Answer Bot API

Answer Bot API makes it possible for the system to read, infer meaning, and deliver precise answers from large sets of documents with high accuracy.

Search from Q&A

POST https://backend.alli.ai/webapi/faq

This API lets you find the most relevant question and answer pairs from your Q&A knowledge base.

Headers

Request Body

200 The API will find the most relevant question and answers from your Q&A database. confidence: It shows the confidence value from AI model. Shown as a number value between 0 and 1. effectiveConfidence: When you provide feedback to the query result, it automatically trains the AI model. Effective confidence is the adjusted score with these users' and agents' feedback. Shown as a number value between 0 and 1. question: This is the question part of the selected Q&A pair. answer: This is the answer part of the selected Q&A pair. id: This is used to identify the result to give or cancel feedback. hashtags: Hashtags registered for the Q&A. lastUpdatedDate: The date when the Q&A is last updated. agentFeedback: The feedback from agents (through dashboard and REST calls) about this Q&A. userFeedback: The feedback from users (through conversation) about this Q&A. count: The number of suggested Q&As. hashId: This hash id is being used when you call select_answer later. The number of search results and the threshold follows your dashboard setting. Please check your settings in Q&A > Settings.

{"result": 
  [
    {
      "confidence": CONFIDENCE_VALUE, 
      "effectiveConfidence": EFFECTIVE_CONFIDENCE_VALUE, 
      "question": "QUESTION_1", 
      "answer": "ANSWER_1",
      "id": "ID_1",
      "hashtags": [],
      "lastUpdatedDate": "DATE",
      "agentFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
              },
      "userFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
              }
    }, ... 
  ],
  "count": 3,
  "hashId": "HASH_ID"
}

Search from Documents

POST https://backend.alli.ai/webapi/mrc

Documents API finds an answer from your unstructured text documents and even from complex tables.

Headers

Request Body

200 You will get the result as the following JSON format. answer: It's the answer extracted from uploaded documents in the dashboard. answerHash: This is used to identify the answer to give or cancel feedback. confidence: It shows the confidence value from AI model. Shown as a number value between 0 and 1. effectiveConfidence: When you provide feedback to the query result, it automatically trains the AI model. Effective confidence is the adjusted score with these users' and agents' feedback. Shown as a number value between 0 and 1. documentId: The document's ID where the answer is extracted from. documentName: The document's name where the answer is extracted from. hashtags: The hashtags attached to the document. pageNo: The page number in the document where the answer was derived. agentFeedback: createdDate: The date when the document was uploaded. agentFeedback: The feedback from agents (through dashboard and REST calls) about this document userFeedback: The feedback from users about this document The number of search results and the threshold follows your dashboard setting. Please check your setting in Documents > Settings. body: If returnPreview is true in the request, the html body of the document search preview is displayed. Note: body parameter will be deprecated on 12/9/2021 due to technical changes made to the preview feature. css: If returnPreview is true in the request, the css of the document search preview is displayed. Note: css parameter will be deprecated on 12/9/2021 due to technical changes made to the preview feature.

{
    "result": [
        {
            "answer": "ANSWER_1",
            "answerHash": "ANSWER_HASH_1",
            "confidence": CONFIDENCE_1,
            "effectiveConfidence": EFFECTIVE_CONFIDENCE_1,
            "documentId": "DOCUMENT_ID_1",
            "documentName": "DOCUMENT_NAME_1",
            "hashtags": [],
            "pageNo": PAGE_NUMBER,
            "createdDate": "DATE",
            "agentFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "userFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "body": "PREVIEW_HTML_BODY",
            "css": "PREVIEW_CSS"
        }
    ]
}

Get Single Q&A

GET https://backend.alli.ai/webapi/single_faq

This is the method to get all the details of a single Q&A.

Headers

Request Body

200 Includes fields: question: The question associated with the Q&A. answer : The answer to the question. id: The id of this Q&A. userFeedback: The feedback from users (through conversation) about this Q&A. agentFeedback: The feedback from agents (through dashboard and REST calls) about this Q&A. lastUpdatedDate, createdDate: The date when the Q&A was updated / first created. hashtags: All hashtags associated with this question.

{
    "result": {
        "question": "Who is there?",
        "answer": "Elmo",
        "id": "RkFROjYwMmY2ZTQ0YWZmMWQ5YmQ0NmM5Y2VkNw==",
        "userFeedback": {
            "positiveCount": 0,
            "negativeCount": 0
        },
        "agentFeedback": {
            "positiveCount": 0,
            "negativeCount": 1
        },
        "lastUpdatedDate": "2021-02-19",
        "createdDate": "2021-02-19",
        "hashtags": []
    }
}

Get Single Document

GET https://backend.alli.ai/webapi/single_document

This is the method to get all details of a single document.

Headers

Request Body

200 You will get the result as the following JSON format. id: The Document's ID. documentName: The document's file name. createdDate: The date when the document was uploaded. hashtags: Hashtags registered for the document. agentFeedback : Counts of positive and negative ratings by employees. userFeedback: The feedback from users about this document{"result": {

      "id": "S25vd2xlZGdlQmFzZTo1ZjMzODFkZmNhYWJjYWUyMjkzYjFhY2U=",
      "documentName": "Policy document 1.docx",
      "createdDate": "2020-11-12",
      "agentFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
            },
            "userFeedback": {
            "positiveCount": 0,
            "negativeCount": 0
        },
      "hashtags" : ["hashtag1", "hashtag2"]
    }
}

Q&A Feedbacks

GET https://backend.alli.ai/webapi/faq_feedbacks

This API lets you get the list of feedbacks given to Q&A pairs for each search query.

