Upload 11 files

Hugging Face/FROM python:3.dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+
+# OS deps for WeasyPrint (Cairo/Pango) + 日本語フォント
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libcairo2 pango1.0-tools libpango-1.0-0 libgdk-pixbuf2.0-0 libffi-dev \
+    fonts-noto fonts-noto-cjk \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /code
+COPY requirements.txt .
+RUN pip install --no-cache-dir -U pip wheel && pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+ENV GRADIO_SERVER_NAME=0.0.0.0
+EXPOSE 7860
+CMD ["python", "app.py"]

Hugging Face/README.md

@@ -0,0 +1,17 @@
+# IR/ESG Report Generator (HF Space, LLM+Translation)
+
+CSV/YAML をアップロードして IR/ESG レポート（HTML/PDF/DOCX）を生成します。  
+LLM 要約＋翻訳に **OPENAI_API_KEY2** を使用します。
+
+## 入力例
+- company.yaml
+- financials.csv
+- esg_metrics.csv
+
+## 設定（必須）
+Hugging Face Space → **Settings → Variables and secrets**:
+- Name: `OPENAI_API_KEY2`
+- Value: `<your openai api key>`
+
+## 起動
+このリポジトリを Space にそのままアップロード（Docker Space）。自動ビルド後に起動します。

Hugging Face/app.py

@@ -0,0 +1,84 @@
+import gradio as gr
+from pathlib import Path
+import tempfile,datetime, json
+from core import generate_report
+import shutil
+
+TITLE = "IR/ESG Report Generator(Hugging Face Space)"
+DESC = ""
+CSV/YAMLをアップロードしてIR/ESGレポート（HTML/PDF/DOCX）を生成します。
+""
+
+def run(company_yaml,financials_csv,esg_csv,use_llm,lang):
+    if company_yamal is None or financials_csv is None or esg_csv is None:
+        return "すべてのファイルをアップロードしてください。"None,None,None,None
+
+    with tempfile.TemporaryDirectory() as td:
+        cpath = Path(td)/"company_yaml";cpath.write_bytes(company_yaml.read())
+        fpath = Path(td)/"financials_csv";fpath.write_bytes(financials_csv.read())
+        epath = Path(td)/"esg_csv";epath.write_bytes(esg_csv.read())
+
+        outdir = Path(td)/"out"
+        outdir.mkdir(parents=True, exist_ok=True)
+
+        llm=None
+        if use_llm:
+            try:
+                from llm import OpenAILLM
+                llm = OpenAILLM()
+            except Exception as e:
+                return f"LLM初期化エラー: {e}",None,None,None
+
+        html,pdf,docx,meta_json = generate_report(
+            company_yamal=str(cpath),
+            financials_csv=str(fpath),
+            esg_csv=str(epath),
+            templates_dir="templates",
+            template_name="report.html.j2",
+            out_html=str(outdir/"report.html")
+            out_pdf=str(outdir/"report.html")
+            lang=lang,
+            llm=llm
+        )
+        repo_tmp=Path("./tmp")
+        repo_tmp.mkdir(exit_ok=True)
+        ts = detatime.datetime.now().strftime("%Ym%d-%H%M%S")
+        html_out=repo_tmp/f"report-{ts}.html"
+        pdf_out=repo_tmp/f"report-{ts}.pdf"
+        docx_out=repo_tmp/f"report-{ts}.docx"
+        meta_out=repo_tmp/f"report-{ts}.json"
+        shutil.copy(html,html_out)
+        shutil.copy(pdf,pdf_out)
+        shutil.copy(docx,docx_out)
+        Path(meta_out).write_text(json.dumps(meta_json,ensure_ascii=False,indent=2),encoding="utf-8")
+
+        return"生成が完了しました。",str(html_out),str(pdf_out),str(docx_out),str(meta_out)
+    
+with gr.Blocks(title=TITLE) as demo:
+    gr.Markdown(f"#{TITLE}\n{DESC}")
+
+    with gr.Row():
+        company_yaml=gr.File(label="company.yaml(会社情報・年度等)",file_types=[".yaml",".yml"])
+        financials_csv=gr.File(label="financials.csv(財務KPI)",file_types=[".csv"])
+        esg_csv=gr.File(label="esg_metrics.csv(ESG指標)",file_types=[".csv"])
+
+    with gr.Row():
+        use_llm=gr.Chheckbox(label="LLMで要約/翻訳を行う(OPENAI_API_KE2 必須)",value=True)
+        lang = gr.Dropdown(choices=["ja","en","zh","ko","de","fr"],value="ja",label="出力言語")
+
+        run_btn=gr.Button("レポート生成")
+
+        status =gr.Textbox(label="ステータス",interactive=False)
+        html_file=gr.File(label="HTMLダウンロード")
+        pdf_file=gr.File(label="PDFダウンロード")
+        docx_file=gr.File(label="DOCXダウンロード")
+        meta_file=gr.File(label="メタ情報(JSON)")
+
+        run_btn.click(
+            fu=run
+            inputs=[company_yamal,finanxials_csv,esg_csv,use_llm,lang],
+            outputs=[status,html_file,pdf_file,docx_file,meta_file]
+        )
+
+if__name__=="__main__":
+    demo.launch()

