Merge pull request #6541 from EnterpriseDB/release/2025-02-24a

Release: 2025-02-24a

Author: gvasquezvargas

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

@@ -22,8 +22,7 @@ The starting point for this process is creating a model. When you create a model
 select aidb.create_model(
 'my_local_ollama',
 'embeddings',
-'{"model":"llama3.1", "url":"http://llama.local:11434/v1/embeddings", "dimensions":2000}'::JSONB,
-'{"api_key":""}'::JSONB);
+'{"model":"llama3.1", "url":"http://llama.local:11434/v1/embeddings", "dimensions":2000}'::JSONB);
 ```
 
 ### Model name and model provider
@@ -42,21 +41,19 @@ The next parameter is the configuration. This is a JSON string, which when expan
 
 In this case, we are setting the model to [“llama3.3”](https://ollama.com/library/llama3.3), a relatively new and powerful model. Remember to run `ollama run llama3.3` to pull and start the model on the server.
 
-The next json setting is the important one, overriding the endpoint that the aidb model will use. 
+The next json setting is the important one, overriding the endpoint that the aidb model will use.
 
 * Our server is running on a machine called `llama.local`.
 * It has port 11434 (the default port for Ollama) open to service requests over HTTP (not HTTPS in this case).
 * The path to the endpoint on the server `/v1/embeddings`; the same as OpenAI.
 
-Putting those components together we get `[`http://llama.local:11434/v1/embeddings`](http://art.local:11434/v1/embeddings","api_key":"","dimensions":2000}'::JSONB)` as our end point.
+Putting those components together we get `http://llama.local:11434/v1/embeddings` as our end point.
 
 The last JSON parameter in this example is “dimensions” which is a hint to the system about how many vector values to expect from the model. If we [look up llama3.3’s properties](https://ollama.com/library/llama3.3/blobs/4824460d29f2) we can see the `llama.embedding_length` value is 8192. The provider defaults to 1536 (with some hard-wired exceptions depending on model) but it doesn’t know about llama3.3's max. Another factor is [pgvector is limited to 2000 dimensions](https://github.com/pgvector/pgvector?tab=readme-ov-file#what-if-i-want-to-index-vectors-with-more-than-2000-dimensions). So we pass a  dimension value of 2000 in the configuration, to get the maximum dimensions available with pgvector.
 
 That completes the configuration parameter.
 
-### Credentials
-
-The last parameter is the credentials parameter, which is another JSON string. It’s usually used for carrying the `api_key` for the OpenAI service and any other necessary credential information. It is not part of the configuration and by being separate, it can be securely hidden from users with lesser permissions. For our ollama connection, we don’t need an `api_key`, but the model provider currently requires that one is specified. We can specify an empty string for the `api_key` to satisfy this requirement.
+If the endpoint requires an API key, that would be passed in the credentials parameter. As this is a local model, we don’t need to pass any credentials.
 
 ## Using the model
 

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

@@ -99,6 +99,7 @@ The following configuration settings are available for OpenAI models:
 
 ## Model credentials
 
-The following credentials are required for these models:
+The following credentials may be required by the service providing these models:
 
 * `api_key` - The API key to use for authentication.
+

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

@@ -76,6 +76,6 @@ The following configuration settings are available for OpenAI models:
 
 ## Model credentials
 
-The following credentials are required for OpenAI models:
+The following credentials may be required by the service providing these models:
 
 * `api_key` - The OpenAI API key to use for authentication.

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

@@ -46,20 +46,20 @@ You can also find out what model providers are available by running the followin
 ```sql
 SELECT * FROM aidb.model_providers;
 __OUTPUT__
-    server_name     | server_options
---------------------+----------------
- t5_local           |
- embeddings         |
- completions        |
- openai_embeddings  |
- openai_completions |
- nim_completions    |
- nim_embeddings     |
- nim_clip           |
- nim_reranking      |
- bert_local         |
- clip_local         |
- dummy              |
+    server_name     |                                          server_description                                          | server_options 
+--------------------+------------------------------------------------------------------------------------------------------+----------------
+ t5_local           | A simple language model, ideal for translation, summarization, and question answering. Runs locally. | 
+ embeddings         | For any model that implements the OpenAI embeddings API.                                             | 
+ completions        | For any model that implements the OpenAI completions API.                                            | 
+ openai_embeddings  | For any embeddings model on the OpenAI platform                                                      | 
+ openai_completions | For any completions model on the OpenAI platform.                                                    | 
+ nim_completions    | For any model that implements the OpenAI completions API on NVIDIA NIM.                              | 
+ nim_embeddings     | For any model that implements the OpenAI embeddings API on NVIDIA NIM.                               | 
+ nim_clip           | Vision/text model, ideal for encoding text and images, runs on NVIDIA NIM.                           | 
+ nim_reranking      | Reranking model, runs on NVIDIA NIM.                                                                 | 
+ bert_local         | Simple language model, ideal for encoding text, runs locally.                                        | 
+ clip_local         | A vision/text model, ideal for encoding text and images, runs locally.                               | 
+ dummy              | Provides fake data, ideal for testing.                                                               | 
