codebaxing 0.2.54 → 1.0.1
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/README.md +12 -3
- package/README.vi.md +12 -3
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -38,6 +38,8 @@ npx codebaxing@latest index /path/to/your/project
|
|
|
38
38
|
|
|
39
39
|
This creates a `.codebaxing/` folder with the index. Only needs to be done once per project.
|
|
40
40
|
|
|
41
|
+
> **Performance note:** Local embedding is slow (~4 min for ~4,000 files). For faster indexing, use Gemini embedding (free) — see [Cloud Embedding](#cloud-embedding-fastest) below.
|
|
42
|
+
|
|
41
43
|
### 3. Install MCP Server for AI Editors
|
|
42
44
|
|
|
43
45
|
```bash
|
|
@@ -90,10 +92,10 @@ After installing, AI agents can use these tools:
|
|
|
90
92
|
|
|
91
93
|
### Cloud Embedding (Fastest)
|
|
92
94
|
|
|
93
|
-
|
|
95
|
+
Local embedding runs on CPU and can be slow for large codebases (~4 min for ~4,000 files). Cloud embedding is **~25x faster** and recommended for any project with 1,000+ files.
|
|
94
96
|
|
|
95
97
|
```bash
|
|
96
|
-
# Gemini (FREE - recommended)
|
|
98
|
+
# Gemini (FREE - recommended, 1500 RPM free tier)
|
|
97
99
|
CODEBAXING_EMBEDDING_PROVIDER=gemini GEMINI_API_KEY=... npx codebaxing@latest index /path
|
|
98
100
|
|
|
99
101
|
# OpenAI (text-embedding-3-small, 384 dims)
|
|
@@ -103,7 +105,14 @@ CODEBAXING_EMBEDDING_PROVIDER=openai OPENAI_API_KEY=sk-... npx codebaxing@latest
|
|
|
103
105
|
CODEBAXING_EMBEDDING_PROVIDER=voyage VOYAGE_API_KEY=va-... npx codebaxing@latest index /path
|
|
104
106
|
```
|
|
105
107
|
|
|
106
|
-
|
|
108
|
+
| Provider | Model | Speed | Cost |
|
|
109
|
+
|----------|-------|-------|------|
|
|
110
|
+
| **Gemini** | `text-embedding-004` (768 dims) | ~10,000 texts/sec | Free (1500 RPM) |
|
|
111
|
+
| **OpenAI** | `text-embedding-3-small` (384 dims) | ~10,000 texts/sec | ~$0.02 / 1M tokens |
|
|
112
|
+
| **Voyage** | `voyage-code-3` (1024 dims) | ~10,000 texts/sec | ~$0.06 / 1M tokens |
|
|
113
|
+
| **Local** | `all-MiniLM-L6-v2` (384 dims) | ~200 texts/sec | Free (CPU) |
|
|
114
|
+
|
|
115
|
+
> **Note:** Switching between providers requires full re-index (`npx codebaxing@latest index <path>`) due to dimension differences.
|
|
107
116
|
|
|
108
117
|
### Environment Variables
|
|
109
118
|
|
package/README.vi.md
CHANGED
|
@@ -38,6 +38,8 @@ npx codebaxing@latest index /path/to/your/project
|
|
|
38
38
|
|
|
39
39
|
Tạo folder `.codebaxing/` chứa index. Chỉ cần làm một lần cho mỗi project.
|
|
40
40
|
|
|
41
|
+
> **Lưu ý về tốc độ:** Embedding local khá chậm (~4 phút cho ~4,000 files). Để index nhanh hơn, dùng Gemini embedding (miễn phí) — xem phần [Cloud Embedding](#cloud-embedding-nhanh-nhất) bên dưới.
|
|
42
|
+
|
|
41
43
|
### 3. Cài MCP Server cho AI Editors
|
|
42
44
|
|
|
43
45
|
```bash
|
|
@@ -90,10 +92,10 @@ Sau khi cài, AI agents có thể dùng các tools:
|
|
|
90
92
|
|
|
91
93
|
### Cloud Embedding (Nhanh nhất)
|
|
92
94
|
|
|
93
|
-
|
|
95
|
+
Embedding local chạy trên CPU và khá chậm cho codebase lớn (~4 phút cho ~4,000 files). Cloud embedding nhanh hơn **~25x** và được khuyến khích cho project từ 1,000+ files.
|
|
94
96
|
|
|
95
97
|
```bash
|
|
96
|
-
# Gemini (MIỄN PHÍ - khuyên dùng)
|
|
98
|
+
# Gemini (MIỄN PHÍ - khuyên dùng, 1500 RPM free tier)
|
|
97
99
|
CODEBAXING_EMBEDDING_PROVIDER=gemini GEMINI_API_KEY=... npx codebaxing@latest index /path
|
|
98
100
|
|
|
99
101
|
# OpenAI (text-embedding-3-small, 384 dims)
|
|
@@ -103,7 +105,14 @@ CODEBAXING_EMBEDDING_PROVIDER=openai OPENAI_API_KEY=sk-... npx codebaxing@latest
|
|
|
103
105
|
CODEBAXING_EMBEDDING_PROVIDER=voyage VOYAGE_API_KEY=va-... npx codebaxing@latest index /path
|
|
104
106
|
```
|
|
105
107
|
|
|
106
|
-
|
|
108
|
+
| Provider | Model | Tốc độ | Chi phí |
|
|
109
|
+
|----------|-------|--------|---------|
|
|
110
|
+
| **Gemini** | `text-embedding-004` (768 dims) | ~10,000 texts/s | Miễn phí (1500 RPM) |
|
|
111
|
+
| **OpenAI** | `text-embedding-3-small` (384 dims) | ~10,000 texts/s | ~$0.02 / 1M tokens |
|
|
112
|
+
| **Voyage** | `voyage-code-3` (1024 dims) | ~10,000 texts/s | ~$0.06 / 1M tokens |
|
|
113
|
+
| **Local** | `all-MiniLM-L6-v2` (384 dims) | ~200 texts/s | Miễn phí (CPU) |
|
|
114
|
+
|
|
115
|
+
> **Lưu ý:** Chuyển đổi giữa các provider cần re-index (`npx codebaxing@latest index <path>`) do khác dimension.
|
|
107
116
|
|
|
108
117
|
### Biến Môi Trường
|
|
109
118
|
|