Skip to main content

Mirage API Python wrapper.

Project description

python-mirage-api

Build and Release PyPI Downloads

The Mirage API Python wrapper. Access AI inference services.

Copyright 2023 Crisp IM SAS. See LICENSE for copying information.

Usage

Install the library:

pip install mirage-api

Then, import it:

from mirage_api import Mirage

Construct a new authenticated Mirage client with your user_id and secret_key tokens.

client = Mirage("ui_xxxxxx", "sk_xxxxxx")

Then, consume the client eg. to transcribe a audio file containing speech to text:

data = client.task.transcribe_speech({
  "locale": {
    "to": "en"
  },

  "media": {
    "type": "audio/webm",
    "url": "https://files.mirage-ai.com/dash/terminal/samples/transcribe-speech/hey-there.weba"
  }
})

Authentication

To authenticate against the API, get your tokens (user_id and secret_key).

Then, pass those tokens once when you instanciate the Mirage client as following:

# Make sure to replace 'user_id' and 'secret_key' with your tokens
client = Mirage("user_id", "secret_key")

Resource Methods

This library implements all methods the Mirage API provides. See the API docs for a reference of available methods, as well as how returned data is formatted.

Task API

➡️ Transcribe Speech

client.task.transcribe_speech({
  "locale": {
    "to": "en"
  },

  "media": {
    "type": "audio/webm",
    "url": "https://files.mirage-ai.com/dash/terminal/samples/transcribe-speech/hey-there.weba"
  }
});
  • Response:
{
  "reason": "processed",

  "data": {
    "locale": "en",

    "parts": [
      {
        "start": 5.0,
        "end": 9.0,
        "text": " I'm just speaking some seconds to see if the translation is correct"
      }
    ]
  }
}

➡️ Answer Prompt

  • Method: client.task.answer_prompt(data)

  • Reference: Answer Prompt

  • Request:

client.task.answer_prompt({
  "prompt": "Generate an article about Alpacas"
});
  • Response:
{
  "reason": "processed",

  "data": {
    "answer": "The alpaca (Lama pacos) is a species of South American camelid mammal. It is similar to, and often confused with, the llama. However, alpacas are often noticeably smaller than llamas. The two animals are closely related and can successfully crossbreed. Both species are believed to have been domesticated from their wild relatives, the vicuña and guanaco. There are two breeds of alpaca: the Suri alpaca and the Huacaya alpaca."
  }
}

➡️ Answer Question

  • Method: client.task.answer_question(data)

  • Reference: Answer Question

  • Request:

client.task.answer_question({
  "question": "Should I pay more for that?",

  "answer": {
    "start": "Sure,"
  },

  "context": {
    "primary_id": "cf4ccdb5-df44-4668-a9e7-3ab31bebf89b",

    "conversation": {
      "messages": [
        {
          "from": "customer",
          "text": "Hey there!"
        },

        {
          "from": "agent",
          "text": "Hi. How can I help?"
        },

        {
          "from": "customer",
          "text": "I want to add more sub-domains to my website."
        }
      ]
    }
  }
});
  • Response:
{
  "reason": "processed",

  "data": {
    "answer": "You can add the Crisp chatbox to your website by following this guide: https://help.crisp.chat/en/article/how-to-add-crisp-chatbox-to-your-website-dkrg1d/ :)"
  }
}

➡️ Summarize Paragraphs

client.task.summarize_paragraphs({
  "paragraphs": [
    {
      "text": "GPT-4 is getting worse over time, not better."
    },

    {
      "text": "Many people have reported noticing a significant degradation in the quality of the model responses, but so far, it was all anecdotal."
    }
  ]
});
  • Response:
{
  "reason": "processed",

  "data": {
    "summary": "GPT-4 is getting worse over time, not better. We have a new version of GPT-4 that is not improving, but it is regressing."
  }
}

➡️ Summarize Conversation

client.task.summarize_conversation({
  "transcript": [
    {
      "name": "Valerian",
      "text": "Hello! I have a question about the Crisp chatbot, I am trying to setup a week-end auto-responder, how can I do that?"
    },

    {
      "name": "Baptiste",
      "text": "Hi. Baptiste here. I can provide you an example bot scenario that does just that if you'd like?"
    }
  ]
});
  • Response:
{
  "reason": "processed",

  "data": {
    "summary": "Valerian wants to set up a week-end auto-responder on Crisp chatbot. Baptiste can give him an example."
  }
}

➡️ Categorize Conversations

client.task.categorize_conversations({
  "conversations": [
    {
      "transcript": [
        {
          "from": "customer",
          "text": "Hello! I have a question about the Crisp chatbot, I am trying to setup a week-end auto-responder, how can I do that?"
        },