 (12 rows)
 ```
 

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

@@ -13,10 +13,11 @@ This section provides reference documentation for EDB Postgres AI AI Accelerator
 
 The `aidb.model_providers` table stores information about the model providers that have been created in the database.
 
-| Column         | Type     | Description                   |
-|----------------|----------|-------------------------------|
-| server_name    | name     | Name for the model server.    |
-| server_options | text\[\] | Options for the model server. |
+| Column             | Type     | Description                      |
+|--------------------|----------|----------------------------------|
+| server_name        | name     | Name for the model server.       |
+| server_description | text     | Description of the model server. |
+| server_options     | text\[\] | Options for the model server.    |
 
 
 ## Functions

advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/ai-accelerator_2.1.2_rel_notes.mdx

@@ -0,0 +1,35 @@
+---
+title: AI Accelerator - Pipelines 2.1.2 release notes
+navTitle: Version 2.1.2
+originalFilePath: advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/rel_notes_2.1.2.yml
+editTarget: originalFilePath
+---
+
+Released: 25 February 2025
+
+In this maintenance release, we fix two bugs and improve the model provider listing output.
+
+## Highlights
+
+- Model provider output now contains descriptions of the providers.
+
+## Enhancements
+
+<table class="table w-100"><thead><tr><th>Description</th><th width="10%">Addresses</th></tr></thead><tbody>
+<tr><td><details><summary>Added model provider descriptions</summary><hr/><p>The model provider view <code>select * from aidb.model_providers;</code> now includes a description column detailing the purpose and capabilities of each model provider.</p>
+</details></td><td></td></tr>
+</tbody></table>
+
+
+## Bug Fixes
+
+<table class="table w-100"><thead><tr><th>Description</th><th width="10%">Addresses</th></tr></thead><tbody>
+<tr><td><details><summary>Fixed the volume listing command</summary><hr/><p>The <code>aidb.list_volumes();</code> call is now functional. A bug prevented this call from succeeding (without affecting any other functionality).</p>
+</details></td><td></td></tr>
+<tr><td><details><summary>Fixed the search path handling</summary><hr/><p>Some internal commands used to append <code>aidb</code> to the search_path. This failed in certain cases depending on the contents of the existing search path. We changed the implementation to no longer modify the search_path in order to avoid this issue. This also means that the existing search_path no longer gets modified by AIDB.</p>
+</details></td><td></td></tr>
+<tr><td><details><summary>Credentials are now completely optional for OpenAI compatible models</summary><hr/><p>Previously the <code>aidb.create_model()</code> function required a key with an empty value to be passed for the api-key. It now allows you to omit the <code>credentials</code> parameter.</p>
+</details></td><td></td></tr>
+</tbody></table>
+
+

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

@@ -4,6 +4,7 @@ navTitle: Release notes
 description: Release notes for EDB Postgres AI - AI Accelerator
 indexCards: none
 navigation:
+  - ai-accelerator_2.1.2_rel_notes
   - ai-accelerator_2.1.1_rel_notes
   - ai-accelerator_2.0.0_rel_notes
   - ai-accelerator_1.0.7_rel_notes
@@ -17,6 +18,7 @@ The EDB Postgres AI - AI Accelerator describes the latest version of AI Accelera
 
 | AI Accelerator version | Release Date |
 |---|---|
+| [2.1.2](./ai-accelerator_2.1.2_rel_notes) | 25 Feb 2025 |
 | [2.1.1](./ai-accelerator_2.1.1_rel_notes) | 03 Feb 2025 |
 | [2.0.0](./ai-accelerator_2.0.0_rel_notes) | 13 Jan 2025 |
 | [1.0.7](./ai-accelerator_1.0.7_rel_notes) | 10 Dec 2024 |

advocacy_docs/edb-postgres-ai/ai-accelerator/rel_notes/src/rel_notes_2.1.2.yml

@@ -0,0 +1,40 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/EnterpriseDB/docs/refs/heads/develop/tools/automation/generators/relgen/relnote-schema.json
+product: AI Accelerator - Pipelines
+version: 2.1.2
+date: 25 February 2025
+intro: |
+  In this maintenance release, we fix two bugs and improve the model provider listing output.
+highlights: |
+ - Model provider output now contains descriptions of the providers.
+relnotes:
+- relnote: Added model provider descriptions
+  details: |
+    The model provider view `select * from aidb.model_providers;` now includes a description column detailing the purpose and capabilities of each model provider. 
+  jira: "AID-176"
+  addresses: ""
+  type: Enhancement
+  impact: High
+- relnote: Fixed the volume listing command
+  details: |
+    The `aidb.list_volumes();` call is now functional. A bug prevented this call from succeeding (without affecting any other functionality). 
+  jira: "AID-300"
+  addresses: ""
+  type: Bug Fix
+  impact: High
+- relnote: Fixed the search path handling
+  details: |
+    Some internal commands used to append `aidb` to the search_path. This failed in certain cases depending on the contents of the existing search path. We changed the implementation to no longer modify the search_path in order to avoid this issue. This also means that the existing search_path no longer gets modified by AIDB. 
+  jira: "AID-219"
+  addresses: ""
+  type: Bug Fix
+  impact: High
+- relnote: Credentials are now completely optional for OpenAI compatible models
+  details: |
+    Previously the `aidb.create_model()` function required a key with an empty value to be passed for the api-key. It now allows you to omit the `credentials` parameter.
+  jira: ""
+  addresses: ""
+  type: Bug Fix
+  impact: Low
+
+
+

install_template/templates/products/edb*plus/index.njk

@@ -20,5 +20,5 @@ redirects:
 
 {% block otherosinstall %}
 ## Windows
-- [Windows Server 2019, 2022, and Windows 11](windows)
+- [Windows Server 2022 and Windows 11](windows)
 {% endblock otherosinstall %}

product_docs/docs/edb_plus/41/installing/index.mdx

@@ -66,4 +66,4 @@ Select a link to access the applicable installation instructions:
 
 ## Windows
 
-- [Windows Server 2019, 2022, and Windows 11](windows)
+- [Windows Server 2022 and Windows 11](windows)