Headers

Request Body

200 You will get the result as the following JSON format. query: It's the search query that has feedback for Q&A search results. feedbacks: It contains detailed feedback information for the query, faqId and postive. faqId: The Q&A pair's ID that has the feedback information. positive: true or false. true indicates that the Q&A pair has positive feedback upon the search, and false indicates negative feedback. count: The total number of feedbacks listed.

{
  "result": [
    {
      "query": "QUERY_1",
      "feedbacks": [
        {
          "faqId": "FAQ_ID_1_1", 
          "positive": true or false
        }, ...
      ]
    }, ...
  ],
  "count": COUNT_1
}

Q&A Feedback

POST https://backend.alli.ai/webapi/faq_feedback

This API lets you give or cancel feedback given to a Q&A pair for a search query.

Headers

Request Body

200 You will get the result as the following JSON format. id: The ID for the Q&A you want to give or cancel feedback for the query. It's the same one you used for the request. positiveCount: The total number of positive feedbacks after the request is processed. negativeCount: The total number of negative feedbacks after the request is processed.

{
    "result": {
        "faqTrainSearchResult": {
            "faq": {
                "id": "ID"
            },
            "agentFeedback": {
                "positiveCount": NUMBER,
                "negativeCount": NUMBER
            }
        }
    },
    "errors": null
}

Q&A User Feedback

POST https://backend.alli.ai/webapi/faq/user_feedback

The feedback registered with the above API will be submitted as user feedback. This API registers user feedback (user feedback is what the users who use the Alli chatbot and approve or disprove of answers submit).

Headers

Request Body

200 Returns the current user feedback for this FAQ, both the positiveCount and negativeCount.

{
    "result": {
        "userFeedback": {
            "positiveCount": 1,
            "negativeCount": 0
        }
    }
}

Upload Q&As

POST https://backend.alli.ai/webapi/upload_faq_file

You can upload multiple Q&As in the tsv, csv, xlsx, and zip format using this API.

Headers

Request Body

200 result: success if the file upload is successful. notUploaded: If any of the questions are not uploaded or updates existing Q&A, the details will be listed here. question: The question part of not-uploaded or updated Q&A. state: dup if the Q&A is not uploaded due to duplication in 'similar questions' content. up if the Q&A updated an existing one due to the same question content.

{
    "result": "success",
    "notUploaded": [
        {
            "question": "QUESTION_1",
            "state": "dup"
        },
        {
            "question": "QUESTION_2",
            "state": "up"
        }
    ]
}

Add Q&A

POST https://backend.alli.ai/webapi/register_faq

You can add a new Q&A or update an existing Q&A using this API.

Headers

Request Body

200 status: The status of the registered Q&A. 'created' means the Q&A is newly created. 'updated' means an existing Q&A is updated with a new answer. id: The registered Q&A's ID.

{
    "result": {
        "status": "created",
        "id": "Q&A_ID"
    },
    "errors": null
}

Delete Q&A

POST https://backend.alli.ai/webapi/delete_faq

You can delete a Q&A using this API.

Headers

Request Body

200 status: 'deleted' if the Q&A is successfully deleted.

{
    "result": {
        "status": "deleted"
    },
    "errors": null
}

404 When there's no Q&A with the ID, this error will be returned.

{
    "errors": "The record doesn't exist."
}

List Q&As

GET https://backend.alli.ai/webapi/faqs

You can list Q&As in the Knowledge Base using this API.

Headers

Request Body

200 offset: The same offset value with the offset request parameter. count: Total number of Q&As listed after limit is applied. totalCount: Total number of Q&As as the result of applied filters. id: The ID of the Q&A. question: The question part of the Q&A. answer: The answer part of the Q&A. hashtags: The hashtags added on the Q&A. userFeedback: Number of positive and negative user feedbacks. User feedbacks affects the search result for future queries. agentFeedback: Number of positive and negative agent feedbacks. Agent feedbacks affects the search result for future queries. lastUpdatedDate: The date when the Q&A is last updated. createdDate: The date when the Q&A is created.

{
    "offset": 0,
    "count": 10,
    "totalCount": 12,
    "results": [
        {
            "id": "Q&A_ID_1",
            "question": "QUESTION_1",
            "answer": "ANSWER_1",
            "hashtags": [
                "HASHTAG_1",
                "HASHTAG_2"
            ],
            "userFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "agentFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "lastUpdatedDate": "2021-05-04",
            "createdDate": "2021-02-23"
        },
        {
            "id": "Q&A_ID_2",
            "question": "QUESTION_2",
            "answer": "ANSWER_2",
            "hashtags": [
                "HASHTAG_1",
                "HASHTAG_3"
            ],
            "userFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "agentFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "lastUpdatedDate": "2021-05-04",
            "createdDate": "2021-02-23"
        }, ...
    ]
}

Q&A Candidates

GET https://backend.alli.ai/webapi/faq_candidates

Using this API, you can get the list of unanswered questions from customers. They're called Candidates.

