Merge pull request #6658 from EnterpriseDB/release-2025-03-31a

Release 2025-03-31a

Author: djw-m

advocacy_docs/edb-postgres-ai/ai-accelerator/capabilities.mdx

@@ -20,27 +20,27 @@ The storage locations can be used by AI Accelerator to create a volume. This vol
 
 ### Create a preparer (optional)
 
-This step is optional and only needed for pre-processing source AI data.
+This step is optional and needed only for preprocessing source AI data.
 
-A preparer is created with the Pipelines system. A preparer is a function that retrieves data from a table or volume and returns it in a format that can be used by the model.
+Create a preparer with the Pipelines system. A preparer is a function that retrieves data from a table or volume and returns it in a format that can be used by the model.
 
-With any configuration, a Preparer requires:
+With any configuration, a preparer requires:
 
-* a name
-* the data preparation operation
-* the name of the destination table where the output data will be stored
-* the name of the column in the destination table where the output data will be stored
+* A name
+* The data preparation operation
+* The name of the destination table where the output data will be stored
+* The name of the column in the destination table where the output data will be stored
 
 If the preparer is for a table, it also needs:
 
-* the name of the source table
-* the name of the column in the source table that contains the data
+* The name of the source table
+* The name of the column in the source table that contains the data
 
-If, on the other hand, the preparer is for a volume, it needs:
+But if the preparer is for a volume, it needs:
 
-* the name of the volume
+* The name of the volume
 
-When a preparer is created, by default it assumes column identifiers of "id" for the source and destination but this can be customized.
+When a preparer is created, by default it assumes column identifiers of "id" for the source and destination, but this can be customized.
 
 ### Create a model
 

advocacy_docs/edb-postgres-ai/ai-accelerator/gettingstarted/index.mdx

@@ -59,12 +59,12 @@ INSERT 0 9
 The result is a table with some data in it: food products and some very personal opinions about them.
 
 !!! Note
-This example uses simple, processed data. Pipelines can also handle multiple pre-processing steps via [Preparers](../preparers).
+This example uses simple, processed data. Pipelines can also handle multiple preprocessing steps via [preparers](../preparers).
 !!!
 
