deepseek-tui 0.4.4 → 0.5.2
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/README.md +13 -0
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -37,6 +37,19 @@ The app talks to DeepSeek's documented OpenAI-compatible Chat Completions API.
|
|
|
37
37
|
Set `DEEPSEEK_BASE_URL` only if you need the China endpoint or DeepSeek beta
|
|
38
38
|
features such as strict tool mode, chat prefix completion, or FIM completion.
|
|
39
39
|
|
|
40
|
+
NVIDIA NIM-hosted DeepSeek V4 Pro is also supported:
|
|
41
|
+
|
|
42
|
+
```bash
|
|
43
|
+
deepseek auth set --provider nvidia-nim --api-key "YOUR_NVIDIA_API_KEY"
|
|
44
|
+
deepseek --provider nvidia-nim
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
For a single process, set `DEEPSEEK_PROVIDER=nvidia-nim` and `NVIDIA_API_KEY`
|
|
48
|
+
or `NVIDIA_NIM_API_KEY` (with `DEEPSEEK_API_KEY` as a compatibility fallback).
|
|
49
|
+
The NIM default model is `deepseek-ai/deepseek-v4-pro` and the default base URL
|
|
50
|
+
is `https://integrate.api.nvidia.com/v1`. With `--provider nvidia-nim`,
|
|
51
|
+
`--model deepseek-v4-flash` maps to `deepseek-ai/deepseek-v4-flash`.
|
|
52
|
+
|
|
40
53
|
## Supported platforms
|
|
41
54
|
|
|
42
55
|
- Linux x64
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "deepseek-tui",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"deepseekBinaryVersion": "0.
|
|
3
|
+
"version": "0.5.2",
|
|
4
|
+
"deepseekBinaryVersion": "0.5.2",
|
|
5
5
|
"description": "Install and run deepseek and deepseek-tui binaries from GitHub release artifacts.",
|
|
6
6
|
"author": "Hmbown",
|
|
7
7
|
"license": "MIT",
|