Headers

Request Body

200 You will get the result as the following JSON format. count: The total number of candidates. id: The ID of the extracted answer to the unanswered question. Whenever there is a new unanswered question registered, Alli tries to extract and add an answer from uploaded documents automatically. frequency: Sum of all the frequency numbers under the questions. textAnswer: The answer extracted from the uploaded documents for the question. state: The status of the candidate. ACTIVE if the candidate is not added to the Q&A database yet. ARCHIVED if the candidate is added to the Q&A database. createdAt: The timestamp of when the candidate was created. questions: Multiple similar questions can have the same answer. Information about all the questions for the answer is under here. id (under questions): The ID of the unanswered question from customers. question (under questions): The unanswered question from customers. frequency (under questions): How many times the question was asked by customers. id (under history): The ID of the history information of the unanswered question. The history is the customers' log when the question was asked.

{
	"result": {
		"faqCandidates": [
		  {
				"id": "ID_ANSWER_1",
				"frequency": 1,
				"textAnswer": "ANSWER_1",
				"state": "ACTIVE",
				"createdAt": NUMBER,
				"questions": [{
					"id": "ID_QUESTION_1",
					"question": "QUESTION_1",
					"frequency": 1,
					"history": {
						"id": "ID_HISTORY_1"
					}
				}]
			},
		],
		"count": 1
	},
	"errors": null
}

Q&A Candidates

POST https://backend.alli.ai/webapi/add_faq_candidates

Registers a new Q&A Candidate with the system.

Headers

Request Body

200 You will get the result as the following JSON format. id: The id of the candidate registered.

{
    "result": {
        "candidates": [
            {
                "id": "CANDIDATE_ID_1"
            },
            {
                "id": "CANDIDATE_ID_2"
            }
        ]
    },
    "errors": null
}

Documents Feedbacks

GET https://backend.alli.ai/webapi/mrc_feedbacks

This API lets you get the list of feedbacks given to Document search results (AI-extracted answers from uploaded documents) for each search query.

Headers

Request Body

200 You will get the result as the following JSON format. query: The search query for the extracted answer. documentId: The ID of the document where the answer was extracted from. answer: The answer part extracted from the document for the query. answerHash: The ID for the answer part extracted from the document for the query. It is created whenever a Documents search happens and bound to the query and the answer pair. It's the same value from the POST Documents API above. positive: true or false. true indicates that the extracted answer has positive feedback upon the search, and false indicates negative feedback. count: The total number of feedbacks listed.

{
  "result": [
    {
      "query": "QUERY_1",
      "feedbacks": [
        {
          "documentId": "DOCUMENT_ID_1",
          "answer": "ANSWER_1",
          "answerHash": "ANSWER_HASH_1",
          "positive": true or false
        }, ...
      ]
    }
  ],
  "count": NUMBER
}

Documents Search Feedback

POST https://backend.alli.ai/webapi/mrc_feedback

This API lets you give or cancel feedback given to a Document search result for a search query.

Headers

Request Body

200 You will get the result as the following JSON format. positiveCount: The total number of positive feedbacks after the request is processed. negativeCount: The total number of negative feedbacks after the request is processed.

{
    "result": {
        "mrcFeedbackSearchResult": {
            "agentFeedback": {
                "positiveCount": NUMBER,
                "negativeCount": NUMBER
            }
        }
    },
    "errors": null
}

Documents Search User Feedback

POST https://backend.alli.ai/webapi/mrc/user_feedback

Provide user feedback to the Documents search result.

Headers

Request Body

200 Returns the positiveCount and negativeCount of the user feedback after the change.

{
    "result": {
        "userFeedback": {
            "positiveCount": 1,
            "negativeCount": 0
        }
    }
}

Upload Documents

POST https://backend.alli.ai/webapi/upload_file

This API method allows you to upload documents for Cognitive Search. Available file formats for the upload: PDF, TXT, MS Word, PowerPoint, Excel, HTM and HTML. To upload a HTML file with linked resources, please compress in a ZIP file along with any relative linked resources before uploading.

Headers

Request Body

200 You will get the result in the following JSON format. id: The ID of the uploaded document. fileName: The filename of the uploaded document. hashtags: The array of hashtags added to the uploaded document. footer: The footer (source) info added to the uploaded document. It can be the default one or the one specified by footerTitle and footerUrl parameters.

{
    "result": {
        "id": "DOCUMENT_ID",
        "fileName": "YOUR_FILE_NAME",
        "hashtags": [
            "HASHTAG_1",
            "HASHTAG_2"
        ],
        "footer": "FOOTER_IN_HTML"
    }
}

Upload Documents from S3

POST https://backend.alli.ai/webapi/upload_from_s3

This API lets you transfer documents stored in S3 into Cognitive Search. They will appear as Knowledge Base documents in the dashboard. Available file formats are same in the section of Upload Documents.

Headers

Request Body

200 You will get the result in the following JSON format: id: The id for the transferred document. fileName: The filename of the transferred document. hashtags: The array of hashtags added to the uploaded document. footer: The footer (source) info added to the uploaded document. It can be the default one or the one specified by footerTitle and footerUrl parameters.

{
    "result": {
        "id": "DOCUMENT_ID",
        "fileName": "YOUR_FILE_NAME",
        "hashtags": [
            "HASHTAG_1",
            "HASHTAG_2"
        ],
        "footer": "FOOTER_IN_HTML"
    }
}

Check Document Status

GET https://backend.alli.ai/webapi/check_file_status

Once you upload documents through API, it is converted, parsed, and embedded as vectors. This API shows the status of the process for a document being uploaded.

