@fre4x/gemini 1.0.31 → 1.0.42
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 +24 -5
- package/dist/index.js +30987 -30822
- package/package.json +5 -4
package/README.md
CHANGED
|
@@ -10,15 +10,25 @@ Google's Gemini is not a chatbot. It is a multimodal reasoning engine. This B1TE
|
|
|
10
10
|
|
|
11
11
|
| Tool | Capability |
|
|
12
12
|
|------|-----------|
|
|
13
|
-
| `generate_text` | Text generation and reasoning
|
|
14
|
-
| `analyze_media` | Multimodal analysis — image, video, audio —
|
|
15
|
-
| `
|
|
16
|
-
| `
|
|
13
|
+
| `generate_text` | Text generation and reasoning. Default model: `gemini-2.5-flash` |
|
|
14
|
+
| `analyze_media` | Multimodal analysis — image, video, audio — via URL or `file://` path. MIME type auto-detected from extension. |
|
|
15
|
+
| `list_models` | List available Gemini, Imagen, and Veo models. Filter by `text`, `image`, `video`, or `all`. |
|
|
16
|
+
| `generate_image` | Image synthesis via Imagen 4 (`imagen-4.0-generate-001`). Optionally save to `output_dir`. |
|
|
17
|
+
| `generate_video` | Async video generation via Veo (`veo-2.0-generate-001`). Returns `operation_name` to poll. |
|
|
18
|
+
| `get_video_status` | Poll video generation status. Returns URLs when complete. Optionally saves to `output_dir`. |
|
|
17
19
|
|
|
18
20
|
## Requirements
|
|
19
21
|
|
|
20
22
|
A [Google AI Studio API key](https://aistudio.google.com/) — set as `GEMINI_API_KEY`.
|
|
21
23
|
|
|
24
|
+
## Mock Mode
|
|
25
|
+
|
|
26
|
+
Run without an API key (returns fixture data of identical shape):
|
|
27
|
+
|
|
28
|
+
```bash
|
|
29
|
+
MOCK=true npx @fre4x/gemini
|
|
30
|
+
```
|
|
31
|
+
|
|
22
32
|
## Deploy
|
|
23
33
|
|
|
24
34
|
```json
|
|
@@ -35,12 +45,21 @@ A [Google AI Studio API key](https://aistudio.google.com/) — set as `GEMINI_AP
|
|
|
35
45
|
}
|
|
36
46
|
```
|
|
37
47
|
|
|
48
|
+
## Notes
|
|
49
|
+
|
|
50
|
+
- **Image generation** requires Imagen access — not available on all free-tier API keys. Check [AI Studio](https://aistudio.google.com/).
|
|
51
|
+
- **Video generation** is async. Call `generate_video` → poll `get_video_status` every ~30s until `done: true`.
|
|
52
|
+
- `analyze_media` accepts `file://` paths for local files and auto-detects MIME type from URL extension (jpg, png, mp4, mp3, pdf, etc.).
|
|
53
|
+
- `output_dir` on `generate_image` and `get_video_status` saves files to disk. Directory is created if it doesn't exist.
|
|
54
|
+
|
|
38
55
|
## Development
|
|
39
56
|
|
|
40
57
|
```bash
|
|
41
58
|
npm install
|
|
42
59
|
npm run dev # tsx, no build
|
|
43
|
-
npm run build #
|
|
60
|
+
npm run build # esbuild → dist/
|
|
61
|
+
npm test # vitest unit tests
|
|
62
|
+
npm run test:e2e # e2e (requires Python 3 + mcp package)
|
|
44
63
|
```
|
|
45
64
|
|
|
46
65
|
## License
|