🌐 AI搜索 & 代理 主页
Skip to content

Commit f962797

Browse files
authored
Docs pass (#1419)
1 parent 82dc23f commit f962797

File tree

14 files changed

+383
-102
lines changed

14 files changed

+383
-102
lines changed
Lines changed: 57 additions & 0 deletions
Loading
107 KB
Loading
46.7 KB
Loading
157 KB
Loading
48.1 KB
Loading
52.1 KB
Loading
70.3 KB
Loading

pgml-cms/docs/README.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -6,17 +6,17 @@ description: The key concepts that make up PostgresML.
66

77
PostgresML is a complete MLOps platform built on PostgreSQL. Our operating principle is:
88

9-
> _Move the models 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._
1010
11-
The data for 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+
Data for 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.
1212

1313
## AI engine
1414

1515
PostgresML allows you to take advantage of the fundamental relationship between data and models, by extending the database with the following capabilities:
1616

1717
* **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 from HuggingFace, 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 like LLaMA and BERT to improve performance
18+
* **Model Store** - Access to open-source models including state of the art LLMs from Hugging 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 like Llama and BERT to improve performance
2020
* **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
2121

2222
<figure><img src=".gitbook/assets/ml_system.svg" alt="Machine Learning Infrastructure (2.0) by a16z"><figcaption class="mt-2"><p>PostgresML handles all of the functions <a href="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
3434

3535
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.
3636

37-
Use cases include:
37+
Some of the use cases include:
3838

3939
* Chat with streaming responses from state-of-the-art open source LLMs
4040
* Semantic search with keywords and embeddings
4141
* RAG in a single request without using any third-party services
4242
* Text translation between hundreds of languages
4343
* Text summarization to distill complex documents
44-
* Forecasting timeseries data for key metrics with and metadata
44+
* Forecasting time series data for key metrics with and metadata
4545
* Anomaly detection using application data
4646

4747
## Our mission

pgml-cms/docs/SUMMARY.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
## Introduction
44

55
* [Overview](README.md)
6-
* [Getting Started](introduction/getting-started/README.md)
6+
* [Getting started](introduction/getting-started/README.md)
77
* [Create your database](introduction/getting-started/create-your-database.md)
88
* [Connect your app](introduction/getting-started/connect-your-app.md)
99
* [Import your data](introduction/getting-started/import-your-data/README.md)
@@ -52,12 +52,12 @@
5252

5353
## Product
5454

55-
* [Cloud Database](product/cloud-database/README.md)
55+
* [Cloud database](product/cloud-database/README.md)
5656
* [Serverless](product/cloud-database/serverless.md)
5757
* [Dedicated](product/cloud-database/dedicated.md)
5858
* [Enterprise](product/cloud-database/plans.md)
59-
* [Vector Database](product/vector-database.md)
60-
* [PgCat Proxy](product/pgcat/README.md)
59+
* [Vector database](product/vector-database.md)
60+
* [PgCat pooler](product/pgcat/README.md)
6161
* [Features](product/pgcat/features.md)
6262
* [Installation](product/pgcat/installation.md)
6363
* [Configuration](product/pgcat/configuration.md)

pgml-cms/docs/introduction/getting-started/README.md

Lines changed: 9 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -2,16 +2,18 @@
22
description: Setup a database and connect your application to PostgresML
33
---
44

5-
# Getting Started
5+
# Getting started
66

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:
88

9-
* PostgreSQL database, with `pgml`, `pgvector` and many other extensions installed, including backups, metrics, logs, replicas and high availability
10-
* PgCat pooler to provide secure access and model load balancing across thousands of clients
11-
* A web application to manage deployed models and share experiments and analysis in SQL notebooks
9+
* PostgreSQL database, with `pgml`, `pgvector` and many other extensions that add features useful in day-to-day and machine learning use cases
10+
* [PgCat pooler](/docs/product/pgcat/) to load balance thousands of concurrenct client requests across several database instances
11+
* A web application to manage deployed models and share experiments analysis with SQL notebooks
1212

13-
<figure class="m-3"><img src="../../.gitbook/assets/architecture.png" alt="PostgresML architecture"><figcaption></figcaption></figure>
13+
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).
14+
15+
<figure class="my-4"><img src="../../.gitbook/assets/architecture.png" alt="PostgresML architecture"><figcaption></figcaption></figure>
1416

1517
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.
1618

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.

0 commit comments

Comments
 (0)