Headers

Request Body

200 You will get the result in the following JSON format. id: The ID of the document being checked. status: Status of the document. Please see Response Example below for possible values.

{"result": 
    {"id": "YOUR DOCUMENT ID", 
    "status": "initializing"}}

Delete Documents

POST https://backend.alli.ai/webapi/delete_file

This API lets you delete uploaded files.

Headers

Request Body

200 You will get the result in the following JSON format. ok: true if the deletion completes successfully. If the deletion fails, the result will be false and errors will contain an error message.

{
    "result": {
        "ok": BOOLEAN
    },
    "errors": null
}

List Documents

GET https://backend.alli.ai/webapi/knowledge_bases

This API lets you list out the uploaded documents.

Query Parameters

Headers

200 You will get the result in the following JSON format. id: The ID of the listed document. fileName: The filename of the list document. hashtags: The hashtags added on the document. autoHashtags : The automatically generated hashtags added to the document.

{
  "result": {
    "items": [
      {
        "id": "DOCUMENT_ID",
        "fileName": "FILENAME",
        "hashtag": ["HASHTAG_1", "HASHTAG_2"],
        "autoHashtag": ["AUTOHASHTAG_1"]
      }
    ]
  },
  "errors": null
}

Rename Documents (Knowledge Base)

POST https://backend.alli.ai/webapi/update_kb_name

This API lets you update the name for an uploaded document.

Headers

Request Body

200 You will get the result in the following JSON format: id: The Document id for the file who's name was changed. filename: The Document's new name.

{
    "result": {
        "id": "DOCUMENT_ID",
        "filename": "FILENAME"
    }
}

Update Documents

POST https://backend.alli.ai/webapi/update_document

This API lets you update hashtags, footer title, and footer title link for a document.

Headers

Request Body

200 You will get the result in the following JSON format. id: The id of the document to which the hashtags correspond hashtags: Hashtags attached to the document after update footer: The footer (source) info added to the uploaded document. It can be the default one or the one specified by footerTitle and footerUrl parameters.

{
    "result": {
        "knowledgeBase": {
            "id": "DOCUMENT_ID",
            "hashtags": [
                "HASHTAG_1",
                "HASHTAG_2"
            ],
            "footer": "FOOTER_IN_HTML"
        }
    },
    "errors": null
}

Knowledge Base Toggle Status

POST https://backend.alli.ai/webapi/toggle_documents

This API lets you change the status of many documents (AKA knowledge bases) at once

Headers

Request Body

200 You will get the result in the following JSON format: knowledgeBases : a list of ONLY the knowledge bases whose status were toggled id: id of knowledge base status: new status of knowledge base (boolean). true meaning status is now on.

{
  "result": {
    "knowledgeBases": [
      {
        "id": "YOUR_FIRST_DOCUMENT_ID",
        "status": true or false
      },
      {
        "id": "YOUR_SECOND_DOCUMENT_ID",
        "status": true or false
      }
    ]
  },
  "errors": null
}

Knowledge Base Auto Hashtag (Classification)

POST https://backend.alli.ai/webapi/kb_auto_hashtag

This API lets you get the hashtag list with classification keywords for the documents.

Headers

Request Body

200 You will get the result in the following JSON format. updated -> id : The id of the Document to which the hashtags correspond. autoHashtags: Array of JSON objects, containing the list of hashtags auto-generated for the Document. state: Status of hashtag, depending on if agent has confirmed this auto-generated hashtag. Will be one of: "SUGGESTED", "APPROVED", "DECLINED". bestConfidence: Numerical confidence of this auto-generated hashtag from 0 to 1. autoHashtags -> id: The id of the hashtag. hashtag: String value of hashtag (displayed in Dashboard).

{
    "result": {
        "updated": [
            {
                "id": "DOCUMENT_ID",
                "autoHashtags": [
                    {
                        "id": "KNOWLEDGE_BASE_AUTO_HASHTAG_ID",
                        "state": "STATE",
                        "bestConfidence": NUMBER,
                        "autoHashtag": {
                            "hashtag": "HASHTAG_VALUE"
                        }
                    }
                ]
            }
        ]
    },
    "errors": null
}

Knowledge Base Auto Hashtag Feedback (Classification)

POST https://backend.alli.ai/webapi/kb_auto_hashtag_feedback

This API lets you approve or decline classification hashtags for documents

Headers

Request Body

200 You will get the result in the following JSON format: result: Array of JSON objects, each corresponding to a auto-hashtag id: The id of the hashtag state: The hashtag's feedback from agent. Will be one of: "suggested", "approved", "declined"

{
    "result": [
        {
            "id": "KNOWLEDGE_BASE_AUTO_HASHTAG_ID",
            "state": "STATE"
        },
        {
            "id": "KNOWLEDGE_BASE_AUTO_HASHTAG_ID_2",
            "state": "STATE"
        }
    ]
}

Select Answer

POST https://backend.alli.ai/webapi/faq/select_answer

This method should be used to simulate a user looking up a specific FAQ

Path Parameters

Request Body

200 You will get the result in the following JSON format: In case of success

{"result": "Success"}

404 In case you provide an invalid FAQ

{"result": [], "error": "Record does not exist."}

Agent Management

POST https://backend.alli.ai/webapi/agent_management

Used to create and delete agents from the project.