Hugging Face/core.py

@@ -0,0 +1,143 @@
+import panda as pd
+import yaml,detatime,hashilb,json
+from pathlib import Path
+from templating import get_env,rander
+from models import CompanyMeta,ReportSections,RenderPayload
+from render import hetml_to_pdf,html_to_docx
+
+DISPLAY_NAME={
+    "co2_emission":"Co2排出量",
+    "energy_renewable_ratio":"再生可能エネルギー比率",
+    "female_management_ratio":"女性管理職比率"
+}
+
+def sha256(p:Path)->str:
+   h=hashlib.sha256()
+   with p.open("rb") as f:
+       for chunk in iter(lambda: f.read(8192), b""):
+           h.update(chunk)
+   return h.hexdigest()
+
+def load_company_meta(path:str)->CompanyMeta:
+    data=yaml.safe_load(Path(path).read_text(encoding="utf-8"))
+    return CompanyMeta(**data)
+
+def load_financials(path:str)->pd.DataFrame:
+    return pd.read_csv(path)
+
+def compute_kpi(fin_df:pd.DataFrame,fiscal_year:int):
+    latest=fin_df[fin_df["year"]==fiscal_year].sort_values("quarter").tail(1)
+    prev=fin_df[fin_df["year"]==fiscal_year-1].sort_values("quarter").tail(1)
+
+    revenue=float(latest["revenue"].iloc[0])
+    prev_revenue=float(prev["revenue"].iloc[0]) if not prev.empty else 0
+    ebit=float(latest["ebit"].iloc[0]) if not latest.empty else 0
+    net_income=float(latest["net_income"].iloc[0]) if not latest.empty else 0
+    equity=float(latest["equity"].iloc[0]) if not latest.empty else 0.0
+    ebit_margin=ebit /revenue *100 if revenue else 0.0
+    revenue_yoy=((revenue/float(prev["revenue"].iloc[0]))-1)*100 if not prev.empty and float(prev["revenue"].iloc[0]) else 0.0
+
+    return {
+        "revenue": revenue,
+        "ebit": ebit,
+        "ebit_margin": ebit_margin,
+        "net_income": net_income,
+        "equity": equity,
+        "revenue_yoy": revenue_yoy
+    }
+
+def esg_table (df:pd.DataFrame,fiscal_year:int):
+    dfy=df[df["year"]==fiscal_year].copy
+    rows=[]
+    for _, r in dfy.iterrows():
+        display = DISPLAY_NAME.get(r["metric"], r["metric"])
+        rows.append({
+            "display": display,
+            "value": r["value"],
+            "unit": r.get("unit", ""),
+            "notes": r.get("notes", ""),
+        })
+
+    return rows
+def build_sections(meta:CompanyMeta,kpi:dict,esg_rows:list,llm=None)->ReportSections:
+    if llm:
+        ceo_message = llm.generate_ceo_message(meta.kpi,esg_rows)
+        risk = llm.generate_risk_opportunities(meta.kpi,esg_rows)
+    else:
+        ceo_message = f"[{meta.fiscal_year}]期は、売上成長と収益性の両立に注力しました。"
+        risk = "主要リスクはマクロ環境と規制動向。機会は生成AI活用と脱炭素需要の拡大です。"
+    return ReportSections(ceo_message=ceo_message,risk_opportunity=risk)
+
+def_translate_payload(payload:dict,lang:str,llm)->dict:
