From 4f3b18c3b3392dbb8e7c87a17eeef5928c6229d3 Mon Sep 17 00:00:00 2001
From: Xinyao Wang <xinyao.wang@intel.com>
Date: Fri, 13 Dec 2024 13:49:21 +0800
Subject: [PATCH] fix bug

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
---
 comps/llms/text-generation/vllm/langchain/llm.py     |  8 --------
 ...ms_text-generation_vllm_langchain_on_intel_hpu.sh | 12 ++++++++++++
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/comps/llms/text-generation/vllm/langchain/llm.py b/comps/llms/text-generation/vllm/langchain/llm.py
index ee21fe146..19c16b8ea 100644
--- a/comps/llms/text-generation/vllm/langchain/llm.py
+++ b/comps/llms/text-generation/vllm/langchain/llm.py
@@ -222,11 +222,8 @@ async def stream_generator():
             chat_completion = client.completions.create(
                 model=model_name,
                 prompt=prompt,
-                best_of=input.best_of,
                 echo=input.echo,
                 frequency_penalty=input.frequency_penalty,
-                logit_bias=input.logit_bias,
-                logprobs=input.logprobs,
                 max_tokens=input.max_tokens,
                 n=input.n,
                 presence_penalty=input.presence_penalty,
@@ -261,9 +258,6 @@ async def stream_generator():
                 model=model_name,
                 messages=input.messages,
                 frequency_penalty=input.frequency_penalty,
-                logit_bias=input.logit_bias,
-                logprobs=input.logprobs,
-                top_logprobs=input.top_logprobs,
                 max_tokens=input.max_tokens,
                 n=input.n,
                 presence_penalty=input.presence_penalty,
@@ -275,8 +269,6 @@ async def stream_generator():
                 stream_options=input.stream_options,
                 temperature=input.temperature,
                 top_p=input.top_p,
-                tools=input.tools,
-                parallel_tool_calls=input.parallel_tool_calls,
                 user=input.user,
             )
 
diff --git a/tests/llms/test_llms_text-generation_vllm_langchain_on_intel_hpu.sh b/tests/llms/test_llms_text-generation_vllm_langchain_on_intel_hpu.sh
index 88435054e..da75ad624 100644
--- a/tests/llms/test_llms_text-generation_vllm_langchain_on_intel_hpu.sh
+++ b/tests/llms/test_llms_text-generation_vllm_langchain_on_intel_hpu.sh
@@ -114,6 +114,18 @@ function validate_microservice() {
         docker logs test-comps-vllm-microservice
         exit 1
     fi
+    result=$(http_proxy="" curl http://${ip_address}:5030/v1/chat/completions \
+        -X POST \
+        -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": "What is Deep Learning?", "max_tokens":17, "stream":false}' \
+        -H 'Content-Type: application/json')
+    if [[ $result == *"content"* ]]; then
+        echo "Result correct."
+    else
+        echo "Result wrong. Received was $result"
+        docker logs test-comps-vllm-service
+        docker logs test-comps-vllm-microservice
+        exit 1
+    fi
 }
 
 function stop_docker() {