Headers

Request Body

200 id: ID of agent that was deleted/created status: What happened (either "deleted" or "created")

{
    "result": {
        "id" : "QWdlbnQ6NWZkMmFjMzIwODQ4MzY1ZDI4NWFjMGUw",
        "status": "deleted" 
    },
    "errors": null
}

400 If the agent you try to create already has an email registered.

{
  "result": [],
  "errors": "Agent with provided email already exists."
}

404 If you try to delete an agent that doesn't exist.

{
  "result": [],
  "errors": "The record does not exist."
}

Get All Hashtags

GET https://backend.alli.ai/webapi/hashtags

Gets all hashtags from both FAQs and MRCs

Headers

200 Returns each hashtag with its count of uses

{
  "result": {
    "sample_tag1": 2,
   "sample_tag2": 1,
  }
}

Q&A Query History

GET https://backend.alli.ai/webapi/faq_histories

Returns the past Q&A Searches that have been done, both through the REST API and the Alli dashboard.

Query Parameters

Headers

200 Each query will have the following attributes: agent: an object which contains the id of the agent who made the query. question: The question actually asked in the query answers: All answers provided by the system to the query. Each answer has the Q&A that was referred to, and the confidence, effective confidence. There is also a count of how many queries were returned in a count field.

{
    "result": {
        "histories": [
            {
                "agent": {
                    "id": "QWdlbnQ6NjA0NmMyNWJmNTFjMmVlYjc4Mjg3Zjcy"
                },
                "question": "What is life?",
                "answers": [
                    {
                        "faq": {
                            "id": "RkFROjYwNDZjMmUxM2MzYmQ5MjVmMzgxMGNkOQ=="
                        },
                        "effectiveConfidence": 0.9999999999999927,
                        "confidence": 0.9999999999999927
                    }
                ]
            }
        ],
        "count": 1
    },
    "errors": null
}

Documents Query History

GET https://backend.alli.ai/webapi/mrc_histories

Returns the past Documents Searches that have been done, both through the REST API and the Alli dashboard.

Query Parameters

Headers

200 Each query history will have the following attributes: agent: The id of the agent who made the request. question: The actual question asked. answers: A list of all possible answers provided. Each answer has the knowledgeBase used to source that answer (both the filename and the id), the actual answer itself, the answerFormat, the hashtags associated with the knowledgeBase that was retrieved, and whether feedbackAvailable for this specific answer.

{
    "result": {
        "histories": [
            {
                "agent": {
                    "id": "QWdlbnQ6NWZiNzc5MGIwZjE3Zjc5ZmNiNzVlYzFh"
                },
                "question": "program memory of c004",
                "answers": [
                    {
                        "knowledgeBase": {
                            "id": "S25vd2xlZGdlQmFzZTo2MDUyODM0ODFiYzgxNDcwZTEzNGRjNDQ=",
                            "fileName": "specification_en.pdf"
                        },
                        "answer": "{\"blocks\": [{\"key\": \"kn13\", \"type\": \"unstyled\", \"text\": \"Type capacity program memory program memory - C004, B04KR: 80KB\", \"depth\": 0, \"inlineStyleRanges\": [], \"entityRanges\": [], \"data\": {}}, {\"key\": \"2vjf\", \"text\": \" \", \"type\": \"unstyled\", \"depth\": 0, \"inlineStyleRanges\": [], \"entityRanges\": [], \"data\": {}}, {\"key\": \"45cb\", \"text\": \"— From specification_en.pdf\", \"type\": \"unstyled\", \"depth\": 0, \"inlineStyleRanges\": [{\"offset\": 0, \"length\": 27, \"style\": \"ITALIC\"}], \"entityRanges\": [{\"offset\": 7, \"length\": 20, \"key\": 0}], \"data\": {}}], \"entityMap\": {\"0\": {\"type\": \"LINK\", \"mutability\": \"MUTABLE\", \"data\": {\"url\": \"https://staging-download.alli.ai/download_document/UHJvamVjdDo1ZmI3NzkwYjBmMTdmNzlmY2I3NWVjMWM=/S25vd2xlZGdlQmFzZTo2MDUyODM0ODFiYzgxNDcwZTEzNGRjNDQ=\"}}}}",
                        "answerHash": "6648c76e9be27864557f84ab7822cde8",
                        "answerFormat": "DRAFTJS",
                        "hashtags": [],
                        "feedbackAvailable": true,
                        "columnFilterValues": []
                    },
                    ...
                    {
                        "knowledgeBase": {
                            "id": "S25vd2xlZGdlQmFzZTo2MDUyODM0ODFiYzgxNDcwZTEzNGRjNDQ=",
                            "fileName": "specification_en.pdf"
                        },
                        "answer": "{\"blocks\": [{\"key\": \"87us\", \"type\": \"unstyled\", \"text\": \"Type capacity reload memory reload memory - C004, B04KR: 2048KB\", \"depth\": 0, \"inlineStyleRanges\": [], \"entityRanges\": [], \"data\": {}}, {\"key\": \"p0wr\", \"text\": \" \", \"type\": \"unstyled\", \"depth\": 0, \"inlineStyleRanges\": [], \"entityRanges\": [], \"data\": {}}, {\"key\": \"qpau\", \"text\": \"— From specification_en.pdf\", \"type\": \"unstyled\", \"depth\": 0, \"inlineStyleRanges\": [{\"offset\": 0, \"length\": 27, \"style\": \"ITALIC\"}], \"entityRanges\": [{\"offset\": 7, \"length\": 20, \"key\": 0}], \"data\": {}}], \"entityMap\": {\"0\": {\"type\": \"LINK\", \"mutability\": \"MUTABLE\", \"data\": {\"url\": \"https://staging-download.alli.ai/download_document/UHJvamVjdDo1ZmI3NzkwYjBmMTdmNzlmY2I3NWVjMWM=/S25vd2xlZGdlQmFzZTo2MDUyODM0ODFiYzgxNDcwZTEzNGRjNDQ=\"}}}}",
                        "answerHash": "9537b6560701930d079f39ced8be1b3e",
                        "answerFormat": "DRAFTJS",
                        "hashtags": [],
                        "feedbackAvailable": true,
                        "columnFilterValues": []
                    }
                ]
            }
        ],
        "count": 1
    },
    "errors": null
}

