RedisML

RedisML is an archived, superseded Redis module for teams needing lightweight machine-learning inference, and it stores trained models as data types and…

  • AI
  • Databases
RedisML is an archived, superseded Redis module for teams needing lightweight machine-learning inference, and it stores trained models as data types and serves predictions or recommendations directly from Redis; new deployments should prefer RedisAI for deep-learning support.

Platform availability

Available on 0 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

32/100 Low

Maintained
0GitHub repository is archived
Popular
50305 GitHub stars
Easy to install
250 install platforms, install notes, Docker image
Light to run
108 GB minimum RAM
Security check
95no serious findings, CI, tests
GitHub stars
305
Open issues
8
Last commit
2019-06-22
Latest release
v0.99.2
Activity
stale

Checked 3 days ago - source: GitHub (RedisLabsModules/redisml)

Resources & Compatibility

Minimum requirements: 8 GB RAM, 2 CPU core(s). ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Superseded by RedisAI RedisML is no longer maintained and its repository is archived. The project is planned to be replaced by RedisAI, which adds deep learning support. Use RedisAI for new deployments. source
  • Maintenance status The RedisML GitHub repository is archived and the project is no longer maintained (last activity 2019). source
  • Deprecation RedisML is superseded by RedisAI; prefer RedisAI for new deployments because it adds deep-learning support. source
  • Archived status Repository is archived; use RedisAI for new deployments. source
  • Install Install RedisML as a Redis module, then load trained models from any platform; the models serve predictions directly. source
  • Model Loading Load ML models from any platform, immediately ready to serve. source

Fetched 3 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How can I load RedisML into Redis?

Start Redis with the --loadmodule option pointing to redis-ml.so, add it as a configuration directive, or send the MODULE LOAD command.

How should I number the trees when adding them to a RedisML forest?

Use numeric tree IDs that start at 0 and increase by exactly 1 for each new tree.

How do I run a classification prediction on a stored RedisML forest?

Send ML.FOREST.RUN with the forest key, the input vector, and the CLASSIFICATION argument.

Can I bring trained models from another platform into RedisML?

The documentation says ML models can be loaded from any platform and then used to serve predictions.

Answers sourced from github.com

Community

Collected 47 days ago - public community threads