@gsa-tts/graymatter-ui 0.6.0 → 0.6.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@gsa-tts/graymatter-ui",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.1",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"publishConfig": {
|
|
6
6
|
"access": "public"
|
|
@@ -61,8 +61,8 @@
|
|
|
61
61
|
"typescript": "5.7.3",
|
|
62
62
|
"vite": "^6.4.1",
|
|
63
63
|
"vitest": "^3.0.7",
|
|
64
|
-
"@gsa-tts/graymatter-eslint": "0.0.2",
|
|
65
64
|
"@gsa-tts/graymatter-typescript-config": "0.0.2",
|
|
65
|
+
"@gsa-tts/graymatter-eslint": "0.0.2",
|
|
66
66
|
"@gsa-tts/graymatter-vitest-config": "0.0.1"
|
|
67
67
|
},
|
|
68
68
|
"dependencies": {
|
|
@@ -27,6 +27,13 @@ USAi API is organized around [REST](http://en.wikipedia.org/wiki/Representationa
|
|
|
27
27
|
- [Llama 3.2 11B](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_2/)
|
|
28
28
|
- [Llama 4 Maverick](https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/)
|
|
29
29
|
|
|
30
|
+
**OpenAI models**
|
|
31
|
+
- [GPT 5.2](https://developers.openai.com/api/docs/models/gpt-5.2)
|
|
32
|
+
- [GPT 5.4](https://developers.openai.com/api/docs/models/gpt-5.4)
|
|
33
|
+
|
|
34
|
+
**xAI models**
|
|
35
|
+
- [Grok 4](https://docs.x.ai/developers/models/grok-4.20)
|
|
36
|
+
|
|
30
37
|
The interface is modeled after the [OpenAI Chat Completion API](https://platform.openai.com/docs/guides/text?api-mode=responses). We will continue to add more models over time; we may also remove models if they are found to not meet our standards. You will be notified if a model is removed.
|
|
31
38
|
|
|
32
39
|
Each model we draw on has unique capabilities. Models may also respond differently to the same API request. Below is a summary of each endpoint’s functionality:
|
|
@@ -58,7 +65,9 @@ Because the underlying platforms have different capabilities and interfaces, not
|
|
|
58
65
|
|
|
59
66
|
#### Guardrail limitations
|
|
60
67
|
|
|
61
|
-
|
|
68
|
+
For OpenAI and xAI models we have Azure's DefaultV2 content filtering enabled, which provides automated harm detection across four categories (Hate, Self-Harm, Sexual, Violence) plus advanced protections against prompt injection, and copyright violations. When the platform detects harmful content it will raise an HTTP 400 error in non-streaming contexts and return an error chunk when streaming.
|
|
69
|
+
|
|
70
|
+
For Google, Anthropic, and Meta models we do not have guardrails beyond those provided by our model providers; this means that an API user has full control over what inputs and outputs are allowed when using the API. We expect API users to interact with the API ethically and deliberately, and add their own guardrails and system prompts as needed. We recommend implementing system prompts when using the API in situations where you do not know what inputs the model will receive.
|
|
62
71
|
|
|
63
72
|
System prompts should address your needs and concerns. Some of the system prompts in USAi Chat include:
|
|
64
73
|
- You are a helpful assistant that works for a government agency.
|