Uploading Q&A and Documents

Please sign up and sign in to the Alli dashboard first. You must select 'Cognitive Search' for the Project Type when you sign up. Go to the Q&A tab on the dashboard to upload question-answer pairs. If you want to upload unstructured text data such as Word, PDF, Powerpoint, and Excel file, go to the Documents tab in the dashboard and upload the documents.

If you want to automatically sync with your data source, such as MS OneDrive, please go to the Source tab. Uploading the document via API is in the Upload Document section in this page.

Getting the API KEY

Please provide your API key in the request header API-KEY. Your API key can be found in your dashboard Settings menu, under the General tab.

Providing Agent or User Information

For certain endpoints, you can add agent or user information in the request header to specify who makes the call.

Agent information can be provided in the request header AGENT-EMAIL. You can find your agents' email information in your dashboard Settings > Agent menu. Below is an example.

-H 'AGENT-EMAIL: [e-mail]'

A user ID can be provided in the request header OWN-USER-ID. The user ID can be either a new one or an existing one, and if a new user ID is provided, Alli will create a new user with that ID. Any future API calls with the same OWN-USER-ID header will be considered as they're from the same user.

If you want to update the user's email address at the same time, you can provide the email address in the request header USER-EMAIL. Below is an example.

-H 'OWN-USER-ID: 5f1234567a409876c082487z' \
-H 'USER-EMAIL: [e-mail]'

You cannot use non-ASCII characters for OWN-USER-ID. If the user ID includes any non-ASCII characters, you can encode the ID to base64 and use base64:CONVERTED_ID.

You can find saved user ID and email information in your Alli dashboard Customers menu.

Error Messages

Please read the error message you get if you don't get the response that you expected. For example, if you don't use the right HTTP method for the API, you'll get this type of error as response:

{“error”: “Method Not Allowed POST: /webapi/faq_feedbacks”}

Search from Q&A

POST https://backend.alli.ai/webapi/faq

This API lets you find the most relevant question and answer pairs from your Q&A knowledge base.

Headers

Request Body

200

The API will find the most relevant question and answers from your Q&A database.

confidence: It shows the confidence value from AI model. Shown as a number value between 0 and 1.

effectiveConfidence: When you provide feedback to the query result, it automatically trains the AI model. Effective confidence is the adjusted score with these users' and agents' feedback. Shown as a number value between 0 and 1.

question: This is the question part of the selected Q&A pair.

answer: This is the answer part of the selected Q&A pair.

id: This is used to identify the result to give or cancel feedback.

hashtags: Hashtags registered for the Q&A.

lastUpdatedDate: The date when the Q&A is last updated.

agentFeedback: The feedback from agents (through dashboard and REST calls) about this Q&A.

userFeedback: The feedback from users (through conversation) about this Q&A.

count: The number of suggested Q&As.

hashId: This hash id is being used when you call select_answer later.

The number of search results and the threshold follows your dashboard setting. Please check your settings in Q&A > Settings.

{"result": 
  [
    {
      "confidence": CONFIDENCE_VALUE, 
      "effectiveConfidence": EFFECTIVE_CONFIDENCE_VALUE, 
      "question": "QUESTION_1", 
      "answer": "ANSWER_1",
      "id": "ID_1",
      "hashtags": [],
      "lastUpdatedDate": "DATE",
      "agentFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
              },
      "userFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
              }
    }, ... 
  ],
  "count": 3,
  "hashId": "HASH_ID"
}

Request Example

Please replace YOUR_API_KEY with your one in the example below. Please see getting-api-key section.

curl -d '{ 
  "query": "How much is it?",
  "maxResults": 3, 
  "hashtags": ["wiki", "knowledge"], 
  "hashtagsOperator": "OR",
  "format": "text"}' \
-H 'API-KEY: YOUR API KEY' \
-H 'Content-Type: application/json' \
https://backend.alli.ai/webapi/faq