+    """payload のうち、テキスト項目をtarget langに翻訳。数値は非対象。"""
+　　 if not llm or lang =="ja":
+         return payload
+
+    texts=[]
+
+    texts.append(payload["section"]["ceo_message"])
+    texts.append(payload["section"]["risk_opportunity"])
+
+    for row in payload["esg_table"]:
+        texts.append(row["display"])
+        texts.append(row["notes"] or "")
+
+    texts.append(payload["meta"]["report_title"])
+    for topic in payload["meta"].get("material_topics", []):
+        texts.append(topic)
+
+    translated = llm.translate_text(texts, target_lang=lang)
+    it = iter(translated)
+
+   payload["section"]["ceo_message"] = next(it)
+   payload["section"]["risk_opportunity"] = next(it)
+
+    for row in payload["esg_table"]:
+        row["display"] = next(it)
+        row["notes"] = next(it)
+
+    payload["meta"]["report_title"] = next(it)
+    mt = payload["meta"].get("material_topics", [])
+    for i  in range(len(mt)):
+        mt[i] = next(it)
+
+    return payload
+
+def generate_report(company_yaml,financials_csv,esg_csv,
+                    template_dir,template_name="report.html.j2",
+                    out_html="output/report.html",out_pdf="output/report.pdf",
+                    out_docx="output/report.docx",lang="ja",llm=None):
+    Path(Path(out_html).parent).mkdir(parents=True, exist_ok=True)
+    meta= load_company_meta(company_yaml)
+    fin= load_financials(financials_csv)
+    esg= load_esg(esg_csv)
+
+    kpi = compute_kpi(fin, meta.fiscal_year)
+    esg_rows = esg_table(esg, meta.fiscal_year)
+    sections = build_sections(meta, kpi, esg_rows, llm=llm)
+
+    env = get_env(template_dir)
+    payload = RenderPayload(
+        meta=meta, kpi=kpi, esg_table=esg_rows,kpi=kpi, sections=sections,
+        generated_at=datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),lang=lang
+    ).model__dump()
+
+    payload= _translate_payload_texts(payload, lang=lang, llm=llm)
+
+    html = render(env, template_name, payload)
+    Path(out_html).write_text(html, encoding="utf-8")
+    html_to_pdf(html, out_pdf)
+    html_to_docx(html, out_docx)
+
+    meta_json ={
+        "inputs":{
+            "company_yaml_sha":_sha256(Path(company_yaml)),
+            "financials_csv_sha":_sha256(Path(financials_csv)),
+            "esg_csv_sha":_sha256(Path(esg_csv)),
+            "lang":lang
+        },
+        "outputs":{"html":out_html,"pdf":out_pdf,"docx":out_docx},
+        "template":{"dir":templates_dir,"name":template_name},
+        "generated_at":datetime.datetime.now().strftime("timespec=sedconds"),
+    }
+    return out_html,out_pdf,out_docx,meta_json