 ## Creating a retriever
 
-The core of Pipelines is the Retriever. A retriever is a way to access the data in the table and use it in AI workflows.
+The core of Pipelines is the *retriever*. A retriever is a way to access the data in the table and use it in AI workflows.
 
 ```sql
 select aidb.create_retriever_for_table('products_retriever', 't5', 'products', 'description', 'Text');
@@ -196,6 +196,6 @@ __OUTPUT__
 
 In [Models](../models), you can learn how to create more models with Pipelines, including external models from OpenAI API-compatible services.
 
-In [Preparers](../preparers), you can learn more about how to create Preparers in order to perform pre-processing steps on your data before embeddings are calculated.
+In [Preparers](../preparers), you can learn more about how to create preparers to perform preprocessing steps on your data before embeddings are calculated.
 
 In [Retrievers](../retrievers), you can learn more about how to use retrievers with external data sources, local files, or S3 storage and how to use the retriever functions to get the data you need.

advocacy_docs/edb-postgres-ai/ai-accelerator/limitations.mdx

@@ -33,13 +33,13 @@ There's currently no load balancing mechanism for model access.
 
 Retriever Pipelines currently supports only text and image formats. Other formats, including structured data, video, and audio, aren't currently supported.
 
-### Auto-Embedding for Images
+### Auto-embedding for images
 
-* Auto-Embedding is only supported for text data. Image data embeddings can be manually computed.
+* Auto-embedding is supported only for text data. Image data embeddings can be manually computed.
 
-### Auto-Data Preparation
+### Auto-data preparation
 
-* Auto-Data Preparation is not currently supported. Bulk data preparation can be executed manually.
+* Auto-data preparation isn't currently supported. Bulk data preparation can be executed manually.
 
 ## Upgrading
 

advocacy_docs/edb-postgres-ai/ai-accelerator/models/index.mdx

@@ -17,6 +17,6 @@ Pipelines has a model registry that manages configured instances of models. Any
 * See the [supported models](./supported-models) that come with Pipelines.
 * Using [models with OpenAI API-compatible services and Nvidia NIM](using-with) with Pipelines.
 
-## Next Steps
+## Next steps
 
 Once you are familiar with models, you can learn how to use those models with [retrievers](../retrievers).

advocacy_docs/edb-postgres-ai/ai-accelerator/models/supported-models/completions.mdx

@@ -13,9 +13,7 @@ Model aliases:
 
 ## About completions
 
-Completions enables the use of any OpenAI API-compatible text-generation model.
-
-It's suitable for chat/text transforms, text completion, and other text generation tasks.
+Completions enables the use of any OpenAI API-compatible text-generation model. It's suitable for chat/text transforms, text completion, and other text generation tasks.
 
 Based on the name of the model, the model provider sets defaults accordingly:
 
@@ -99,7 +97,7 @@ The following configuration settings are available for OpenAI models:
 
 ## Model credentials
 
-The following credentials may be required by the service providing these models. Note: `api_key` and `basic_auth` are exclusive. Only one of these two options can be used.
+The following credentials may be required by the service providing these models. Note: `api_key` and `basic_auth` are exclusive. You can use only one of these two options.
 
-* `api_key` &mdash; The API key to use for Bearer Token authentication. The api_key will be sent in a header field as `Authorization: Bearer <api_key>`.
-* `basic_auth` &mdash; credentials for HTTP Basic authentication. The credentials provided here will be sent verbatim as `Authorization: Basic <basic_auth>`. If your server requires username/password with HTTP Basic authentication, use the syntax `username:password`. If only a token is required, only provide the token.
+* `api_key` &mdash; The API key to use for Bearer Token authentication. The api_key is sent in a header field as `Authorization: Bearer <api_key>`.
+* `basic_auth` &mdash; Credentials for HTTP Basic authentication. The credentials provided here are sent verbatim as `Authorization: Basic <basic_auth>`. If your server requires username/password with HTTP Basic authentication, use the syntax `username:password`. If only a token is required, provide only the token.

advocacy_docs/edb-postgres-ai/ai-accelerator/models/using-models.mdx

@@ -8,7 +8,7 @@ Pipelines has a model registry that manages configured instances of models. Any
 
 ## Discover the preloaded models
 
-Pipelines comes with a set of pre-configured models that you can use out of the box.
+Pipelines comes with a set of preconfigured models that you can use out of the box.
 
 To find them, run the following query:
 
@@ -27,13 +27,13 @@ This query returns a list of all the models that are currently created in the sy
  dummy                 | dummy             | {"config={}"}
 ```
 
-The `bert`, `clip`, and `t5` models are all pre-configured and ready to use. The `dummy` model is a placeholder model that can be used for testing purposes.
+The `bert`, `clip`, and `t5` models are all preconfigured and ready to use. The `dummy` model is a placeholder model that can be used for testing purposes.
 
 !!! note First use of local models
-The first time you use any of the local models, the model will be downloaded from [HuggingFace](https://huggingface.co/).  The model is then run locally.
+The first time you use any of the local models, the model will be downloaded from [HuggingFace](https://huggingface.co/). The model is then run locally.
 Subsequent uses of the model will be faster, as the model will be cached locally.
 
-If you use a proxy, ensure that it is [configured on the Postgres server](../installing/complete#proxy-settings).
+If you use a proxy, ensure that it's [configured on the Postgres server](../installing/complete#proxy-settings).
 
 !!!
 