Response Example

{"result": 
  [
    {
      "confidence": 0.8371959004827834, 
      "effectiveConfidence": 0.9698303406362148, 
      "question": "How is the product priced?", 
      "answer": "We have a pricing table that includes a free plan.",
      "id": "ClMVIjCoNDAiZDLyNWZhM1O3YTUIIKZjPPRcER==",
      "hashtags": [],
      "lastUpdatedDate": "2020-11-19",
      "agentFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
            },
      "userFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
            }
    },
    {
      "confidence": 0.6119840535714456, 
      "effectiveConfidence": 0.7738889000171243, 
      "question": "Do you have a pricing table?", 
      "answer": "Yes we do. Please check out our website",
      "id": "RkFROjVmNDAwZDMyNWZhM2Y4YTA1ZDZjNWUwMQ==",
      "hashtags": [],
      "lastUpdatedDate": "2020-11-20",
      "agentFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
            },
      "userFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
            } 
  ],
  "count": 2,
  "hashId": "d4ca12d4e64766er0c2b45f4aa5463a4"
}

Search from Documents

POST https://backend.alli.ai/webapi/mrc

Documents API finds an answer from your unstructured text documents and even from complex tables.

Headers

Request Body

200

You will get the result as the following JSON format:

answer: It's the answer extracted from uploaded documents in the dashboard.answerHash: This is used to identify the answer to give or cancel feedback.

answerHash: This is used to identify the answer to give or cancel feedback.

confidence: It shows the confidence value from AI model. Shown as a number value between 0 and 1.

effectiveConfidence: When you provide feedback to the query result, it automatically trains the AI model. Effective confidence is the adjusted score with these users' and agents' feedback. Shown as a number value between 0 and 1.

documentId: The document's ID where the answer is extracted from.

documentName: The document's name where the answer is extracted from.hashtags: The hashtags attached to the document.

pageNo: The page number in the document where the answer was derived.

createdDate: The date when the document was uploaded.

agentFeedback: The feedback from agents (through dashboard and REST calls) about this document

userFeedback: The feedback from users about this document

body: If returnPreview is true in the request, the html body of the document search preview is displayed.

css: If returnPreview is true in the request, the css of the document search preview is displayed.

pdfPreview: If returnPdfPreview is true in the request, the URL to a PDF preview of the document with the answer highlighted is displayed. Note that the URL can be restricted using the Download IP Allowlist setting.

folder: If the answer is found from a folder under the Documents database, the folder name will be returned here.

editor: List of the agents' email who has the editor access to the documents (if they're set in the Alli dashboard).

viewer: List of the agents' email who has the viewer access to the documents. (if they're set in the Alli dashboard).

paragraphIndex: This value is needed to highlight a specific area when requesting a preview. It is used as parameters for the preview API.

The number of search results and the threshold follows your dashboard setting. Please check your setting in Documents > Settings.

{
    "result": [
        {
            "answer": "ANSWER_1",
            "answerHash": "ANSWER_HASH_1",
            "confidence": CONFIDENCE_1,
            "effectiveConfidence": EFFECTIVE_CONFIDENCE_1,
            "documentId": "DOCUMENT_ID_1",
            "documentName": "DOCUMENT_NAME_1",
            "hashtags": [],
            "pageNo": PAGE_NUMBER,
            "paragraphIndex": 0,
            "createdDate": "DATE",
            "agentFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "userFeedback": {
                "positiveCount": 0,
                "negativeCount": 0
            },
            "body": "PREVIEW_HTML_BODY",
            "css": "PREVIEW_CSS",
            "pdfPreview": "PDF_PREVIEW_URL",
            "folder": "folder 1", 
            "editor": ["[e-mail]", "[e-mail]"], 
            "viewer": ["[e-mail]"]
        }
    ]
}

Request Example (hashtags)

Please replace YOUR_API_KEY with your one in the example below. Please see getting-api-key section.

curl -X POST -d '{ 
  "query": "can I disclose the composite ratings?",
  "maxResults": 3, 
  "hashtags": ["wiki", "knowledge"], 
  "hashtagsOperator": "OR",
  "format": "text",
  "returnPdfPreview": true,
  "returnPdfPreviewRawData": true \
-H 'API-KEY: YOUR API KEY' \
-H 'Content-Type: application/json' \
https://backend.alli.ai/webapi/mrc

Request Example (combinedHashtags)

Please replace YOUR_API_KEY with your one in the example below. Please see getting-api-key section.

curl -X POST -d '{ 
  "query": "can I disclose the composite ratings?",
  "maxResults": 3, 
  "hashtags": [], 
  "hashtagsOperator": "OR",
  "combinedHashtags": [["wiki","knowledge"],["elibrary","compliance"]]
  "combinedHashtagsOperator": "AND",
  "format": "text",
  "returnPdfPreview": true,
  "returnPdfPreviewRawData": true }' \
-H 'API-KEY: YOUR API KEY' \
-H 'Content-Type: application/json' \
https://backend.alli.ai/webapi/mrc