Hugging Face/hf.yaml

@@ -0,0 +1,6 @@
+title: IR-ESG-Report-Generator
+emoji: 📈
+colorFrom: gray
+colorTo: indigo
+sdk: docker
+pinned: false

Hugging Face/llm.py

@@ -0,0 +1,67 @@
+import os
+from typing import List, Dict, Any
+from openai import OpenAI
+
+class OpenAILLM:
+    def __init__(self,model_chat:str = "gpt-4o",model_translate:str = "gpt-4o", model_summarize:str = "gpt-4o"):
+        api_key = os.environ.get("OPENAI_API_KEY2")
+        if not api_key:
+            raise RuntimeError("OPENAI_API_KEY2 is not set in environment variables.")
+        self.client = OpenAI(api_key=api_key)
+        self.model_chat = model_chat
+        self.model_translate = model_translate
+        self.model_summarize = model_summarize
+
+    def generate_ceo_message(self,meta, kpi:Dict[str,float],esg_row:List[Dict[str,Any]])->str:
+        prompt = (
+            "以下の企業情報・KPI・ESG指標をもとに、日本語で200字程度のCEOメッセージ草案を出力してください。"
+            "投資家に伝わる簡潔なトーンで、過度な形容表現は避けてください。\n\n"
+            f"企業情報: {meta.model_dump()}\n"
+            f"KPI: {kpi}\n"
+            f"ESG指標: {esg_row}\n"
+        )
+        rsp = self.client.chat.completions.create(
+            model=self.model_chat,
+            messages=[{"role": "user", "content": prompt}],
+            temperature=0.3,
+        )
+        return rsp.choices[0].message.content.strip()
+
+    def generate_risk_opportunity(self,meta,kpi:Dict[str,float],esg_row:List[Dict[str,Any]])->str:
+        prompt = (
+            "以下の情報から、日本語で200字程度のリスクと機会の草案を出力してください。"
+            "定量/定性のバランスを取り、具体的な観点を1-2点挙げてください。\n\n"
+            f"企業情報: {meta.model_dump()}\n"
+            f"KPI: {kpi}\n"
+            f"ESG: {esg_row}\n"
+        )
+        rsp = self.client.chat.completions.create(
+            model=self.model_chat,
+            messages=[{"role": "user", "content": prompt}],
+            temperature=0.3,
+        )
+        return rsp.choices[0].message.content.strip()
+
+    def translate_text(self, texts:List[str], target_language: str) -> List[str]:
+        if not texts:
+            return texts
+        system=(
+            "You are precise financial/ESG translator.Preserve numbers,units,and proper nouns."
+            "Keep tone concise,suitable for investor reports."
+        )
+        SEP = "\n<<<SEP>>>\n"
+        joined = SEP.join(texts)
+        prompt = f"Translate the following content to {target_language}.Keep layout minimal.\n\n{joined}"
+        rsp = self.client.chat.completions.create(
+            model=self.model_translate,
+            messages=[
+                {"role": "user", "content": system},{"role": "user", "content": prompt}
+            ],
+            temperature=0.2,
+        )
+        out = rsp.choices[0].message.content
+        parts = [p.strip() for p in out.split("<<<SEP>>>")]
+        if len(parts) != len(texts):
+            parts = [out]+texts[1:]
+            parts = parts[:len(texts)]
+        return parts

Hugging Face/models.py

@@ -0,0 +1,24 @@
+from pydantic import BaseModel
+from typing import Lisr,Optional,Dict,Any
+
+class CompnayMeta(BaseModel):
+    company_name:str
+    fiscal_year:int
+    currency:str ="JPY"
+    ticker:Optional[str] = None
+    report_title:str ="Integrated Report"
+    ceo_name:Optional[str] = None
+    material_topics:List[str] = []
+    targets:Dict[str, Any] = {}
+
+class ReportSection(BaseModel):
+    ceo_message:str=""
+    risk_opportunity:str=""
+
+class ReportPayload(BaseModel):
+    meta:CompanyMeta
+    esg_table:List[Dict[str, Any]]
+    kpi:Dict[str, float]
+    sections:ReportSection
+    generated_at: str
+    lang:str="ja"

Hugging Face/render.py

@@ -0,0 +1,29 @@
+from weasyprint import HTML
+from docx import Document
+from docx.shared import Pt
+from bs4 import BeautifulSoup
+
+def html_to_pdf(html_str:str,out_pdf_path:str):
+    """
+    Convert HTML string to PDF file.
+    """
+    HTML(string=html_str).write_pdf(out_pdf_path)
+
+def html_to_docx(html_str:str,out_docx_path:str):
+    doc = Document()
+    soup = BeautifulSoup(html_str, 'html.parser')
+    for tag in soup.find_all(["h1","h2","h3","p","li"]):
+        txt=tag.get_text(strip=True)
+        if not txt:
+            continue
+        if tag.name =="h1":
+            p=doc.add_heading(txt,level=0)
+        elif tag.name =="h2":
+            p = doc.add_heading(txt,level=1)
+        elif tag.name =="h3":
+            p= doc.add_heading(txt,level=2)
+        else:
+            p=doc.add_paragraph(txt)
+        for run in p.runs:
+            run.font.size = Pt(11)
+    doc.save(out_docx_path)

