geoffsee/predict-otron-9001
1
0
Fork 0
mirror of https://github.com/geoffsee/predict-otron-9001.git synced 2025-09-08 22:46:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update SERVER_CONFIG.md, replacing Local with Standalone

Browse Source
This commit is contained in:
Geoff Seemueller
2025-08-28 13:18:55 -04:00
committed by GitHub
parent d9772a67d1
commit 5bce413f8f
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/SERVER_CONFIG.md
View File

@@ -2,7 +2,7 @@
The predict-otron-9000 server supports two deployment modes controlled by the `SERVER_CONFIG` environment variable: The predict-otron-9000 server supports two deployment modes controlled by the `SERVER_CONFIG` environment variable:
1. **Local Mode** (default): Runs inference and embeddings services locally within the main server process 1. **Standalone Mode** (default): Runs inference and embeddings services locally within the main server process
2. **HighAvailability Mode**: Proxies requests to external inference and embeddings services 2. **HighAvailability Mode**: Proxies requests to external inference and embeddings services
## Configuration Format ## Configuration Format
@@ -11,7 +11,7 @@ The `SERVER_CONFIG` environment variable accepts a JSON configuration with the f
```json ```json
{ {
"serverMode": "Local", "serverMode": "Standalone",
"services": { "services": {
"inference_url": "http://inference-service:8080", "inference_url": "http://inference-service:8080",
"embeddings_url": "http://embeddings-service:8080" "embeddings_url": "http://embeddings-service:8080"
@@ -35,17 +35,17 @@ or
- `serverMode`: Either `"Local"` or `"HighAvailability"` - `serverMode`: Either `"Local"` or `"HighAvailability"`
- `services`: Optional object containing service URLs (uses defaults if not provided) - `services`: Optional object containing service URLs (uses defaults if not provided)
## Local Mode (Default) ## Standalone Mode (Default)
If `SERVER_CONFIG` is not set or contains invalid JSON, the server defaults to Local mode. If `SERVER_CONFIG` is not set or contains invalid JSON, the server defaults to Local mode.
### Example: Explicit Local Mode ### Example: Explicit Local Mode
```bash ```bash
export SERVER_CONFIG='{"serverMode": "Local"}' export SERVER_CONFIG='{"serverMode": "Standalone"}'
./run_server.sh ./run_server.sh
``` ```
In Local mode: In Standalone mode:
- Inference requests are handled by the embedded inference engine - Inference requests are handled by the embedded inference engine
- Embeddings requests are handled by the embedded embeddings engine - Embeddings requests are handled by the embedded embeddings engine
- No external services are required - No external services are required
@@ -220,4 +220,4 @@ To migrate from Local to HighAvailability mode:
3. Restart the predict-otron-9000 server 3. Restart the predict-otron-9000 server
4. Verify endpoints are working with test requests 4. Verify endpoints are working with test requests
The API contract remains identical, ensuring zero-downtime migration possibilities. The API contract remains identical, ensuring zero-downtime migration possibilities.