@@ -101,7 +101,7 @@ SELECT aidb.create_model(
   );
 ```
 
-Replace the `api_key` value with your own OpenAI API key (Read more about credential handling under [supported models](./supported-models)). Then you can use the `my_openai_model` model in your Pipelines functions and, in this example, leverage the GPT-4o model from OpenAI.
+Replace the `api_key` value with your own OpenAI API key. (For more information about credential handling, see [supported models](./supported-models).) Then you can use the `my_openai_model` model in your Pipelines functions and, in this example, leverage the GPT-4o model from OpenAI.
 
 Creating the OpenAI embeddings model is similar to creating the completions model:
 

advocacy_docs/edb-postgres-ai/ai-accelerator/models/using-with/index.mdx

@@ -4,8 +4,8 @@ navTitle: Using models with...
 description: How to use OpenAI-compatible and Nvidia NIM models with AI Accelerator Pipelines.
 ---
 
-In this section we look at some particular ways to use models with AI Accelerator Pipelines.
-These techniques show how to use API compatible services, running locally or in the cloud, with Pipelines and how to make use of Nvidia NIM models.
+This section describes some particular ways to use models with AI Accelerator Pipelines.
+These techniques show how to use API-compatible services, running locally or in the cloud, with Pipelines and how to make use of Nvidia NIM models.
 
 * [OpenAI API-compatible services](openai-api-compatibility) with Pipelines.
 * [Nvidia NIM models](using-nvidia-nim) with Pipelines.

advocacy_docs/edb-postgres-ai/ai-accelerator/models/using-with/openai-api-compatibility.mdx

@@ -37,7 +37,7 @@ Specify the model provider as `embeddings`, which is the provider that defaults
 
 ### Configuration
 
-The next parameter is the configuration. This is a JSON string. When expanded, it has two parameters: the model, and the url.
+The next parameter is the configuration. This is a JSON string. When expanded, it has two parameters: the model and the url.
 
 ```json
 '{"model":"llama3.2", "url":"http://llama.local:11434/v1/embeddings"}'::JSONB

advocacy_docs/edb-postgres-ai/ai-accelerator/models/using-with/using-nvidia-nim/index.mdx

@@ -4,9 +4,9 @@ navTitle: Nvidia NIM models
 description: How to use Nvidia NIM models, either in your own environment or in the Nvidia cloud, with AI Accelerator Pipelines.
 ---
 
-You can use Nvidia NIM models with AI Accelerator. The models can be run in the Nvidia cloud or run within your environment under your control.
+You can use Nvidia NIM models with AI Accelerator. The models can run in the Nvidia cloud or in your environment under your control.
 
-This guide shows you how to use Nvidia NIM models with AI Accelerator in both scenarios.
+You can learn how to use Nvidia NIM models with AI Accelerator in both scenarios:
 
 * [In the Nvidia cloud](using-nim-in-nvidia-cloud)
 * [In your environment](using-nim-in-your-environment)

advocacy_docs/edb-postgres-ai/ai-accelerator/models/using-with/using-nvidia-nim/using-nim-in-nvidia-cloud.mdx

@@ -5,37 +5,37 @@ description: Learn how to use Nvidia NIM models in the Nvidia cloud, hosted by N
 ---
 
 
-To use a Nvidia NIM that is hosted Nvidia's cloud, you first need a select a model to use. For this tutorial, we will be using the Nvidia NIM model llama-3.3-70b-instruct.
+To use a Nvidia NIM that's hosted in Nvidia's cloud, you first need to select a model to use. This tutorial uses the Nvidia NIM model llama-3.3-70b-instruct.
 
 ## Prerequisites
 
-* An Nvidia NGC account. (If you don't have one, you can create one [here](https://build.nvidia.com/explore/discover/))
+* An Nvidia NGC account. (If you don't have one, you can create one [here](https://build.nvidia.com/explore/discover/).)
 
 ## Configuring the Nvidia cloud
 
-### 1. Select a Model
+### 1. Select a model
 
-Choose a model from [Nvidia's model library](https://build.nvidia.com/models). For this example, we will used the [llama-3.3-70b-instruct](https://build.nvidia.com/meta/llama3-70b) model.
+Choose a model from [Nvidia's model library](https://build.nvidia.com/models). This example uses the [llama-3.3-70b-instruct](https://build.nvidia.com/meta/llama3-70b) model.
 
