You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+12Lines changed: 12 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -163,8 +163,20 @@ Settings are initialized by `openkb init`, and stored in `.openkb/config.yaml`:
163
163
model: gpt-5.4 # LLM model (any LiteLLM-supported provider)
164
164
language: en # Wiki output language
165
165
pageindex_threshold: 20# PDF pages threshold for PageIndex
166
+
storage_backend: sqlite # Storage backend: sqlite (default) or json
166
167
```
167
168
169
+
### Storage Backend
170
+
171
+
OpenKB supports two storage backends for the file hash registry:
172
+
173
+
| Backend | Description | Use Case |
174
+
|---------|-------------|----------|
175
+
| `sqlite` | SQLite database (default) | Better concurrency, scalability, recommended for production |
176
+
| `json` | JSON file | Simple, human-readable, for small installations |
177
+
178
+
Migration from JSON to SQLite happens automatically when you switch to `sqlite` backend and a `hashes.json` file exists. The JSON file is preserved but no longer used.
179
+
168
180
Model names use `provider/model` LiteLLM [format](https://docs.litellm.ai/docs/providers) (OpenAI models can omit the prefix):
0 commit comments