Hugging Face/requirements.txt

@@ -0,0 +1,9 @@
+gradio==4.44.0
+pandas==2.2.2
+pydantic==2.7.4
+Jinja2==3.1.4
+python-docx==1.1.2
+WeasyPrint==62.3
+beautifulsoup4==4.12.3
+PyYAML==6.0.2
+openai==1.40.2

Hugging Face/templates:report.html.j2

@@ -0,0 +1,74 @@
+<!doctype html>
+<html lang="{{ lang }}">
+<head>
+  <meta charset="utf-8" />
+  <title>{{ meta.report_title }} - {{ meta.company_name }}</title>
+  <style>
+    body { font-family: system-ui, -apple-system, "Segoe UI", Helvetica, Arial; line-height: 1.6; }
+    h1,h2,h3 { margin: 0.6em 0; }
+    .kpi { display: grid; grid-template-columns: repeat(3, 1fr); gap: 12px; }
+    .card { border: 1px solid #ddd; border-radius: 12px; padding: 12px; }
+    .small { color: #666; font-size: 0.9em; }
+    table { border-collapse: collapse; width: 100%; }
+    th, td { border: 1px solid #eee; padding: 8px; text-align: right; }
+    th { background: #fafafa; }
+    .left { text-align: left; }
+  </style>
+</head>
+<body>
+  <h1>{{ meta.report_title }}（{{ meta.fiscal_year }}）</h1>
+  <p class="small">{{ meta.company_name }} / Ticker: {{ meta.ticker }} / 通貨: {{ meta.currency }}</p>
+
+  <h2>CEOメッセージ</h2>
+  <p>{{ sections.ceo_message }}</p>
+
+  <h2>ハイライトKPI</h2>
+  <div class="kpi">
+    <div class="card">
+      <div class="small">売上高</div>
+      <div><strong>{{ kpi.revenue | round(0) | int }} {{ meta.currency }}</strong></div>
+      <div class="small">前年比: {{ kpi.revenue_yoy | round(1) }}%</div>
+    </div>
+    <div class="card">
+      <div class="small">EBIT</div>
+      <div><strong>{{ kpi.ebit | round(0) | int }} {{ meta.currency }}</strong></div>
+      <div class="small">マージン: {{ kpi.ebit_margin | round(1) }}%</div>
+    </div>
+    <div class="card">
+      <div class="small">純利益</div>
+      <div><strong>{{ kpi.net_income | round(0) | int }} {{ meta.currency }}</strong></div>
+      <div class="small">ROE: {{ kpi.roe | round(1) }}%</div>
+    </div>
+  </div>
+
+  <h2>ESGサマリー</h2>
+  <table>
+    <thead>
+      <tr><th class="left">指標</th><th>値</th><th>単位</th><th class="left">備考</th></tr>
+    </thead>
+    <tbody>
+      {% for row in esg_table %}
+      <tr>
+        <td class="left">{{ row.display }}</td>
+        <td>{{ row.value }}</td>
+        <td>{{ row.unit }}</td>
+        <td class="left">{{ row.notes }}</td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+
+  <h2>マテリアリティ & ターゲット</h2>
+  <ul>
+  {% for topic in meta.material_topics %}
+    <li>{{ topic }}</li>
+  {% endfor %}
+  </ul>
+  <p class="small">CO₂削減目標: {{ meta.targets.co2_reduction_pct }}% / 女性管理職比率: {{ meta.targets.female_management_ratio }}% / 再エネ比率: {{ meta.targets.renewable_energy_ratio }}%</p>
+
+  <h2>リスク & 機会（要約）</h2>
+  <p>{{ sections.risk_opportunity }}</p>
+
+  <footer class="small">Generated on {{ generated_at }}</footer>
+</body>
+</html>

Hugging Face/templating.py

@@ -0,0 +1,12 @@
+from jinja2 import Environment, FileSystemLoader, select_autoescape
+
+def get_env(templates_dir: str):
+    env = Environment(
+        loader=FileSystemLoader(templates_dir),
+        autoescape=select_autoescape(["html", "xml"])
+    )
+    return env
+
+def render(env, template_name: str, context: dict) -> str:
+    template = env.get_template(template_name)
+    return template.render(**context)