First Commit

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,73 @@
+import re
+import unicodedata
+
+import requests
+import streamlit as st
+from bs4 import BeautifulSoup
+from transformers import (
+    AutoModelForQuestionAnswering,
+    AutoTokenizer,
+    QuestionAnsweringPipeline,
+)
+
+model_name = "KoichiYasuoka/bert-base-japanese-wikipedia-ud-head"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+qa_pipeline = QuestionAnsweringPipeline(model=model, tokenizer=tokenizer)
+
+
+st.title("株価お知らせBot")
+stock_code = st.text_input(
+    "株価を知りたい企業の証券コードを入力してください",
+    placeholder="証券コード",
+    max_chars=4,
+    help="4桁の数字",
+)
+
+if "content" not in st.session_state:
+    st.write("株価を知りたい企業の証券コードを入力してください")
+
+if st.button("株価を知りたい"):
+    url = f"https://nikkei.com/nkd/company/?scode={stock_code}"
+    res = requests.get(url)
+    soup = BeautifulSoup(res.text, "html.parser")
+
+    _text = soup.find("div", attrs={"class": "m-stockInfo_top_left"}).text
+
+    content = unicodedata.normalize("NFKD", _text)
+    st.session_state.content = re.sub("[\r\t\n]+", " ", content)
+
+
+# Transformersで回答を作成
+def generate_response(prompt, max_length=50):
+    # input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    # Generate response
+    answer = qa_pipeline(context=st.session_state.content[:100], question=prompt)
+
+    return answer["answer"]
+
+
+# メッセージがない時
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "何か御用ですか？"}]
+
+# チャット内容の表示
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+# ユーザーの質問
+if prompt := st.chat_input():
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+# AIによる回答
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("考え中..."):
+            response = generate_response(prompt)
+            st.write(response)
+    message = {"role": "assistant", "content": response}
+    st.session_state.messages.append(message)

pyproject.toml

@@ -0,0 +1,67 @@
+[tool.poetry]
+name = "simple-chatbot"
+version = "0.1.0"
+description = ""
+authors = ["YoheiHayamizu <[email protected]>"]
+license = "mit"
+readme = "README.md"
+packages = [{ include = "simple_chatbot" }]
+
+[tool.poetry.dependencies]
+python = "^3.10"
+streamlit = "^1.40.2"
+sentencepiece = "^0.2.0"
+transformers = "^4.47.0"
+bs4 = "^0.0.2"
+cython = "^3.0.11"
+torch = "^2.5.1"
+
+
+[tool.poetry.group.dev.dependencies]
+ruff = "^0.8.2"
+
+[tool.ruff]
+line-length = 119
+indent-width = 4
+
+[tool.ruff.lint]
+# Flake8、Black、isort、エラー、警告のみを選択
+select = ["F", "B", "I", "E", "W"]
+ignore = []
+
+# すべてのルールに対して修正を許可（`--fix`を使用した場合）
+fixable = ["ALL"]
+unfixable = []
+# extend-select = ["E501"]
+
+[tool.ruff.lint.per-file-ignores]
+# `__init__.py`ファイルや特定のサブディレクトリで、`E402`（インポート違反）を無視
+"__init__.py" = ["E402"]
+"**/{tests,docs,tools}/*" = ["E402"]
+
+[tool.ruff.format]
+# デフォルトで除外されるディレクトリ
+exclude = [
+    ".venv",
+    ".git",
+    ".tox",
+    ".mypy_cache",
+    ".pytest_cache",
+    "__pycache__",
+    "build",
+    "dist",
+    "docs",
+    "tests",
+    "tools",
+]
+indent-style = "space" # Blackと同様に、インデントはスペースで
+quote-style = "double" # Blackと同様に、文字列はダブルクォートを使用
+skip-magic-trailing-comma = false # Blackと同様に、魔法のカンマ（トレイリングコンマ）を無視しない
+line-ending = "auto" # Blackと同様に、行末文字を自動検出
+docstring-code-format = false # ドキュメンテーションストリング内のコード例を自動フォーマット
+docstring-code-line-length = "dynamic" # ドキュメンテーションストリング内のコードスニペットの行の長さ
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"