Token-Optimized Query API
Token-Optimized Retrieval API is a high-performance modern C++ service designed for fast, efficient query compression. It transforms verbose input into compact, high-signal text for retrieval and LLM workflows. Engineered for low latency and high throughput, it can process ~1500-word inputs in seconds, making it ideal for real-time applications and large-scale pipelines. A minimal, focused API…
Token-Optimized Query API endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET |
getHealth /health |
|
| GET |
getStatus /status |
|
| POST |
prepareQueryFile /prepare-query-file |
|
| POST |
prepareQuery /prepare-query |
|
| GET |
getJob /jobs/{job_id} |
|
| GET |
getVersion /version |
|
| GET |
getHealth /health |
|
| GET |
getStatus /status |
|
| GET |
getJob /jobs/{job_id} |
|
| POST |
prepareQuery /prepare-query |
|
| POST |
prepareQueryFile /prepare-query-file |