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: docs/en_US/ai_tools.rst
+11-4Lines changed: 11 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -48,15 +48,18 @@ button and select *AI*).
48
48
Select your preferred LLM provider from the dropdown:
49
49
50
50
**Anthropic**
51
-
Use Claude models from Anthropic. Requires an Anthropic API key.
51
+
Use Claude models from Anthropic, or any Anthropic-compatible API provider.
52
52
53
-
* **API Key File**: Path to a file containing your Anthropic API key (obtain from https://console.anthropic.com/).
53
+
* **API URL**: Custom API endpoint URL (leave empty for default: https://api.anthropic.com/v1).
54
+
* **API Key File**: Path to a file containing your Anthropic API key (obtain from https://console.anthropic.com/). This path refers to the filesystem where the pgAdmin server is running (e.g., inside the container if using Docker). The ``~`` prefix is expanded to the home directory of the user running the pgAdmin server process. Optional when using a custom URL with a provider that does not require authentication.
54
55
* **Model**: Select from available Claude models (e.g., claude-sonnet-4-20250514).
55
56
56
57
**OpenAI**
57
-
Use GPT models from OpenAI. Requires an OpenAI API key.
58
+
Use GPT models from OpenAI, or any OpenAI-compatible API provider (e.g.,
59
+
LiteLLM, LM Studio, EXO, or other local inference servers).
58
60
59
-
* **API Key File**: Path to a file containing your OpenAI API key (obtain from https://platform.openai.com/).
61
+
* **API URL**: Custom API endpoint URL (leave empty for default: https://api.openai.com/v1). Include the ``/v1`` path prefix if required by your provider.
62
+
* **API Key File**: Path to a file containing your OpenAI API key (obtain from https://platform.openai.com/). This path refers to the filesystem where the pgAdmin server is running (e.g., inside the container if using Docker). The ``~`` prefix is expanded to the home directory of the user running the pgAdmin server process. Optional when using a custom URL with a provider that does not require authentication.
60
63
* **Model**: Select from available GPT models (e.g., gpt-4).
61
64
62
65
**Ollama**
@@ -72,6 +75,10 @@ Select your preferred LLM provider from the dropdown:
72
75
* **API URL**: The URL of the Docker Model Runner API (default: http://localhost:12434).
73
76
* **Model**: Select from available models or enter a custom model name.
74
77
78
+
.. note:: You can also use the *OpenAI* provider with a custom API URL for any
79
+
OpenAI-compatible endpoint, including Docker Model Runner and other local
80
+
inference servers.
81
+
75
82
After configuring your provider, click *Save* to apply the changes.
|`Issue #4011 <https://github.com/pgadmin-org/pgadmin4/issues/4011>`_ - Added support to download binary data from result grid.
24
+
|`Issue #9703 <https://github.com/pgadmin-org/pgadmin4/issues/9703>`_ - Added support for custom LLM provider URLs for OpenAI and Anthropic, allowing use of OpenAI-compatible providers such as LM Studio, EXO, and LiteLLM.
25
+
|`Issue #9709 <https://github.com/pgadmin-org/pgadmin4/issues/9709>`_ - Fixed an issue where AI features (AI Assistant tab, AI Reports menus, and AI Preferences) were visible in the UI even when LLM_ENABLED is set to False.
26
+
|`Issue #9738 <https://github.com/pgadmin-org/pgadmin4/issues/9738>`_ - Allow copying of text from the AI Assistant chat panel.
23
27
24
28
Housekeeping
25
29
************
26
30
27
31
Bug fixes
28
32
*********
29
33
34
+
|`Issue #8992 <https://github.com/pgadmin-org/pgadmin4/issues/8992>`_ - Fixed an issue where selecting all in the Query Tool's Messages tab would select the entire page content.
35
+
|`Issue #9279 <https://github.com/pgadmin-org/pgadmin4/issues/9279>`_ - Fixed an issue where OAuth2 authentication fails with 'object has no attribute' if OAUTH2_AUTO_CREATE_USER is False.
