From c724543da1e599012b9e14ef664dd9d61bcec75f Mon Sep 17 00:00:00 2001
From: lidia9 <lidia@aliasrobotics.com>
Date: Fri, 9 May 2025 16:48:52 +0200
Subject: [PATCH] run tests before mr

---
 benchmarks/eval.py            |  1 -
 ci/benchmarks/.benchmarks.yml | 10 ----------
 2 files changed, 11 deletions(-)

diff --git a/benchmarks/eval.py b/benchmarks/eval.py
index a39bd7ca..58684a7e 100644
--- a/benchmarks/eval.py
+++ b/benchmarks/eval.py
@@ -9,7 +9,6 @@ Usage:
 Arguments:
     -m, --model           Specify the model to evaluate (e.g., "gpt-4", "qwen2.5:14b", etc.)
     -d, --dataset_file    Path to the dataset file (JSON or TSV) containing questions to evaluate
-    -o, --output_dir      Specify the output directory for results (default: "benchmarks/outputs/[benchmark_name]")
     -B, --backend         Backend to use: "openai", "openrouter", "ollama" (required)
     -e, --eval            Specify the evaluation benchmark
 
diff --git a/ci/benchmarks/.benchmarks.yml b/ci/benchmarks/.benchmarks.yml
index febb3f54..69648915 100644
--- a/ci/benchmarks/.benchmarks.yml
+++ b/ci/benchmarks/.benchmarks.yml
@@ -19,16 +19,6 @@
         fi
       done
 
-    # to be removed 
-    - |
-      if [ "$BACKEND" = "ollama" ]; then
-        echo "Starting Ollama service..."
-        ollama serve &
-        sleep 10  # Give time for Ollama to start
-        curl http://localhost:8000/api/tags || echo "Ollama service may not be running properly"
-      fi
-    ## to be removed
-
 
     #- python3 benchmarks/cybermetric/CyberMetric_evaluator.py --model_name $MODEL_NAME --file_path $BENCHMARK_FILE
     - echo $OLLAMA_API_BASE