Update README.md

README.md

@@ -244,18 +244,63 @@ with KaLMVLLMReranker(
     print(reranker.rank(query, documents))
 ```
 
-Offline CLI and online service:
+Offline CLI:
 
 ```bash
 kalm-vllm-rerank --return-margin
+```
+
+To deploy the online service, install the HTTP dependencies and keep the
+server running in the first terminal:
 
+```bash
 pip install "fastapi>=0.136,<0.137" "uvicorn>=0.46,<0.47"
-kalm-vllm-serve --host 0.0.0.0 --port 8000
-kalm-vllm-client --endpoint rerank --return-margin
+export CUDA_VISIBLE_DEVICES=0
+export VLLM_PLUGINS=kalm_t5gemma2
+
+kalm-vllm-serve \
+  --host 0.0.0.0 \
+  --port 8000 \
+  --model KaLM-Embedding/KaLM-Reranker-V1-Nano \
+  --query-max-length 512 \
+  --document-max-length 1024 \
+  --encoder-chunk-size 4 \
+  --max-model-len 2048
+```
+
+In a second terminal, check the server:
+
+```bash
+conda activate kalm-vllm
+kalm-vllm-client --base-url http://127.0.0.1:8000 --health
+```
+
+Use `/rerank` for one query and a list of documents. Results are sorted by
+score:
+
+```bash
+kalm-vllm-client \
+  --base-url http://127.0.0.1:8000 \
+  --endpoint rerank \
+  --json-file ./KaLM-Reranker-V1-Nano/vllm_support/examples/rerank_request.json \
+  --return-margin \
+  --top-k 10
+```
+
+Use `/score` to score a batch of independent query-document pairs. Results
+preserve the input order and optional IDs:
+
+```bash
+kalm-vllm-client \
+  --base-url http://127.0.0.1:8000 \
+  --endpoint score \
+  --json-file ./KaLM-Reranker-V1-Nano/vllm_support/examples/score_request.json \
+  --return-margin
 ```
 
 The default output is `P(yes)`. Set `return_margin=true` to also receive
-`yes_logit - no_logit`. The supported encoder chunk sizes are
+`yes_logit - no_logit`; the client flag `--return-margin` applies the same
+setting to a JSON file request. The supported encoder chunk sizes are
 `1, 2, 4, 8, 16, 32`, with `4` as the default.
 
 This adapter uses vLLM's plugin, scheduling and pooling interfaces while the