 ### 2. Generate an API Key
 
-API keys can be created from the model’s page.
+You can create API keys from the model’s page.
 
 ![Get API Key](images/get-api-key.svg)
 
-Click on the `Get API Key` button to generate an API key. If you have not logged in, you will be prompted to log in and if you have not signed up, you will be invited to do so. You will recieve an API key that you can use to interact with the model. We will refer to this key as the `<NIM API KEY>` in the following steps.
+To generate an API key, select **Get API Key**. If you haven't logged in, you're prompted to log in. If you haven't signed up, you're invited to do so. You'll receive an API key that you can use to interact with the model. This example refers to this key as the `<NIM API KEY>`.
 
-## Integrating the Model with AI Accelerator
+## Integrating the model with AI Accelerator
 
 ### 1. Enable AI Accelerator in EDB Postgres AI
 
-With an EDB Postgres Advanced Server, EDB Postgres Extended Server, or a Community Postgres instance running, connect to the database and enable the AI Accelerator extension:
+With EDB Postgres Advanced Server, EDB Postgres Extended Server, or a community Postgres instance running, connect to the database and enable the AI Accelerator extension:
 
 ```sql
 CREATE EXTENSION aidb CASCADE;
 ```
 
-### 2. Register the Model
+### 2. Register the model
 
 ```sql
 SELECT aidb.create_model( \
@@ -46,9 +46,9 @@ SELECT aidb.create_model( \
 );
 ```
 
-### 3. Run the Model
+### 3. Run the model
 
-Execute the following query to interact with the model:
+To interact with the model, execute the following query:
 
 ```sql
 SELECT aidb.decode_text('my_nim_llm', 'Tell me a short, one sentence story');
@@ -58,4 +58,4 @@ __OUTPUT__
      As the clock struck midnight, a single tear fell from the porcelain doll's glassy eye.
 ```
 
-Your output may vary. You have successfully used Nvidia NIM models, running on Nvidia's cloud, integrated with AI Accelerator.
+Your output may vary. You've successfully used Nvidia NIM models, running on Nvidia's cloud, integrated with AI Accelerator.

advocacy_docs/edb-postgres-ai/ai-accelerator/models/using-with/using-nvidia-nim/using-nim-in-your-environment.mdx

@@ -4,12 +4,12 @@ navTitle: In your environment
 description: Learn how to use Nvidia NIM models in your environment, locally or in your private cloud.
 ---
 
-To use a Nvidia NIM that is hosted in your own environment, you first need a instance of the model. For this tutorial, we will show how to configure an AWS hosted instance with the Nvidia NIM model. We will use the Nvidia NIM model llama3-8b-instruct.
+To use a Nvidia NIM that's hosted in your own environment, you first need an instance of the model. This tutorial shows how to configure an AWS-hosted instance with the Nvidia NIM model. It uses the Nvidia NIM model llama3-8b-instruct.
 
 ## Prerequisites
 
-* A system capable of running Nvidia CUDA Toolkit. We suggest, for this tutorial, using an **EC2 g5.8xlarge instance** with **1024 GB of gp3 storage** running **Ubuntu 24.04 LTS**, although smaller instance sizes may also work.
-* An Nvidia NGC account. (If you don't have one, you can create one [here](https://build.nvidia.com/explore/discover/))
+* A system capable of running Nvidia CUDA Toolkit. For this tutorial, we recommend using an **EC2 g5.8xlarge instance** with **1024 GB of gp3 storage** running **Ubuntu 24.04 LTS**, although smaller instance sizes may also work.
+* A Nvidia NGC account. (If you don't have one, you can create one [here](https://build.nvidia.com/explore/discover/).)
 
 ## Configuring the system
 
@@ -19,15 +19,16 @@ Download and install the CUDA Toolkit from [Nvidia's official page](https://deve
 
 ### 2. Install Docker
 
-If your system does not have Docker installed, download and install docker.
-Instructions for Ubuntu are [here](https://docs.docker.com/engine/install/ubuntu/).
-Instructions for [other Linux platforms are available](https://docs.docker.com/engine/install/) too.
+If your system doesn't have Docker installed, download and install it:
+
+-  Instructions for Ubuntu are [here](https://docs.docker.com/engine/install/ubuntu/).
+-  Instructions for other Linux platforms are [here](https://docs.docker.com/engine/install/).
 
