Retrieve Answers

import requests
endpoint = "https://api-prod.usefini.com/v2/bots/ask-question"

question = "How do I upgrade to premium?"
instruction = "Answer as if you are replying to an email."

# The instruction part (role: 'system') in messageHistory is optional.
# If you skip it (set to []) the instruction from Fini's UI setup page will be picked up instead.
messageHistory = [{"content": instruction, "role": "system"}] # This is optional

data = {"question": question, "messageHistory": messageHistory} // optional parameters: stream, temperature, stop, categories

token = "your_api_key_here"  # Best stored in secrets management
headers = {"Authorization": "Bearer " + token}

# Make sure your 'content-type' header is set to 'application/json'
answer = requests.post(endpoint, json=data, headers=headers)
# This response will contain an updated messageHistory
# Re-use this messageHistory in a new request to enable chat mode

print(answer.json());

{
    "answer": "Hello there! Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes. Let me know if you need more details. Have a fantastic day!",
    "answer_uuid": "f4ead1e0-576b-489f-bc59-7b1c6c43ee27",
    "based_on": [
        {
            "answer": "Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes",
            "score": 0.726,
            "source_id": "https://usefini.com",
            "source_type": "url",
        }
    ],
   "categories": [
           "Fini intro"
       ],
    "messages": [
        {
            "content": "Answer in friendly tone",
            "role": "system"
        },
        {
            "content": "What is Fini?",
            "role": "user"
        },
        {
            "content": "Hello there! Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes. Let me know if you need more details. Have a fantastic day!",
            "role": "assistant"
        }
    ]
}

POST

bots

ask-question

import requests
endpoint = "https://api-prod.usefini.com/v2/bots/ask-question"

question = "How do I upgrade to premium?"
instruction = "Answer as if you are replying to an email."

# The instruction part (role: 'system') in messageHistory is optional.
# If you skip it (set to []) the instruction from Fini's UI setup page will be picked up instead.
messageHistory = [{"content": instruction, "role": "system"}] # This is optional

data = {"question": question, "messageHistory": messageHistory} // optional parameters: stream, temperature, stop, categories

token = "your_api_key_here"  # Best stored in secrets management
headers = {"Authorization": "Bearer " + token}

# Make sure your 'content-type' header is set to 'application/json'
answer = requests.post(endpoint, json=data, headers=headers)
# This response will contain an updated messageHistory
# Re-use this messageHistory in a new request to enable chat mode

print(answer.json());

{
    "answer": "Hello there! Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes. Let me know if you need more details. Have a fantastic day!",
    "answer_uuid": "f4ead1e0-576b-489f-bc59-7b1c6c43ee27",
    "based_on": [
        {
            "answer": "Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes",
            "score": 0.726,
            "source_id": "https://usefini.com",
            "source_type": "url",
        }
    ],
   "categories": [
           "Fini intro"
       ],
    "messages": [
        {
            "content": "Answer in friendly tone",
            "role": "system"
        },
        {
            "content": "What is Fini?",
            "role": "user"
        },
        {
            "content": "Hello there! Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes. Let me know if you need more details. Have a fantastic day!",
            "role": "assistant"
        }
    ]
}

Body

instruction

string

Prompt to generate completions. If you remove this parameter from your request, the instruction from Fini’s UI setup page will be picked up instead. We recommend always filling this for faster responses (skips DB lookup of instruction)

question

string

required

User question for which the answer needs to be fetched

messageHistory

array

required

A list of messages comprising the conversation so far.

Show Toggle object

role

string

required

The role of the messages author. One of system, user, assistant, or function.

content

string

required

The contents of the message. content is required for all messages except assistant messages with function calls.

functions

array

A list of functions the model may generate JSON inputs for.

Show Toggle object

name

string

required

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

description

string

A description of what the function does, used by the model to choose when and how to call the function.

parameters

object

required

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.To describe a function which accepts no parameters, provide the value {"type": "object", "properties": {}}.

function_call

string or object

Controls how the model responds to function calls. “none” means the model does not call a function, and responds to the end-user. “auto” means the model can pick between an end-user or calling a function. Specifying a particular function via {"name":\ "my_function"} forces the model to call that function. “none” is the default when no functions are present. “auto” is the default if functions are present.

user_attributes

object

The user_attributes object contains key-value pairs representing user specific information and attributes within the system. Each attribute is defined by a key-value pair where the key is a string and the value can be a string, boolean, or numeric type. These attributes capture user details, enabling personalized responses and workflow handling.

stream

boolean

default:"false"

Whether to stream back partial progress.

temperature

number

default:"0.4"

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We recommend using 0.4 as the default.

stop

string

The API will stop generating further tokens. The returned text will not contain the stop sequence. It can be set to [“Optional”, “stop”, “words”]

Response

success

number

Indicates whether the call was successful. 1 if successful, 0 if not.

based_on

object

The contents of the “based_on” field. “based_on” is a list of all data blocks from the knowledgbase that were used to generate the answer

Show Toggle object

source_id

string

Link of the source that was used to generate the answer

source_type

string

Source Type- which could be url, specific file, or a third party integration like Zendesk

score

number

Matching score with the user query

messages

object

A list of messages comprising the conversation so far.

import requests
endpoint = "https://api-prod.usefini.com/v2/bots/ask-question"

question = "How do I upgrade to premium?"
instruction = "Answer as if you are replying to an email."

# The instruction part (role: 'system') in messageHistory is optional.
# If you skip it (set to []) the instruction from Fini's UI setup page will be picked up instead.
messageHistory = [{"content": instruction, "role": "system"}] # This is optional

data = {"question": question, "messageHistory": messageHistory} // optional parameters: stream, temperature, stop, categories

token = "your_api_key_here"  # Best stored in secrets management
headers = {"Authorization": "Bearer " + token}

# Make sure your 'content-type' header is set to 'application/json'
answer = requests.post(endpoint, json=data, headers=headers)
# This response will contain an updated messageHistory
# Re-use this messageHistory in a new request to enable chat mode

print(answer.json());

{
    "answer": "Hello there! Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes. Let me know if you need more details. Have a fantastic day!",
    "answer_uuid": "f4ead1e0-576b-489f-bc59-7b1c6c43ee27",
    "based_on": [
        {
            "answer": "Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes",
            "score": 0.726,
            "source_id": "https://usefini.com",
            "source_type": "url",
        }
    ],
   "categories": [
           "Fini intro"
       ],
    "messages": [
        {
            "content": "Answer in friendly tone",
            "role": "system"
        },
        {
            "content": "What is Fini?",
            "role": "user"
        },
        {
            "content": "Hello there! Fini is an AI tool that helps companies turn their knowledgebase into AI chat in 2 minutes. Let me know if you need more details. Have a fantastic day!",
            "role": "assistant"
        }
    ]
}

Authentication Store feedback

API Documentation

Endpoint Examples

Retrieve Answers

Body

Response

API Documentation

Endpoint Examples

​Body

​Response

Body

Response