@irongraph/cli-darwin-arm64 0.1.7 → 0.1.8
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 +4 -5
- package/THIRD_PARTY_NOTICES.txt +631 -1622
- package/bin/irongraph +2 -2
- package/bin/irongraph-mcp +0 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -46,10 +46,9 @@ npx irongraph logs
|
|
|
46
46
|
npx irongraph status
|
|
47
47
|
```
|
|
48
48
|
|
|
49
|
-
Graph execution uses the CPU. Text inference selects its device independently
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
requires a supported accelerator. To run in the
|
|
49
|
+
Graph execution uses the CPU. Text inference selects its device independently: automatic selection
|
|
50
|
+
prefers a supported GPU and falls back to the CPU when no usable GPU is available. You can select
|
|
51
|
+
CPU inference explicitly with `--embedding-backend cpu`. To run in the
|
|
53
52
|
foreground with live terminal output, use `npx irongraph start` without `--background`.
|
|
54
53
|
|
|
55
54
|
### 3. Open the web console
|
|
@@ -178,7 +177,7 @@ your release. CUDA requires a package built with CUDA support.
|
|
|
178
177
|
## Start with a text document in Python
|
|
179
178
|
|
|
180
179
|
You need Python 3.9 or later, a matching official wheel, and a writable directory owned by one
|
|
181
|
-
application process. Default startup
|
|
180
|
+
application process. Default startup downloads, loads, and warms the local Bekko a8m embedding
|
|
182
181
|
model; allow network access and space for the model on first use.
|
|
183
182
|
|
|
184
183
|
After configuring your official package source, install the binary package:
|