 ### 3. Generate an NGC API Key
 
-Obtain an API key from [Nvidia NGC](https://org.ngc.nvidia.com/setup/api-key). This key will be referred to as the NGC API KEY in the following steps.
+Obtain an API key from [Nvidia NGC](https://org.ngc.nvidia.com/setup/api-key). This example refers to this key as `<NGC API KEY>`.
 
-Login to the NGC container registry:
+Log in to the NGC container registry:
 
 ```shell
 docker login nvcr.io
@@ -44,7 +45,7 @@ Download and install the Nvidia NGC CLI from [here](https://org.ngc.nvidia.com/s
 
 ### 5. Run the NIM Model
 
-Save the following script as a shell script and execute it (more information can be found from [Nvidia's documentation](https://docs.nvidia.com/nim/large-language-models/latest/getting-started.html#serving-models-from-local-assets)). Remember to substitute the `<NGC API KEY>` with the API key you generated:
+Save the following script as a shell script and execute it. (For more information, see [Nvidia's documentation](https://docs.nvidia.com/nim/large-language-models/latest/getting-started.html#serving-models-from-local-assets).) Remember to substitute `<NGC API KEY>` with the API key you generated.
 
 ```shell
 # Choose a container name
@@ -68,9 +69,9 @@ docker run -it --rm --name=$CONTAINER_NAME \
 $IMG_NAME 
 ```
 
-### 6. Test the Deployment
+### 6. Test the deployment
 
-Run the following command to verify the model is working:
+To verify the model is working, run the following command:
 
 ```shell
 curl -X POST "http://0.0.0.0:8000/v1/chat/completions" \
@@ -87,21 +88,21 @@ curl -X POST "http://0.0.0.0:8000/v1/chat/completions" \
     }'
 ```
 
-Once you have verified the model is working, you can use it with EDB Postgres AI Accelerator.
+Once you've verified the model is working, you can use it with EDB Postgres AI Accelerator.
 
-Make a note of the public IP address of the EC2 instance, as you will need it to connect to the model from EDB Postgres AI Accelerator. This will be referred to as `<NIM_HOST>` in the following steps.
+Record the public IP address of the EC2 instance, as you'll need it to connect to the model from EDB Postgres AI Accelerator. This example refers to this address as `<NIM_HOST>`.
 
-## Integrating the Model with AI Accelerator
+## Integrating the model with AI Accelerator
 
 ### 1. Enable AI Accelerator in EDB Postgres AI
 
-With an EDB Postgres Advanced Server, EDB Postgres Extended Server, or a Community Postgres instance running, connect to the database and enable the AI Accelerator extension by running the following SQL commands:
+With EDB Postgres Advanced Server, EDB Postgres Extended Server, or a community Postgres instance running, connect to the database. Then enable the AI Accelerator extension by running the following SQL commands:
 
 ```sql
 CREATE EXTENSION aidb CASCADE;
 ```
 
-### 2. Register the Model
+### 2. Register the model
 
 ```sql
 SELECT aidb.create_model(
@@ -111,9 +112,9 @@ SELECT aidb.create_model(
 );
 ```
 
-### 3. Run the Model
+### 3. Run the model
 
-Execute the following query to interact with the model:
+To interact with the model, execute the following query:
 
 ```sql
 SELECT aidb.decode_text('my_nim_llm', 'Tell me a short, one sentence story');
@@ -123,4 +124,4 @@ __OUTPUT__
      As the clock struck midnight, a single tear fell from the porcelain doll's glassy eye.
 ```
 
-Your output may vary. You have successfully used Nvidia NIM models via EDB’s AI Accelerator.
+Your output may vary. You've successfully used Nvidia NIM models via the EDB AI Accelerator.