fix(docs/rerankers): pass rerank=True so examples actually rerank

The reranker examples configured a `reranker` block but called
memory.search(...) without rerank=True. Memory.search() defaults rerank=False
(mem0/memory/main.py:1333) and only reranks 'if rerank and self.reranker'
(:1447), so reranking never ran:

- cohere, zero_entropy, llm, sentence_transformer print result['rerank_score'],
  which doesn't exist unless reranking runs -> KeyError on copy-paste.
- optimization (reranker benchmark) and custom-prompts (reranker-prompt test)
  silently measured un-reranked search.

Add the missing rerank=True flag to every search meant to exercise the reranker.

docs/components/rerankers/custom-prompts.mdx

@@ -193,7 +193,7 @@ for i, prompt in enumerate(prompts):
     config["reranker"]["config"]["scoring_prompt"] = prompt
     memory = Memory.from_config(config)
 
-    results = memory.search("test query", filters={"user_id": "test_user"})
+    results = memory.search("test query", filters={"user_id": "test_user"}, rerank=True)
     print(f"Prompt {i+1} results: {results}")
 ```
 

docs/components/rerankers/models/cohere.mdx

@@ -95,7 +95,7 @@ messages = [
 memory.add(messages, user_id="bob")
 
 # Search with reranking
-results = memory.search("What is the user's profession?", filters={"user_id": "bob"})
+results = memory.search("What is the user's profession?", filters={"user_id": "bob"}, rerank=True)
 
 for result in results['results']:
     print(f"Memory: {result['memory']}")

docs/components/rerankers/models/llm.mdx

@@ -111,7 +111,7 @@ messages = [
 memory.add(messages, user_id="david")
 
 # Search with LLM reranking
-results = memory.search("What programming topics is the user studying?", filters={"user_id": "david"})
+results = memory.search("What programming topics is the user studying?", filters={"user_id": "david"}, rerank=True)
 
 for result in results['results']:
     print(f"Memory: {result['memory']}")

docs/components/rerankers/models/sentence_transformer.mdx

@@ -101,7 +101,7 @@ messages = [
 memory.add(messages, user_id="charlie")
 
 # Search with local reranking
-results = memory.search("What books does the user like?", filters={"user_id": "charlie"})
+results = memory.search("What books does the user like?", filters={"user_id": "charlie"}, rerank=True)
 
 for result in results['results']:
     print(f"Memory: {result['memory']}")

docs/components/rerankers/models/zero_entropy.mdx

@@ -86,7 +86,7 @@ messages = [
 memory.add(messages, user_id="alice")
 
 # Search with reranking
-results = memory.search("What Italian food does the user like?", filters={"user_id": "alice"})
+results = memory.search("What Italian food does the user like?", filters={"user_id": "alice"}, rerank=True)
 
 for result in results['results']:
     print(f"Memory: {result['memory']}")

docs/components/rerankers/optimization.mdx

@@ -146,7 +146,7 @@ def measure_reranker_performance(config, queries, user_id):
     latencies = []
     for query in queries:
         start_time = time.time()
-        results = memory.search(query, filters={"user_id": user_id})
+        results = memory.search(query, filters={"user_id": user_id}, rerank=True)
         latency = time.time() - start_time
         latencies.append(latency)
 
@@ -218,7 +218,7 @@ async def parallel_search(config, queries, user_id):
 
     # Process multiple queries concurrently
     tasks = [
-        memory.search(query, filters={"user_id": user_id})
+        memory.search(query, filters={"user_id": user_id}, rerank=True)
         for query in queries
     ]