<figure><img src=".gitbook/assets/image (8).png" alt=""><figcaption></figcaption></figure>

<figure><img src=".gitbook/assets/image (9).png" alt=""><figcaption></figcaption></figure>

To take advantage of latency savings, you can [deploy a dedicated PostgresML database](https://postgresml.org/signup) in `us-east-1` today. We make it as simple as filling out a very short form and clicking "Create database".

April 21, 2023

This article is the first in a multipart series that will show you how to build a post-modern semantic search and recommendation engine, including personalization, using open source models.

| GPU | 17ms | $72 | 6 hours |

| OpenAI | 300ms | $299 | millennia |

You can also find embedding models that outperform OpenAI's `text-embedding-ada-002` model across many different tests on the [leaderboard](https://huggingface.co/spaces/mteb/leaderboard). It's always best to do your own benchmarking with your data, models, and hardware to find the best fit for your use case.

Save 25% on your ticket with our discount code: 2024\_POSTGRESML\_25

{% endhint %}

PostgresML CEO and founder, Montana Low, will kick off the event on April 17th with a keynote about navigating the confluence of hardware evolution and machine learning technology.&#x20;

We’ll also be hosting a masterclass in retrieval augmented generation (RAG) on April 18th. Our own Silas Marvin will give hands-on guidance to equip you with the ability to implement RAG directly within your database.&#x20;

So, why sit on the sidelines when you could be right in the thick of it, soaking up knowledge, making connections, and maybe even stumbling upon your next big breakthrough? Clear your schedule, grab your ticket, and get ready to geek out with us in San Jose.

See you there!

| Full Text Search | - | ✅ |

| Geospatial Search | - | ✅ |

Both MindsDB and PostgresML support many classical machine learning algorithms to do classification and regression. They are both able to load ~~the latest LLMs~~ some models from Hugging Face, supported by underlying implementations in libtorch. I had to cross that out after exploring all the caveats in the MindsDB implementations. PostgresML supports the models released immediately as long as underlying dependencies are met. MindsDB has to release an update to support any new models, and their current model support is extremely limited. New algorithms, tasks, and models are constantly released, so it's worth checking the documentation for the latest list.

Another difference is that PostgresML also supports embedding models, and closely integrates them with vector search inside the database, which is well beyond the scope of MindsDB, since it's not a database at all. PostgresML has direct access to all the functionality provided by other Postgres extensions, like vector indexes from [pgvector](https://github.com/pgvector/pgvector) to perform efficient KNN & ANN vector recall, or [PostGIS](http://postgis.net/) for geospatial information as well as built in full text search. Multiple algorithms and extensions can be combined in compound queries to build state-of-the-art systems, like search and recommendations or fraud detection that generate an end to end result with a single query, something that might take a dozen different machine learning models and microservices in a more traditional architecture.

| translation\_en\_to\_es | t5-base | 1573 | 1148 | 294 |

| summarization | sshleifer/distilbart-cnn-12-6 | 4289 | 3450 | 479 |

There is a general trend, the larger and slower the model is, the more work is spent inside libtorch, the less the performance of the rest matters, but for interactive models and use cases there is a significant difference. We've tried to cover the most generous use case we could between these two. If we were to compare XGBoost or other classical algorithms, that can have sub millisecond prediction times in PostgresML, the 20ms Python service overhead of MindsDB just to parse the incoming query would be hundreds of times slower.

PostgreSQL is designed to be _**extensible**_. This has created a rich open-source ecosystem of additional functionality built around the core project. Some [extensions](https://www.postgresql.org/docs/current/contrib.html) are include in the base Postgres distribution, but others are also available via the [PostgreSQL Extension Network](https://pgxn.org/).\

There are 2 foundational extensions included in a PostgresML deployment that provide functionality inside the database through SQL APIs.

* **pgml** - provides Machine Learning and Artificial Intelligence APIs with access to more than 50 ML algorithms to train classification, clustering and regression models on your own data, or you can perform dozens of tasks with thousands of models downloaded from HuggingFace.

| Full Text Search | - | ✅ |

| Geospatial Search | - | ✅ |

Both MindsDB and PostgresML support many classical machine learning algorithms to do classification and regression. They are both able to load ~~the latest LLMs~~ some models from Hugging Face, supported by underlying implementations in libtorch. I had to cross that out after exploring all the caveats in the MindsDB implementations. PostgresML supports the models released immediately as long as underlying dependencies are met. MindsDB has to release an update to support any new models, and their current model support is extremely limited. New algorithms, tasks, and models are constantly released, so it's worth checking the documentation for the latest list.

Another difference is that PostgresML also supports embedding models, and closely integrates them with vector search inside the database, which is well beyond the scope of MindsDB, since it's not a database at all. PostgresML has direct access to all the functionality provided by other Postgres extensions, like vector indexes from [pgvector](https://github.com/pgvector/pgvector) to perform efficient KNN & ANN vector recall, or [PostGIS](http://postgis.net/) for geospatial information as well as built in full text search. Multiple algorithms and extensions can be combined in compound queries to build state-of-the-art systems, like search and recommendations or fraud detection that generate an end to end result with a single query, something that might take a dozen different machine learning models and microservices in a more traditional architecture.