@gsa-tts/graymatter-ui 0.5.0 → 0.5.1
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
|
@@ -26,6 +26,12 @@ curl -X 'GET' \
|
|
|
26
26
|
{
|
|
27
27
|
"object": "list",
|
|
28
28
|
"data": [
|
|
29
|
+
{
|
|
30
|
+
"id": "claude_4_5_sonnet",
|
|
31
|
+
"created": 1718841600,
|
|
32
|
+
"object": "model",
|
|
33
|
+
"owned_by": "Anthropic"
|
|
34
|
+
},
|
|
29
35
|
{
|
|
30
36
|
"id": "llama3211b",
|
|
31
37
|
"created": 1727222400,
|
|
@@ -49,7 +55,7 @@ To reach chat completions the documented endpoint is `<base url>/api/v1/chat/com
|
|
|
49
55
|
|
|
50
56
|
**Request Body**
|
|
51
57
|
|
|
52
|
-
* **model**: The model ID (e.g: gemini-2.0-flash)
|
|
58
|
+
* **model**: The model ID (e.g: gemini-2.0-flash, claude_3_haiku)
|
|
53
59
|
* **messages**: An array of of message items consisting of User message, Image Content, Document Content, Assistant Message
|
|
54
60
|
* **max_tokens**: Maximum response length (optional)
|
|
55
61
|
* **temperature**: Response creativity (0.0-2.0, optional)
|
|
@@ -57,6 +63,7 @@ To reach chat completions the documented endpoint is `<base url>/api/v1/chat/com
|
|
|
57
63
|
| **Models** | **Range** | **Default value** |
|
|
58
64
|
| :------- | :------: | -------: |
|
|
59
65
|
| Google models | 0.0 - 2.0 | 1.0 |
|
|
66
|
+
| Anthropic models | 0.0 - 1.0 | 0.5 |
|
|
60
67
|
| Meta models | 0.0 - 1.0 | 0.5 |
|
|
61
68
|
|
|
62
69
|
* **top_p**: An alternative to sampling with temperature, called nucleus sampling (optional)
|
|
@@ -18,6 +18,10 @@ USAi API is organized around [REST](http://en.wikipedia.org/wiki/Representationa
|
|
|
18
18
|
- [Gemini 2.5 Flash](https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash)
|
|
19
19
|
- [Gemini 2.5 Pro](https://ai.google.dev/gemini-api/docs/models#gemini-2.5-pro)
|
|
20
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)
|
|
21
25
|
|
|
22
26
|
**Meta models**
|
|
23
27
|
- [Llama 3.2 11B](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_2/)
|
|
@@ -33,7 +37,7 @@ Each model we draw on has unique capabilities. Models may also respond different
|
|
|
33
37
|
|
|
34
38
|
#### Content types
|
|
35
39
|
|
|
36
|
-
The models USAi API draws on support multiple types of inputs; text, image, and file content types. For additional detail about how we handle these content types, reference [OpenAI’s API documentation](https://platform.openai.com/docs/api-reference/chat/create).
|
|
40
|
+
The models USAi API draws on support multiple types of inputs; text, image, and file content types. However, each model has different input capabilities: for example, Claude Sonnet supports Optical Character Recognition (OCR) and recognizes image-only PDFs, while Claude Haiku and Llama currently do not. For additional detail about how we handle these content types, reference [OpenAI’s API documentation](https://platform.openai.com/docs/api-reference/chat/create).
|
|
37
41
|
|
|
38
42
|
### Authentication
|
|
39
43
|
|