Skip to content

Add expected facts for eval dataset #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
korryu3 wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Add expected facts for eval dataset #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a5b938f
feat: add base expected_facts
korryu3 Feb 3, 2025
1abecda
feat: delete old eval dataset
korryu3 Feb 3, 2025
3431661
feat: jsonでLLM-as-a-Judgeが実行できるように変更
korryu3 Feb 3, 2025
c54adaa
chore: debug用のコードを削除
korryu3 Feb 3, 2025
fec83a7
Merge branch 'main' into add-expected_facts_for-eval-dataset
korryu3 Feb 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 21 additions & 11 deletions RAG_eval-LLM-As-A-Judge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,20 +63,30 @@
# COMMAND ----------

import mlflow
import pandas as pd
import json

exsample_eval_set = [
{
"request_id": "1",
"request": "AO入学はありますか？", # question
"expected_response": "はい、あります！AO入学制度は、学力試験だけでは評価できない個性や意欲を重視した入学選考方法です。" # 模範解答
},
{
"request_id": "1",
"request": "AO入学はありますか？", # question
"expected_facts": [
"AO入学はあります",
],
},
]

#### Convert dictionary to a pandas DataFrame
csv_path = "eval-dataset.csv"
eval_set_df = pd.read_csv(csv_path)
json_path = "eval-dataset.json"
with open(json_path, "r") as f:
tmp_eval_dataset_list = json.load(f)

eval_set_df["request_id"] = eval_set_df["request_id"].astype(str) # 文字列じゃないとエラー出る
eval_dataset_list = []
for i, tmp_eval_dataset_dict in enumerate(tmp_eval_dataset_list, start=1):
eval_dataset_dict = {
"request": tmp_eval_dataset_dict["request"],
"expected_facts": tmp_eval_dataset_dict["expected_facts"],
"request_id": str(i)
}
eval_dataset_list.append(eval_dataset_dict)

model_name = f"{catalog}.{dbName}.{registered_model_name}"

Expand All @@ -86,7 +96,7 @@
# with mlflow.start_run(run_id=logged_chain_info.run_id):
with mlflow.start_run(run_name="new_eval_run"):
evaluation_results = mlflow.evaluate(
data=eval_set_df,
data=eval_dataset_list,
# data=exsample_eval_set,
model=f"models:/{model_name}/{uc_model_info.version}",
model_type="databricks-agent",
Expand Down
Loading