Levelfish API Overview
The LevelFish Paraphrase API allows you or your customers to generate multiple paraphrases from a single sentence. Designed to provide multiple-choice options for Conversational AI or chatbot training data, the API can take a single or multiple utterance input and return a number of paraphrases that match the original intent.
Download the Levelfish API guide here...
Access LevelFish docs here..
How does it work
LevelFish combines a number of AI NLG inference engines combined to generate the most relevant alternative phrasing. This is filtered through a set of quality filters to provide a high quality paraphrase set. Some of these engines are designed to focus on word use, while others are designed to focus on originality of rephrasing.
To use any of the LevelFish APIs you will require:
an account and an API token. Contact firstname.lastname@example.org if you don’t have these.
An API identifier - this is the name of the paraphrase engine you will use to generate your paraphrases.
Adding your API Token to your request headers will authorise the transaction. Any requests to the LevelFish services using your API Token will be attributed to your contract, allowance or costs. If you feel the API Token may have been compromised, please request a replacement as soon as possible.
Using the API
To generate paraphrases we have several alternative methods:
For demonstrations and simple use:
Synchronous, Single/Multiple-phrase, simple results
For production implementation:
Synchronous, Single/Multiple-phrase, detailed results
Asynchronous, Single/Multiple-phrase, detailed results
With an additional feedback loop
Synchronous, Single/Multiple-phrase, detailed results with feedback (RECOMMENDED)
Asynchronous, Single/Multiple-phrase, detailed results with feedback
phrase, simple results
This is ideal for testing or demonstrating paraphrase examples.
This is not recommended for a production implementation as it cannot be used alongside the feedback API. This API call requires the API authentication token
phrase, detailed results
This is ideal for a simple implementation and gives information about the source of all the Engines used to generate the paraphrases, an indication of what has been removed by filters and provides the itemIDs needed for a feedback API implementation at some later date.
phrase, detailed results
This is ideal for batch processing paraphrase requests. If you wish to send more than 5 phrases at a time it may be better to batch those requests and asynchronously pick up the results.
Method 4: (RECOMMENDED)
Synchronous, Single/Multiple- phrase, detailed results with
This method is the recommended implementation as it is a synchronous request which makes the reaction real-time.In addition, it provides the ItemIDs needed to be able to give feedback which paraphrases the user has selected.
phrase, detailed results with
This method can be used for batch processing tasks as above, but with the added feedback call.