        {
          "from": "agent",
          "text": "Hi. Baptiste here. I can provide you an example bot scenario that does just that if you'd like?"
        }
      ]
    }
  ]
});
  • Response:
{
  "reason": "processed",

  "data": {
    "categories": [
      "Chatbot Configuration Issue"
    ]
  }
}

➡️ Rank Question

  • Method: client.task.rank_question(data)

  • Reference: Rank Question

  • Request:

client.task.rank_question({
  "question": "Hi! I am having issues setting up DNS records for my Crisp helpdesk. Can you help?",

  "context": {
    "source": "helpdesk",
    "primary_id": "cf4ccdb5-df44-4668-a9e7-3ab31bebf89b"
  }
});
  • Response:
{
  "reason": "processed",

  "data": {
    "results": [
      {
        "id": "15fd3f24-56c8-435e-af8e-c47d4cd6115c",
        "score": 9,
        "grouped_text": "Setup your Helpdesk domain name\ntutorials for most providers",

        "items": [
          {
            "source": "helpdesk",
            "primary_id": "51a32e4c-1cb5-47c9-bcc0-3e06f0dce90a",
            "secondary_id": "15fd3f24-56c8-435e-af8e-c47d4cd6115c",
            "text": "Setup your Helpdesk domain name\ntutorials for most providers",

            "metadata": {
              "title": "Setup your Helpdesk domain name"
            }
          }
        ]
      }
    ]
  }
}

➡️ Translate Text

  • Method: client.task.translate_text(data)

  • Reference: Translate Text

  • Request:

client.task.translate_text({
  "locale": {
    "from": "fr",
    "to": "en"
  },

  "type": "html",
  "text": "Bonjour, comment puis-je vous aider <span translate=\"no\">Mr Saliou</span> ?"
});
  • Response:
{
  "reason": "processed",

  "data": {
    "translation": "Hi, how can I help you Mr Saliou?"
  }
}

➡️ Fraud Spamicity

  • Method: client.task.fraud_spamicity(data)

  • Reference: Fraud Spamicity

  • Request:

client.task.fraud_spamicity({
  "name": "Crisp",
  "domain": "crisp.chat",
  "email_domain": "mail.crisp.chat"
});
  • Response:
{
  "reason": "processed",

  "data": {
    "fraud": false,
    "score": 0.13
  }
}

Data API

➡️ Context Ingest

client.data.context_ingest({
  "items": [
    {
      "operation": "index",
      "primary_id": "pri_cf44dd72-4ba9-4754-8fb3-83c4261243c4",
      "secondary_id": "sec_6693a4a2-e33f-4cce-ba90-b7b5b0922c46",
      "tertiary_id": "ter_de2bd6e7-74e1-440d-9a23-01964cd4b7da",

      "text": "Text to index here...",
      "source": "chat",
      "timestamp": 1682002198552,

      "metadata": {
        "custom_key": "custom_value",
        "another_key": "another_value"
      }
    }
  ]
});
  • Response:
{
  "reason": "processed",

  "data": {
    "imported": true
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mirage-api-1.5.0.tar.gz (6.7 kB view details)

Uploaded Source

Built Distribution

mirage_api-1.5.0-py3-none-any.whl (7.4 kB view details)

Uploaded Python 3

File details

Details for the file mirage-api-1.5.0.tar.gz.

File metadata

  • Download URL: mirage-api-1.5.0.tar.gz
  • Upload date:
  • Size: 6.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for mirage-api-1.5.0.tar.gz
Algorithm Hash digest
SHA256 43419620a5e1e6768442dc0ffb44207f76806c48cc2fbac8f507b5df3b0d3cb4
MD5 ccf33eaad023fd0ab95a8572cccf9c0c
BLAKE2b-256 8cdc4a48cae0e1eadd3a5290ae4bc499910fec024c2203cb555cbf8b3ffa218c

See more details on using hashes here.

Provenance

File details

Details for the file mirage_api-1.5.0-py3-none-any.whl.

File metadata

  • Download URL: mirage_api-1.5.0-py3-none-any.whl
  • Upload date:
  • Size: 7.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for mirage_api-1.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 391d7f8a6617fe2dc97a34504797d0e064682ee2e260a3475bda3254a2991a60
MD5 4b9b9c950f26f104104fb605f4402d2b
BLAKE2b-256 31c692d953263e9313c8b865f0c0d271fbe14c2d2e7612dc10406d940f659c4b

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page