You signed in with another tab or window.Reload to refresh your session.You signed out in another tab or window.Reload to refresh your session.You switched accounts on another tab or window.Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: pgml-cms/docs/README.md
+6-6Lines changed: 6 additions & 6 deletions
Original file line number
Diff line number
Diff line change
@@ -6,17 +6,17 @@ description: The key concepts that make up PostgresML.
6
6
7
7
PostgresML is a complete MLOps platform built on PostgreSQL. Our operating principle is:
8
8
9
-
>_Movethemodels to the database, rather than constantly moving the data to the models._
9
+
>_Move models to the database, rather than constantly moving data to the models._
10
10
11
-
The datafor ML & AI systems is inherently larger and more dynamic than the models. It's more efficient, manageable and reliable to move the models to the database, rather than continuously moving data to the models.
11
+
Datafor ML & AI systems is inherently larger and more dynamic than the models. It's more efficient, manageable and reliable to move models to the database, rather than continuously moving data to the models.
12
12
13
13
##AI engine
14
14
15
15
PostgresML allows you to take advantage of the fundamental relationship between data and models, by extending the database with the following capabilities:
16
16
17
17
***Model Serving** - GPU accelerated inference engine for interactive applications, with no additional networking latency or reliability costs
18
-
***Model Store** - Access to open-source models including state of the art LLMs fromHuggingFace, and track changes in performance between versions
19
-
***Model Training** - Train models with your application data using more than 50 algorithms for regression, classification or clustering tasks; fine tune pre-trained models likeLLaMA and BERT to improve performance
18
+
***Model Store** - Access to open-source models including state of the art LLMs fromHugging Face, and track changes in performance between versions
19
+
***Model Training** - Train models with your application data using more than 50 algorithms for regression, classification or clustering tasks; fine tune pre-trained models likeLlama and BERT to improve performance
20
20
***Feature Store** - Scalable access to model inputs, including vector, text, categorical, and numeric data: vector database, text search, knowledge graph and application data all in one low-latency system
21
21
22
22
<figure><imgsrc=".gitbook/assets/ml_system.svg"alt="Machine Learning Infrastructure (2.0) by a16z"><figcaptionclass="mt-2"><p>PostgresML handles all of the functions <ahref="https://a16z.com/emerging-architectures-for-modern-data-infrastructure/">described by a16z</a></p></figcaption></figure>
@@ -34,14 +34,14 @@ The PostgresML team also provides [native language SDKs](https://github.com/post
34
34
35
35
While using the SDK is completely optional, SDK clients can perform advanced machine learning tasks in a single SQL request, without having to transfer additional data, models, hardware or dependencies to the client application.
36
36
37
-
Use cases include:
37
+
Some of the use cases include:
38
38
39
39
* Chat with streaming responses from state-of-the-art open source LLMs
40
40
* Semantic search with keywords and embeddings
41
41
* RAG in a single request without using any third-party services
42
42
* Text translation between hundreds of languages
43
43
* Text summarization to distill complex documents
44
-
* Forecastingtimeseries data for key metrics with and metadata
44
+
* Forecastingtime series data for key metrics with and metadata
Copy file name to clipboardExpand all lines: pgml-cms/docs/introduction/getting-started/README.md
+9-7Lines changed: 9 additions & 7 deletions
Original file line number
Diff line number
Diff line change
@@ -2,16 +2,18 @@
2
2
description:Setup a database and connect your application to PostgresML
3
3
---
4
4
5
-
#GettingStarted
5
+
#Gettingstarted
6
6
7
-
A PostgresML deployment consists of multiple components working in concert to provide a complete Machine Learning platform. We provide a fully managed solution in[our cloud](create-your-database), and document a self-hosted installation in[Developer Docs](/docs/resources/developer-docs/quick-start-with-docker).
7
+
A PostgresML deployment consists of multiple components working in concert to provide a complete Machine Learning platform:
8
8
9
-
* PostgreSQL database, with`pgml`,`pgvector` and many other extensionsinstalled, including backups, metrics, logs, replicas andhigh availability
10
-
* PgCat pooler toprovide secure access and model load balancing acrossthousands of clients
11
-
* A web application to manage deployed models and share experimentsandanalysisin SQL notebooks
9
+
* PostgreSQL database, with`pgml`,`pgvector` and many other extensionsthat add features useful in day-to-day andmachine learning use cases
We provide a fully managed solution in[our cloud](create-your-database), and document a self-hosted installation in the[Developer Docs](/docs/resources/developer-docs/quick-start-with-docker).
By building PostgresML on top of a mature database, we get reliable backups for model inputs and proven scalability without reinventing the wheel, so that we can focus on providing access to the latest developments in open source machine learning and artificial intelligence.
16
18
17
-
This guide will help you get started with a generous free account, that includes access to GPU accelerated models and 5 GB of storage, or you can skip to our[Developer Docs](/docs/resources/developer-docs/quick-start-with-docker) to see how to run PostgresML locally with our Docker image.
19
+
This guide will help you get started with a generous[free account](create-your-database), that includes access to GPU accelerated models and 5 GB of storage, or you can skip to our[Developer Docs](/docs/resources/developer-docs/quick-start-with-docker) to see how to run PostgresML locally with our Docker image.