Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Commit a1ef779

Browse filesBrowse files
committed
Updated with more tasks
2 parents c347f9b + 4f21192 commit a1ef779
Copy full SHA for a1ef779

File tree

1 file changed

+0
-68
lines changed
Filter options

1 file changed

+0
-68
lines changed

‎README.md

Copy file name to clipboardExpand all lines: README.md
-68Lines changed: 0 additions & 68 deletions
Original file line numberDiff line numberDiff line change
@@ -271,7 +271,6 @@ SELECT pgml.transform(
271271
```
272272

273273
### Natural Language Inference (NLI)
274-
275274
NLI, or Natural Language Inference, is a type of model that determines the relationship between two texts. The model takes a premise and a hypothesis as inputs and returns a class, which can be one of three types:
276275
- Entailment: This means that the hypothesis is true based on the premise.
277276
- Contradiction: This means that the hypothesis is false based on the premise.
@@ -578,73 +577,6 @@ SELECT pgml.transform(
578577
# Regression
579578
# Classification
580579

581-
<!-- # Applications
582-
## Text
583-
- AI writing partner
584-
- Chatbot for customer support
585-
- Social media post analysis
586-
- Fintech
587-
- Healthcare
588-
- Insurance
589-
590-
591-
### Tabular data
592-
- Fraud detection
593-
- Recommendation
594-
595-
596-
## Benefits
597-
- Access to hugging face models - a little more about open source language models
598-
- Ease of fine tuning and why
599-
- Rust based extension and its benefits
600-
- Problems with HTTP serving and how PML enables microsecond latency
601-
- Pgcat for horizontal scaling -->
602-
603-
## Concepts
604-
- Database
605-
- Extension
606-
- ML on text data
607-
- Transform operation
608-
- Fine tune operation
609-
- ML on tabular data
610-
- Train operation
611-
- Deploy operation
612-
- Predict operation
613-
614-
## Deployment
615-
- Docker images
616-
- CPU
617-
- GPU
618-
- Data persistence on local/EC2/EKS
619-
- Deployment on AWS using docker images
620-
621-
## What's in the box
622-
See the documentation for a complete **[list of functionality](https://postgresml.org/)**.
623-
624-
### All your favorite algorithms
625-
Whether you need a simple linear regression, or extreme gradient boosting, we've included support for all classification and regression algorithms in [Scikit Learn](https://scikit-learn.org/) and [XGBoost](https://xgboost.readthedocs.io/) with no extra configuration.
626-
627-
### Managed model deployments
628-
Models can be periodically retrained and automatically promoted to production depending on their key metric. Rollback capability is provided to ensure that you're always able to serve the highest quality predictions, along with historical logs of all deployments for long term study.
629-
630-
### Online and offline support
631-
Predictions are served via a standard Postgres connection to ensure that your core apps can always access both your data and your models in real time. Pure SQL workflows also enable batch predictions to cache results in native Postgres tables for lookup.
632-
633-
### Instant visualizations
634-
Run standard analysis on your datasets to detect outliers, bimodal distributions, feature correlation, and other common data visualizations on your datasets. Everything is cataloged in the dashboard for easy reference.
635-
636-
### Hyperparameter search
637-
Use either grid or random searches with cross validation on your training set to discover the most important knobs to tweak on your favorite algorithm.
638-
639-
### SQL native vector operations
640-
Vector operations make working with learned embeddings a snap, for things like nearest neighbor searches or other similarity comparisons.
641-
642-
### The performance of Postgres
643-
Since your data never leaves the database, you retain the speed, reliability and security you expect in your foundational stateful services. Leverage your existing infrastructure and expertise to deliver new capabilities.
644-
645-
### Open source
646-
We're building on the shoulders of giants. These machine learning libraries and Postgres have received extensive academic and industry use, and we'll continue their tradition to build with the community. Licensed under MIT.
647580

648-
## Frequently Asked Questions (FAQs)
649581

650582

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.