Update README.md

README.md

@@ -231,19 +231,30 @@ with open(f"{os.path.dirname(os.path.abspath('__file__'))}/workspace/elyza-tasks
             item = ""
 
 # モデルによるタスクの推論。
+import re
 from tqdm import tqdm
 
 results = []
+n = 2
+
 
 for data in tqdm(datasets, smoothing=0.0):
     input_text = data["input"]
-    dataset_index = retrieve(input_text)
+    dataset_index_list = retrieve(input_text, n)
+
+    examples = ""
+    for dataset_index in dataset_index_list:
+        examples += EXAMPLE_TEMPLATE.format(
+            dataset_input=elyza_tasks_datasets["test"]["input"][dataset_index].strip(),
+            dataset_eval_aspect=elyza_tasks_datasets["test"]["eval_aspect"][dataset_index].strip(),
+            dataset_answer=elyza_tasks_datasets["test"]["output"][dataset_index].strip(),
+        )
 
     system_prompt = SYSTEM_PROMPT.format(
-        dataset_input=elyza_tasks_datasets["test"]["input"][dataset_index],
-        dataset_eval_aspect=elyza_tasks_datasets["test"]["eval_aspect"][dataset_index],
-        dataset_answer=elyza_tasks_datasets["test"]["output"][dataset_index],
+        examples=examples.strip(),
     )
+    # print(examples)
+    # print(input_text)
 
     output = llm(input_text=input_text,
                  system_prompt=system_prompt,
@@ -251,17 +262,23 @@ for data in tqdm(datasets, smoothing=0.0):
                  repetition_penalty=1.15,
                  # stream=True,
                  ).strip()
+    # print("-----------------------------------------------------------------------------------------------------------------------------------")
+    # print(output.strip())
+    # print("===================================================================================================================================")
+    # print(re.sub(r"^[\s\S]*?### 出力", "", re.sub(r"^[\s\S]*?\*\*出力\*\*:", "", output)).strip())
+    # print("-----------------------------------------------------------------------------------------------------------------------------------")
+
     results.append({
         "task_id": data["task_id"],
         "input": input_text,
-        "output": output,
+        "output_org": output.strip(),
+        "output": re.sub(r"^[\s\S]*?### 出力", "", output).strip(),
         "elyza_tasks_id": dataset_index,
-        "dataset_input": elyza_tasks_datasets["test"]["input"][dataset_index],
-        "dataset_eval_aspect": elyza_tasks_datasets["test"]["eval_aspect"][dataset_index],
-        "dataset_answer": elyza_tasks_datasets["test"]["output"][dataset_index],
     })
 
-results にタスクの解答が入っている
+
+
+# results にタスクの解答が入っている
 
 ```