.allganize.ai/api_documentation/#getting-api-key) section.

```
$ curl -H "API-KEY: YOUR_API_KEY" \
       -d'{"process_order":["exact_match", "small_talk", "faq"], \
           "exact_match_list": ["aaaa", "bbbb"], \
           "query": "QA", \
           "faq_threshold": 0.85}' \
       "https://backend.alli.ai/webapi/find_match"
{
  "found": true, 
  "result": [
    {
      "confidence": 0.8660902048311576, 
      "effectiveConfidence": 0.8660902048311576, 
      "question": "QA 게이트(GATE)", 
      "answer": "...", 
      "id": "RkFROjYwZDA3MGU5NWRjZDlkZTliMzFlNTI5MA==", 
      "lastUpdatedDate": "2021-06-21", 
      "createdDate": "2021-06-21", 
      "hashtags": ["실무용어"], 
      "userFeedback": {"positiveCount": 0, "negativeCount": 0}, 
      "agentFeedback": {"positiveCount": 0, "negativeCount": 0}
    }
  ], 
  "process": "faq", 
  "error": null,
  "resultId": "RmluZE1hdGNoUmVzdWx0OjYxODhkZGMwMjE1MmZhYWVkNGExMDRmOA=="
}
```

## Match Feedback

<mark style="color:green;">`POST`</mark> `https://backend.alli.ai/webapi/match_feedback`

if there is no positive\_feedback, It just returns previous result without feedback.

If there is no feedback\_index, it returns all previous result.

Only for 'faq' process can apply feedback. and only 'faq', 'mrc' can get previous result

#### Headers

| Name                                      | Type   | Description                                                                                        |
| ----------------------------------------- | ------ | -------------------------------------------------------------------------------------------------- |
| API-KEY<mark style="color:red;">\*</mark> | String | Your cognitive search API key can be found in your dashboard Settings menu, under the General tab. |

#### Request Body

| Name                                         | Type    | Description                      |
| -------------------------------------------- | ------- | -------------------------------- |
| result\_id<mark style="color:red;">\*</mark> | String  | resultId from find\_match result |
| feedback\_index                              | Int     | result index                     |
| positive\_feedback                           | Boolean | true: positive, false:negative   |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.allganize.ai/api-reference/integrated-api.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.