Response Example

{
  "count": 2,
  "result": [
    {
      "answer": "an institution’s board of directors and senior management",
      "answerHash": "8430cf3b9af628abc1bb063802db39be",
      "confidence": 0.9998937845230103,
      "effectiveConfidence": 1,
      "documentId": "S25vd2xlZGdlQmFzZTo1ZjMzODFkZmNhYWJjYWUyMjkzYjFhY2U=",
      "documentName": "Policy document 1.docx",
      "hashtags": [
        "hashtag1",
        "hashtag2"
      ],
      "pageNo": 5,
      "createdDate": "2020-11-18",
      "agentFeedback": {
        "positiveCount": 1,
        "negativeCount": 0
      },
      "userFeedback": {
        "positiveCount": 0,
        "negativeCount": 0
      },
      "pdfPreviewRawData": {
        "pdfs": [
          {
            "pdfUrl": "PDF_ACTUAL_URL",
            "pageNo": 1,
            "highlight_indexes": [
                12
              ]
          },
          {
            "pdfUrl": "PDF_ACTUAL_URL",
            "pageNo": 2,
            "highlight_indexes": [
                12,
                13,
                14
              ]
          }
      ],
      "totalPageNo": 10
      },
      "pdfPreview" : "PDF_PREVIEW_URL"
      "folder": "folder 1", 
      "editor": ["[e-mail]", "[e-mail]"], 
      "viewer": ["[e-mail]"]
    },
    {
      "answer": "banks cannot, except in very limited circumstances",
      "answerHash": "d849a49662a4f21df51de24d06196547",
      "confidence": 0.9998629689216614,
      "effectiveConfidence": 0.9998629689216614,
      "documentId": "S25vd2xlZGdlQmFzZTo1ZjMzODFkZmNhYWJjYWUyMjkzYjFhY2U=",
      "documentName": "Bank policy 2020.pdf",
      "hashtags": [
        "hashtag1",
        "hashtag2"
      ],
      "pageNo": 220,
      "createdDate": "2020-11-18",
      "agentFeedback": {
        "positiveCount": 1,
        "negativeCount": 0
      },
      "userFeedback": {
        "positiveCount": 0,
        "negativeCount": 0
      },
      "pdfPreviewRawData": {
        "pdfs": [
          {
            "pdfUrl": "PDF_ACTUAL_URL",
            "pageNo": 1,
            "highlight_indexes": [
                12
              ]
          }
      ],
      "totalPageNo": 5
      },
      "pdfPreview" : "PDF_PREVIEW_URL"
    }
  ]
}

Get Single Q&A

GET https://backend.alli.ai/webapi/single_faq

This is the method to get all the details of a single Q&A.

Headers

Request Body

200 Includes fields: question: The question associated with the Q&A. answer : The answer to the question. id: The id of this Q&A. userFeedback: The feedback from users (through conversation) about this Q&A. agentFeedback: The feedback from agents (through dashboard and REST calls) about this Q&A. lastUpdatedDate, createdDate: The date when the Q&A was updated / first created. hashtags: All hashtags associated with this question.

{
    "result": {
        "question": "Who is there?",
        "answer": "Elmo",
        "id": "RkFROjYwMmY2ZTQ0YWZmMWQ5YmQ0NmM5Y2VkNw==",
        "userFeedback": {
            "positiveCount": 0,
            "negativeCount": 0
        },
        "agentFeedback": {
            "positiveCount": 0,
            "negativeCount": 1
        },
        "lastUpdatedDate": "2021-02-19",
        "createdDate": "2021-02-19",
        "hashtags": []
    }
}

Request Example

Please replace YOUR_API_KEY with your one in the example below. Please see getting-api-key section to get the api key.

curl -X GET \
-d '{"id": "iuHjHBhjHGbhjm==", "format": "text"}' \
-H "API-KEY: YOUR API KEY" \
https://backend.alli.ai/webapi/single_faq

Response Example

{
    "result": {
        "question": "Who is there?",
        "similarQuestion": ["Who's present?", "Who is it?"],
        "answer": "Elmo",
        "id": "RkFROjYwMmY2ZTQ0YWZmMWQ5YmQ0NmM5Y2VkNw==",
        "userFeedback": {
            "positiveCount": 0,
            "negativeCount": 0
        },
        "agentFeedback": {
            "positiveCount": 0,
            "negativeCount": 1
        },
        "lastUpdatedDate": "2021-02-19",
        "createdDate": "2021-02-19",
        "hashtags": []
    }
}

Get Single Document

GET https://backend.alli.ai/webapi/single_document

This is the method to get all details of a single document.

Headers

Request Body

200 You will get the result as the following JSON format. id: The Document's ID. documentName: The document's file name. createdDate: The date when the document was uploaded. hashtags: Hashtags registered for the document. agentFeedback : Counts of positive and negative ratings by employees. userFeedback: The feedback from users about this document{"result": {

      "id": "S25vd2xlZGdlQmFzZTo1ZjMzODFkZmNhYWJjYWUyMjkzYjFhY2U=",
      "documentName": "Policy document 1.docx",
      "createdDate": "2020-11-12",
      "agentFeedback": {
                "positiveCount": 1,
                "negativeCount": 0
            },
            "userFeedback": {
            "positiveCount": 0,
            "negativeCount": 0
        },
      "hashtags" : ["hashtag1", "hashtag2"]
    }
}

Request Example

Please replace YOUR_API_KEY with your one in the example below. Please see getting-api-key section to get the api key.

curl -X GET \
-d '{"id": "S25vd2xlZGdlQmFzZTo1ZjMzODFkZmNhYWJjYWUyMjkzYjFhY2U="}' \
-H "API-KEY: YOUR API KEY" \
https://backend.alli.ai/webapi/single_document

Response Example

{"result": {
      "id": "S25vd2xlZGdlQmFzZTo1ZjMzODFkZmNhYWJjYWUyMjkzYjFhY2U=",
      "documentName": "Policy document 1.docx",
      "createdDate": "2020-11-12",
      "agentFeedback": {
                "positiveCount": 1,