36
+
|`Issue #9392 <https://github.com/pgadmin-org/pgadmin4/issues/9392>`_ - Ensure that the Geometry Viewer refreshes when re-running queries or switching geometry columns, preventing stale data from being displayed.
37
+
|`Issue #9457 <https://github.com/pgadmin-org/pgadmin4/issues/9457>`_ - Fixed Process Watcher garbled text on Windows with non-UTF-8 locales.
38
+
|`Issue #9570 <https://github.com/pgadmin-org/pgadmin4/issues/9570>`_ - Fixed an issue where ALT+F5 for executing a query in the Query Tool shows a crosshair cursor icon for rectangular selection.
39
+
|`Issue #9648 <https://github.com/pgadmin-org/pgadmin4/issues/9648>`_ - Fixed an issue where the default fillfactor value for B-tree indexes was incorrect.
40
+
|`Issue #9694 <https://github.com/pgadmin-org/pgadmin4/issues/9694>`_ - Fixed an issue where AI Reports are grayed out after setting an API key by auto-selecting the default provider.
41
+
|`Issue #9696 <https://github.com/pgadmin-org/pgadmin4/issues/9696>`_ - Fixed an issue where AI Assistant does not notify that No API Key or Provider is Set.
42
+
|`Issue #9702 <https://github.com/pgadmin-org/pgadmin4/issues/9702>`_ - Fixed misleading AI activity messages that could be mistaken for actual database operations.
43
+
|`Issue #9719 <https://github.com/pgadmin-org/pgadmin4/issues/9719>`_ - Fixed an issue where AI Reports fail with OpenAI models that do not support the temperature parameter.
44
+
|`Issue #9721 <https://github.com/pgadmin-org/pgadmin4/issues/9721>`_ - Fixed an issue where permissions page is not completely accessible on full scroll.
45
+
|`Issue #9729 <https://github.com/pgadmin-org/pgadmin4/issues/9729>`_ - Fixed an issue where some LLM models would not use database tools in the AI assistant, instead returning text descriptions of tool calls.
46
+
|`Issue #9732 <https://github.com/pgadmin-org/pgadmin4/issues/9732>`_ - Improve the AI Assistant user prompt to be more descriptive of the actual functionality.
47
+
|`Issue #9734 <https://github.com/pgadmin-org/pgadmin4/issues/9734>`_ - Fixed an issue where LLM responses are not streamed or rendered properly in the AI Assistant.
48
+
|`Issue #9736 <https://github.com/pgadmin-org/pgadmin4/issues/9736>`_ - Fix an issue where the AI Assistant was not retaining conversation context between messages, with chat history compaction to manage token budgets.
49
+
|`Issue #9740 <https://github.com/pgadmin-org/pgadmin4/issues/9740>`_ - Fixed an issue where the AI Assistant input textbox sometimes swallows the first character of input.
50
+
|`Issue #9758 <https://github.com/pgadmin-org/pgadmin4/issues/9758>`_ - Clarify where the LLM API key files should be.
51
+
|`Issue #9789 <https://github.com/pgadmin-org/pgadmin4/issues/9789>`_ - Fixed an issue where the Query tool kept prompting for a password when using a shared server.
52
+
|`Issue #9795 <https://github.com/pgadmin-org/pgadmin4/issues/9795>`_ - Support /v1/responses for OpenAI models.
Copy file name to clipboardExpand all lines: pkg/helm/Chart.yaml
+2-2Lines changed: 2 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
apiVersion: v2
2
2
name: pgadmin4-helm
3
-
version: 9.13.0
4
-
appVersion: 9.13.0
3
+
version: 9.14.0
4
+
appVersion: 9.14.0
5
5
description: pgAdmin is the most popular and feature rich Open Source administration and development platform for PostgreSQL, the most advanced Open Source database in the world.
0 commit comments