@gsa-tts/graymatter-ui 1.0.4 → 1.1.0

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.
Files changed (4) hide show
  1. package/package.json +3 -3
  2. package/src/content/api/endpoints.mdx +1 -8
  3. package/src/content/api/getting-started.mdx +29 -20
  4. package/src/content/api/support.mdx +1 -1
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@gsa-tts/graymatter-ui",
3
- "version": "1.0.4",
3
+ "version": "1.1.0",
4
4
  "type": "module",
5
5
  "publishConfig": {
6
6
  "access": "public"
@@ -61,9 +61,9 @@
61
61
  "typescript": "5.7.3",
62
62
  "vite": "^7.3.2",
63
63
  "vitest": "^3.2.4",
64
- "@gsa-tts/graymatter-vitest-config": "0.0.2",
64
+ "@gsa-tts/graymatter-eslint": "0.0.2",
65
65
  "@gsa-tts/graymatter-typescript-config": "0.0.3",
66
- "@gsa-tts/graymatter-eslint": "0.0.2"
66
+ "@gsa-tts/graymatter-vitest-config": "0.0.2"
67
67
  },
68
68
  "dependencies": {
69
69
  "@fontsource/archivo": "^5.2.8",
package/src/content/api/endpoints.mdx CHANGED
@@ -58,14 +58,7 @@ To reach chat completions the documented endpoint is `<base url>/api/v1/chat/com
58
58
  * **model**: The model ID (e.g: gemini-2.0-flash, claude_3_haiku)
59
59
  * **messages**: An array of of message items consisting of User message, Image Content, Document Content, Assistant Message
60
60
  * **max_tokens**: Maximum response length (optional)
61
- * **temperature**: Response creativity (0.0-2.0, optional)
62
-
63
- | **Models** | **Range** | **Default value** |
64
- | :------- | :------: | -------: |
65
- | Google models | 0.0 - 2.0 | 1.0 |
66
- | Anthropic models | 0.0 - 1.0 | 0.5 |
67
- | Meta models | 0.0 - 1.0 | 0.5 |
68
-
61
+ * **temperature**: Response creativity (0.0-1.0, optional)
69
62
  * **top_p**: An alternative to sampling with temperature, called nucleus sampling (optional)
70
63
  * **stream**: a boolean indicating whether to send partials responses as available (optional)
71
64
 
package/src/content/api/getting-started.mdx CHANGED
@@ -14,25 +14,29 @@ Our API has resource-oriented URLs, accepts JSON request bodies, returns JSON re
14
14
 
15
15
  USAi API is organized around [REST](http://en.wikipedia.org/wiki/Representational_State_Transfer) and provides access to the large language models (LLMs):
16
16
 
17
- **Google AI models**
18
- - [Gemini 2.5 Flash](https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash)
19
- - [Gemini 2.5 Pro](https://ai.google.dev/gemini-api/docs/models#gemini-2.5-pro)
20
-
21
- **Anthropic models**
22
- - [Claude Haiku 3.5](https://docs.claude.com/en/docs/overview)
23
- - [Claude Sonnet 4.5](https://docs.claude.com/en/docs/overview)
24
- - [Claude Opus 4.5](https://docs.claude.com/en/docs/overview)
25
-
26
- **Meta models**
27
- - [Llama 3.2 11B](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_2/)
28
- - [Llama 4 Maverick](https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/)
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)
17
+ **[Google AI models](https://ai.google.dev/gemini-api/docs/)**
18
+ - Gemini 2.5 Flash
19
+ - Gemini 2.5 Pro
20
+
21
+ **[Anthropic models](https://docs.claude.com/en/docs/overview)**
22
+ - Claude Haiku 3.5
23
+ - Claude Haiku 4.5
24
+ - Claude Sonnet 4.5
25
+ - Claude Sonnet 4.6
26
+ - Claude Opus 4.5
27
+ - Claude Opus 4.7
28
+ - Claude Opus 4.8
29
+
30
+ **[Meta models](https://www.llama.com/docs/model-cards-and-prompt-formats/)**
31
+ - Llama 4 Maverick
32
+
33
+ **[OpenAI models](https://developers.openai.com/api/docs/models/)**
34
+ - GPT 5.2
35
+ - GPT 5.4
36
+ - GPT 5.5
37
+
38
+ **[xAI models](https://docs.x.ai/developers/models/)**
39
+ - Grok 4
36
40
 
37
41
  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.
38
42
 
@@ -54,7 +58,12 @@ All API requests require an API key. Upon authentication, your agency-specific i
54
58
 
55
59
  #### Rate limitations
56
60
 
57
- We currently have a rate limit of 3 calls / second / API key. If you hit a rate limit, you should expect a 429 error code. If you need additional capacity, please contact us at [support@usai.gov](mailto:support@usai.gov). We can work with our infrastructure providers to secure higher model limits.
61
+ We currently have the following rate limits:
62
+ - Models – 3 calls / second / API key
63
+ - Chat completions – 3 calls / second / API key
64
+ - Embeddings – 100 calls / second / API key
65
+
66
+ If you hit a rate limit, you should expect a 429 error code. If you need additional capacity, please contact us at [partnerships@usai.gov](mailto:partnerships@usai.gov). We can work with our infrastructure providers to secure higher model limits.
58
67
 
59
68
  #### Feature limitations
60
69
 
package/src/content/api/support.mdx CHANGED
@@ -4,7 +4,7 @@ description: ''
4
4
  sortOrder: 30
5
5
  ---
6
6
 
7
- You may encounter issues while working with the USAi API, as it is under active development. We may not be able to fix all issues immediately, but will add them to our backlog for future releases. If you have any questions, hit rate limits, or otherwise need assistance, please contact us at [support@usai.gov](mailto:support@usai.gov).
7
+ If you have any questions, hit rate limits, or otherwise need assistance, please contact us at [support@usai.gov](mailto:support@usai.gov).
8
8
 
9
9
 
10
10