From 4f27044aab45d4e1c1a74fdc82217eadb0384411 Mon Sep 17 00:00:00 2001
From: Irina Yuryeva <76484191+upayuryeva@users.noreply.github.com>
Date: Thu, 6 Mar 2025 18:37:10 +0300
Subject: [PATCH] [Doc] Correct beam_search using in generative_models.md
 (#14363)

---
 docs/source/models/generative_models.md | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/docs/source/models/generative_models.md b/docs/source/models/generative_models.md
index f31e5715d1754..06daa04f2deaa 100644
--- a/docs/source/models/generative_models.md
+++ b/docs/source/models/generative_models.md
@@ -54,14 +54,16 @@ The {class}`~vllm.LLM.beam_search` method implements [beam search](https://huggi
 For example, to search using 5 beams and output at most 50 tokens:
 
 ```python
+from vllm import LLM
+from vllm.sampling_params import BeamSearchParams
+
 llm = LLM(model="facebook/opt-125m")
 params = BeamSearchParams(beam_width=5, max_tokens=50)
-outputs = llm.generate("Hello, my name is", params)
+outputs = llm.beam_search([{"prompt": "Hello, my name is "}], params)
 
 for output in outputs:
-    prompt = output.prompt
-    generated_text = output.outputs[0].text
-    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+    generated_text = output.sequences[0].text
+    print(f"Generated text: {generated_text!r}")
 ```
 
 ### `LLM.chat`