doc(example): update jina example to reflect lack of SDK, add cohere example

Signed-off-by: Kyle Mistele <[email protected]>

Author: K-Mistele

examples/online_serving/cohere_rerank_client.py

@@ -0,0 +1,37 @@
+"""
+Example of using the OpenAI entrypoint's rerank API which is compatible with
+the Cohere SDK: https://github.com/cohere-ai/cohere-python
+
+run: vllm serve --model BAAI/bge-reranker-base
+"""
+import cohere
+
+# cohere v1 client
+co = cohere.Client(base_url="http://localhost:8000", api_key="sk-fake-key")
+rerank_v1_result = co.rerank(
+    model="BAAI/bge-reranker-base",
+    query="What is the capital of France?",
+    documents=[
+        "The capital of France is Paris",
+        "Reranking is fun!",
+        "vLLM is an open-source framework for fast AI serving"
+    ]
+)
+
+print(rerank_v1_result)
+
+# or the v2
+co2 = cohere.ClientV2("sk-fake-key", base_url="http://localhost:8000")
+
+v2_rerank_result = co2.rerank(
+    model="BAAI/bge-reranker-base",
+    query="What is the capital of France?",
+    documents=[
+        "The capital of France is Paris",
+        "Reranking is fun!",
+        "vLLM is an open-source framework for fast AI serving"
+    ]
+)
+
+print(v2_rerank_result)
+

examples/online_serving/jinjaai_rerank_client.py

@@ -1,6 +1,7 @@
 """
 Example of using the OpenAI entrypoint's rerank API which is compatible with
-Jina and Cohere
+Jina and Cohere https://jina.ai/reranker
+
 run: vllm serve --model BAAI/bge-reranker-base
 """
 import json
@@ -21,7 +22,6 @@
         "The capital of France is Paris.", "Horses and cows are both animals"
     ]
 }
-
 response = requests.post(url, headers=headers, json=data)
 
 # Check the response