recommendation-api | Rank and serve recommendations | Recommender System library

by Pocket Python Version: Current License: Apache-2.0

X-Ray Key Features Code Snippets Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | recommendation-api Summary

recommendation-api is a Python library typically used in Artificial Intelligence, Recommender System, Fastapi applications. recommendation-api has no bugs, it has no vulnerabilities, it has a Permissive License and it has low support. However recommendation-api build file is not available. You can download it from GitHub.

Rank and serve recommendations

Support

Quality

Security

License

Reuse

Support

recommendation-api has a low active ecosystem.

It has 21 star(s) with 4 fork(s). There are 18 watchers for this library.

It had no major release in the last 6 months.

recommendation-api has no issues reported. There are 3 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of recommendation-api is current.

Quality

recommendation-api has no bugs reported.

Security

recommendation-api has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

License

recommendation-api is licensed under the Apache-2.0 License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

recommendation-api releases are not available. You will need to build from source code and install.

recommendation-api has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

Top functions reviewed by kandi - BETA

kandi has reviewed recommendation-api and discovered the below as its top functions. This is intended to give you an instant insight into recommendation-api implemented functionality, and help decide if they suit your requirements.

Resolve a home lineup
Return a CorpusSlateLineLookupModel
Return the ids of the ids of all recommendations
Deduplicate a list of slates
Update a user recommendations preferences
Get all available topics
Get a list of topics
Loads and returns a list of SlateLineConfigs
Parse a json file and validate it
Get a list of slates from a given experiment
Returns a list of all available rankers
Get metrics from a given module
Get Personalized topic list
Parse a JSON file and validate it
Get a CorpusSlate model
Handler for creating recommendations
Fetch a user recommendations model for a user
Get a specific slate
Get the list of items for a given user
Get a candidate set by CS_ID
Get recommendations for a given experiment
Load and validate configs
Get a new slateline profile with the fallback
Resolve SetupMomentSlate model
Get a RecitCandidateSet
Returns a list of SlateConfigModel objects
Query metrics

Get all kandi verified functions for this library.

recommendation-api Key Features

No Key Features are available at this moment for recommendation-api.

recommendation-api Examples and Code Snippets

No Code Snippets are available at this moment for recommendation-api.

Community Discussions

Trending Discussions on recommendation-api

Build Id in Azure Recommendations API's Usage Event

QUESTION

Build Id in Azure Recommendations API's Usage Event

Asked 2017-Nov-03 at 16:47

From the documentation of 'Upload usage event' (https://westus.dev.cognitive.microsoft.com/docs/services/Recommendations.V4.0/operations/577ec1847270320f24da25b1), we can tie the event with the build id.

However, from Cognitive Service Recommendation API Upload Usage Event, it seems like I need to create a new build for the event to be considered. Is that still true? If that's the case, what is the purpose of sending the build id in the usage event?

...

ANSWER

Answered 2017-Nov-03 at 16:47

The usage events need to be tied to a particular model, not a particular build.

You will notice in the URL the location where the modelId is passed: https://westus.api.cognitive.microsoft.com/recommendations/v4.0/models/{modelId}/usage/events

That just means that the next build you create for that model will take into consideration the new uploaded usage events. So, yes -- you do need to create a build after changing catalog and usage related information for that to be taken into consideration.

The only reason for the buildId to be passed as part of the usage event information is that it is helpful to get conversion metrics for a particular build. (i.e. Since you would be notifying the system when a purchase actually occurs).

NOTE: Please notice that the recommendations API will be deprecated on Feb. 15 2018 -- therefore I would advise you to use The Recommendations Solutions Template (http://aka.ms/recopcs) instead.

Thanks!

Luis Cabrera | Program Manager | Recommendations Team

Source https://stackoverflow.com/questions/47100254

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install recommendation-api

For complete instructions, see docs/development.md.
docker-compose build
docker-compose up
Visit http://localhost:8000

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: