feat: OpenRouter 외부 AI 연동 (STT 교정 + OCR Vision)

app/ocr_tasks.py

@@ -1,9 +1,8 @@
 """
-OCR Celery Tasks — PaddleOCR 3.x + Ollama Vision
+OCR Celery Tasks
+backend: paddle | ollama | openrouter
 """
-import os
-import base64
-
+import os, base64
 import httpx
 from celery import Celery
 import openpyxl
@@ -17,11 +16,8 @@ OLLAMA_TIMEOUT = int(os.getenv("OLLAMA_TIMEOUT", "600"))
 
 celery_app = Celery("ocr_tasks", broker=REDIS_URL, backend=REDIS_URL)
 celery_app.conf.update(
-    task_serializer="json",
-    result_serializer="json",
-    accept_content=["json"],
-    task_track_started=True,
-    result_expires=3600,
+    task_serializer="json", result_serializer="json",
+    accept_content=["json"], task_track_started=True, result_expires=3600,
 )
 
 _ocr_engine    = None
@@ -46,12 +42,28 @@ def get_structure():
     return _struct_engine
 
 
+# ════════════════════════════════════════════════════════════════
+#  메인 Task
+# ════════════════════════════════════════════════════════════════
 @celery_app.task(bind=True, name="tasks.ocr_task", queue="ocr")
-def ocr_task(self, file_id, image_path, mode="text",
-             backend="paddle", ollama_model="granite3.2-vision", custom_prompt=""):
-    self.update_state(state="PROGRESS", meta={"progress": 8, "message": "엔진 준비 중..."})
+def ocr_task(
+    self,
+    file_id:          str,
+    image_path:       str,
+    mode:             str  = "text",
+    backend:          str  = "paddle",
+    ollama_model:     str  = "granite3.2-vision",
+    openrouter_model: str  = "",
+    openrouter_url:   str  = "",
+    openrouter_key:   str  = "",
+    custom_prompt:    str  = "",
+):
+    self.update_state(state="PROGRESS", meta={"progress":8,"message":"엔진 준비 중..."})
     try:
-        if backend == "ollama":
+        if backend == "openrouter":
+            result = _run_openrouter(self, file_id, image_path, mode,
+                                     openrouter_model, openrouter_url, openrouter_key, custom_prompt)
+        elif backend == "ollama":
             result = _run_ollama(self, file_id, image_path, mode, ollama_model, custom_prompt)
         else:
             result = _run_paddle(self, file_id, image_path, mode)
@@ -64,34 +76,124 @@ def ocr_task(self, file_id, image_path, mode="text",
         raise Exception(f"OCR 실패: {str(e)}")
 
 
-_OLLAMA_PROMPTS = {
+# ════════════════════════════════════════════════════════════════
+#  OpenRouter Vision 백엔드 (OpenAI 호환)
+# ════════════════════════════════════════════════════════════════
+_PROMPTS = {
     "text":      "이 이미지에서 모든 텍스트를 정확하게 추출해줘. 원본의 줄 구분과 단락 구조를 유지해줘.",
     "structure": "이 이미지를 분석해서 표는 마크다운 표 형식으로, 나머지 텍스트는 원본 구조를 유지하며 추출해줘.",
 }
 
+def _run_openrouter(task, file_id, image_path, mode,
+                    model, base_url, api_key, custom_prompt):
+    if not api_key:
+        raise Exception("OpenRouter API 키가 설정되지 않았습니다")
+    if not model:
+        raise Exception("OpenRouter 모델이 선택되지 않았습니다")
+
+    task.update_state(state="PROGRESS",
+                      meta={"progress":15,"message":f"OpenRouter ({model}) 연결 중..."})
+
+    with open(image_path, "rb") as f:
+        raw = f.read()
+
+    # 이미지 MIME 타입 감지
+    ext = image_path.rsplit(".", 1)[-1].lower()
+    mime = {"jpg":"image/jpeg","jpeg":"image/jpeg","png":"image/png",
+            "bmp":"image/bmp","gif":"image/gif","webp":"image/webp"}.get(ext, "image/jpeg")
+    b64 = base64.b64encode(raw).decode()
+    data_url = f"data:{mime};base64,{b64}"
+
+    prompt = custom_prompt.strip() or _PROMPTS.get(mode, _PROMPTS["text"])
+
+    task.update_state(state="PROGRESS", meta={"progress":30,"message":"모델 추론 중..."})
+
+    try:
+        resp = httpx.post(
+            f"{base_url.rstrip('/')}/chat/completions",
+            headers={
+                "Authorization": f"Bearer {api_key}",
+                "HTTP-Referer":  "https://voicescript.local",
+                "X-Title":       "VoiceScript",
+                "Content-Type":  "application/json",
+            },
+            json={
+                "model": model,
+                "messages": [{
+                    "role": "user",
+                    "content": [
+                        {"type": "image_url", "image_url": {"url": data_url}},
+                        {"type": "text",      "text": prompt},
+                    ],
+                }],
+                "temperature": 0.1,
+            },
+            timeout=float(OLLAMA_TIMEOUT),
+        )
+        resp.raise_for_status()
+    except httpx.HTTPStatusError as e:
+        body = ""
+        try: body = e.response.json().get("error",{}).get("message","")
+        except: pass
+        if e.response.status_code == 400:
+            raise Exception(f"이 모델은 이미지를 지원하지 않습니다 — Vision 모델을 선택하세요\n({model})")
+        raise Exception(f"OpenRouter 오류 ({e.response.status_code}): {body or str(e)}")
+    except httpx.TimeoutException:
+        raise Exception(f"OpenRouter 응답 시간 초과. OLLAMA_TIMEOUT 값을 늘려주세요.")
+
+    task.update_state(state="PROGRESS", meta={"progress":85,"message":"결과 저장 중..."})
+
+    full_text = resp.json()["choices"][0]["message"]["content"].strip()
+    if not full_text:
+        raise Exception("OpenRouter 빈 응답")
+
+    tables = _parse_md_tables(full_text) if mode == "structure" else []
+    os.makedirs(OUTPUT_DIR, exist_ok=True)
+    txt_file = f"{file_id}_ocr.txt"
+    with open(os.path.join(OUTPUT_DIR, txt_file), "w", encoding="utf-8") as f:
+        f.write(f"# OCR 결과 (OpenRouter / {model})\n\n{full_text}")
+    xlsx_file = None
+    if tables:
+        xlsx_file = f"{file_id}_tables.xlsx"
+        _save_excel(tables, os.path.join(OUTPUT_DIR, xlsx_file))
+    tables_html = [_md_table_to_html(t) for t in tables]
+    lines = [{"text":l,"confidence":1.0,"bbox":[]} for l in full_text.splitlines() if l.strip()]
+    return {
+        "mode": mode, "backend": "openrouter", "openrouter_model": model,
+        "ollama_model": "",
+        "full_text": full_text, "lines": lines, "line_count": len(lines),
+        "txt_file": txt_file,
+        "tables": [{"html":h,"rows":len(t),"cols":max(len(r) for r in t) if t else 0}
+                   for h, t in zip(tables_html, tables)],
+        "xlsx_file": xlsx_file,
+    }
+
+
+# ════════════════════════════════════════════════════════════════
+#  Ollama Vision 백엔드
+# ════════════════════════════════════════════════════════════════
 def _run_ollama(task, file_id, image_path, mode, ollama_model, custom_prompt):
     task.update_state(state="PROGRESS",
-                      meta={"progress": 15, "message": f"Ollama ({ollama_model}) 연결 중..."})
+                      meta={"progress":15,"message":f"Ollama ({ollama_model}) 연결 중..."})
     with open(image_path, "rb") as f:
         img_b64 = base64.b64encode(f.read()).decode()
-    prompt = custom_prompt.strip() or _OLLAMA_PROMPTS.get(mode, _OLLAMA_PROMPTS["text"])
-    task.update_state(state="PROGRESS", meta={"progress": 30, "message": "모델 추론 중..."})
+    prompt = custom_prompt.strip() or _PROMPTS.get(mode, _PROMPTS["text"])
+    task.update_state(state="PROGRESS", meta={"progress":30,"message":"모델 추론 중..."})
     try:
         resp = httpx.post(f"{OLLAMA_URL}/api/chat", json={
             "model": ollama_model,
-            "messages": [{"role": "user", "content": prompt, "images": [img_b64]}],
-            "stream": False, "options": {"temperature": 0.1},
+            "messages": [{"role":"user","content":prompt,"images":[img_b64]}],
+            "stream": False, "options": {"temperature":0.1},
         }, timeout=float(OLLAMA_TIMEOUT))
         resp.raise_for_status()
     except httpx.ConnectError:
         raise Exception(f"Ollama 서버 연결 실패 ({OLLAMA_URL})")
     except httpx.TimeoutException:
-        raise Exception(f"Ollama 응답 시간 초과 ({OLLAMA_TIMEOUT}초). OLLAMA_TIMEOUT 값을 늘려주세요.")
+        raise Exception(f"Ollama 응답 시간 초과 ({OLLAMA_TIMEOUT}초)")
 
-    task.update_state(state="PROGRESS", meta={"progress": 85, "message": "결과 저장 중..."})
-    full_text = resp.json().get("message", {}).get("content", "").strip()
-    if not full_text:
-        raise Exception("Ollama 빈 응답. 모델이 설치되어 있는지 확인하세요.")
+    task.update_state(state="PROGRESS", meta={"progress":85,"message":"결과 저장 중..."})
+    full_text = resp.json().get("message",{}).get("content","").strip()
+    if not full_text: raise Exception("Ollama 빈 응답. 모델이 Vision을 지원하는지 확인하세요.")
 
     tables = _parse_md_tables(full_text) if mode == "structure" else []
     os.makedirs(OUTPUT_DIR, exist_ok=True)
@@ -103,74 +205,66 @@ def _run_ollama(task, file_id, image_path, mode, ollama_model, custom_prompt):
         xlsx_file = f"{file_id}_tables.xlsx"
         _save_excel(tables, os.path.join(OUTPUT_DIR, xlsx_file))
     tables_html = [_md_table_to_html(t) for t in tables]
-    lines = [{"text": l, "confidence": 1.0, "bbox": []}
-             for l in full_text.splitlines() if l.strip()]
+    lines = [{"text":l,"confidence":1.0,"bbox":[]} for l in full_text.splitlines() if l.strip()]
     return {
         "mode": mode, "backend": "ollama", "ollama_model": ollama_model,
+        "openrouter_model": "",
         "full_text": full_text, "lines": lines, "line_count": len(lines),
         "txt_file": txt_file,
-        "tables": [{"html": h, "rows": len(t), "cols": max(len(r) for r in t) if t else 0}
+        "tables": [{"html":h,"rows":len(t),"cols":max(len(r) for r in t) if t else 0}
                    for h, t in zip(tables_html, tables)],
         "xlsx_file": xlsx_file,
     }
 
 
+# ════════════════════════════════════════════════════════════════
+#  PaddleOCR 백엔드
+# ════════════════════════════════════════════════════════════════
 def _run_paddle(task, file_id, image_path, mode):
     import cv2
     img = cv2.imread(image_path)
-    if img is None:
-        raise ValueError("이미지를 읽을 수 없습니다")
+    if img is None: raise ValueError("이미지를 읽을 수 없습니다")
     os.makedirs(OUTPUT_DIR, exist_ok=True)
-    return _paddle_structure(task, file_id, img) if mode == "structure" \
-           else _paddle_text(task, file_id, img)
+    return _paddle_structure(task, file_id, img) if mode == "structure" else _paddle_text(task, file_id, img)
 
 def _paddle_text(task, file_id, img):
-    task.update_state(state="PROGRESS", meta={"progress": 30, "message": "텍스트 인식 중..."})
+    task.update_state(state="PROGRESS", meta={"progress":30,"message":"텍스트 인식 중..."})
     result = get_ocr().ocr(img)
-    task.update_state(state="PROGRESS", meta={"progress": 80, "message": "결과 정리 중..."})
+    task.update_state(state="PROGRESS", meta={"progress":80,"message":"결과 정리 중..."})
     lines = []
     if result and len(result) > 0:
         r = result[0]
         if isinstance(r, dict):
-            texts  = r.get("rec_texts", [])
-            scores = r.get("rec_scores", [])
-            for text, conf in zip(texts, scores):
-                if text.strip():
-                    lines.append({"text": text, "confidence": round(float(conf), 3), "bbox": []})
+            for text, conf in zip(r.get("rec_texts",[]), r.get("rec_scores",[])):
+                if text.strip(): lines.append({"text":text,"confidence":round(float(conf),3),"bbox":[]})
         elif isinstance(r, list):
             for item in r:
-                if item and len(item) == 2:
+                if item and len(item)==2:
                     _, (text, conf) = item
-                    if text.strip():
-                        lines.append({"text": text, "confidence": round(float(conf), 3), "bbox": []})
+                    if text.strip(): lines.append({"text":text,"confidence":round(float(conf),3),"bbox":[]})
     full_text = "\n".join(l["text"] for l in lines)
-    txt_file  = f"{file_id}_ocr.txt"
-    with open(os.path.join(OUTPUT_DIR, txt_file), "w", encoding="utf-8") as f:
-        f.write(full_text)
-    return {"mode": "text", "backend": "paddle", "ollama_model": "",
-            "full_text": full_text, "lines": lines,
-            "line_count": len(lines), "txt_file": txt_file,
-            "tables": [], "xlsx_file": None}
+    txt_file = f"{file_id}_ocr.txt"
+    with open(os.path.join(OUTPUT_DIR, txt_file), "w", encoding="utf-8") as f: f.write(full_text)
+    return {"mode":"text","backend":"paddle","ollama_model":"","openrouter_model":"",
+            "full_text":full_text,"lines":lines,"line_count":len(lines),
+            "txt_file":txt_file,"tables":[],"xlsx_file":None}
 
 def _paddle_structure(task, file_id, img):
-    task.update_state(state="PROGRESS", meta={"progress": 20, "message": "레이아웃 분석 중..."})
+    task.update_state(state="PROGRESS", meta={"progress":20,"message":"레이아웃 분석 중..."})
     result = get_structure()(img)
-    task.update_state(state="PROGRESS", meta={"progress": 60, "message": "표 구조 추출 중..."})
+    task.update_state(state="PROGRESS", meta={"progress":60,"message":"표 구조 추출 중..."})
     text_blocks, tables_html, tables_data = [], [], []
     for region in result:
-        rtype = region.get("type", "").lower()
+        rtype = region.get("type","").lower()
         if rtype == "table":
-            html = region.get("res", {}).get("html", "")
-            if html:
-                tables_html.append(html)
-                tables_data.append(_html_table_to_list(html))
-        elif rtype in ("text", "title", "figure_caption"):
-            for line in (region.get("res", []) or []):
-                if isinstance(line, (list, tuple)) and len(line) == 2:
-                    _, (text, _conf) = line
-                    text_blocks.append(text)
+            html = region.get("res",{}).get("html","")
+            if html: tables_html.append(html); tables_data.append(_html_table_to_list(html))
+        elif rtype in ("text","title","figure_caption"):
+            for line in (region.get("res",[]) or []):
+                if isinstance(line,(list,tuple)) and len(line)==2:
+                    _, (text, _conf) = line; text_blocks.append(text)
     full_text = "\n".join(text_blocks)
-    task.update_state(state="PROGRESS", meta={"progress": 80, "message": "Excel 생성 중..."})
+    task.update_state(state="PROGRESS", meta={"progress":80,"message":"Excel 생성 중..."})
     xlsx_file = None
     if tables_data:
         xlsx_file = f"{file_id}_tables.xlsx"
@@ -178,15 +272,17 @@ def _paddle_structure(task, file_id, img):
     txt_file = f"{file_id}_ocr.txt"
     with open(os.path.join(OUTPUT_DIR, txt_file), "w", encoding="utf-8") as f:
         f.write("# 텍스트\n\n" + full_text)
-    lines = [{"text": t, "confidence": 1.0, "bbox": []} for t in text_blocks]
-    tables_meta = [{"html": h, "rows": len(d), "cols": max(len(r) for r in d) if d else 0}
+    lines = [{"text":t,"confidence":1.0,"bbox":[]} for t in text_blocks]
+    tables_meta = [{"html":h,"rows":len(d),"cols":max(len(r) for r in d) if d else 0}
                    for h, d in zip(tables_html, tables_data)]
-    return {"mode": "structure", "backend": "paddle", "ollama_model": "",
-            "full_text": full_text, "lines": lines,
-            "line_count": len(lines), "txt_file": txt_file,
-            "tables": tables_meta, "xlsx_file": xlsx_file}
+    return {"mode":"structure","backend":"paddle","ollama_model":"","openrouter_model":"",
+            "full_text":full_text,"lines":lines,"line_count":len(lines),
+            "txt_file":txt_file,"tables":tables_meta,"xlsx_file":xlsx_file}
 
 
+# ════════════════════════════════════════════════════════════════
+#  공통 유틸
+# ════════════════════════════════════════════════════════════════
 def _parse_md_tables(text):
     tables, current = [], []
     for line in text.splitlines():
@@ -204,8 +300,8 @@ def _md_table_to_html(table):
     if not table: return ""
     rows = ""
     for i, row in enumerate(table):
-        tag = "th" if i == 0 else "td"
-        rows += "<tr>" + "".join(f"<{tag}>{c}</{tag}>" for c in row) + "</tr>"
+        tag = "th" if i==0 else "td"
+        rows += "<tr>"+"".join(f"<{tag}>{c}</{tag}>" for c in row)+"</tr>"
     return f"<table>{rows}</table>"
 
 def _html_table_to_list(html):
@@ -213,36 +309,31 @@ def _html_table_to_list(html):
     class P(HTMLParser):
         def __init__(self):
             super().__init__()
-            self.rows, self._row, self._cell, self._in = [], [], [], False
-        def handle_starttag(self, tag, attrs):
-            if tag == "tr": self._row = []
-            elif tag in ("td","th"): self._cell = []; self._in = True
-        def handle_endtag(self, tag):
-            if tag in ("td","th"): self._row.append("".join(self._cell).strip()); self._in = False
-            elif tag == "tr":
+            self.rows,self._row,self._cell,self._in=[],[],[],False
+        def handle_starttag(self,tag,attrs):
+            if tag=="tr": self._row=[]
+            elif tag in("td","th"): self._cell=[];self._in=True
+        def handle_endtag(self,tag):
+            if tag in("td","th"): self._row.append("".join(self._cell).strip());self._in=False
+            elif tag=="tr":
                 if self._row: self.rows.append(self._row)
-        def handle_data(self, data):
+        def handle_data(self,data):
             if self._in: self._cell.append(data)
-    p = P(); p.feed(html); return p.rows
+    p=P();p.feed(html);return p.rows
 
 def _save_excel(tables, path):
-    wb = openpyxl.Workbook(); wb.remove(wb.active)
-    for i, table in enumerate(tables, 1):
-        ws = wb.create_sheet(f"표 {i}")
-        thin = Side(style="thin", color="2A2A33")
-        bdr  = Border(left=thin, right=thin, top=thin, bottom=thin)
-        for r_idx, row in enumerate(table, 1):
-            for c_idx, val in enumerate(row, 1):
-                cell = ws.cell(row=r_idx, column=c_idx, value=val)
-                cell.border = bdr
-                cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=True)
-                if r_idx == 1:
-                    cell.fill = PatternFill("solid", fgColor="1A1A2E")
-                    cell.font = Font(color="00E5A0", bold=True, size=10)
-                else:
-                    cell.font = Font(size=10)
+    wb=openpyxl.Workbook();wb.remove(wb.active)
+    for i,table in enumerate(tables,1):
+        ws=wb.create_sheet(f"표 {i}")
+        thin=Side(style="thin",color="2A2A33");bdr=Border(left=thin,right=thin,top=thin,bottom=thin)
+        for r_idx,row in enumerate(table,1):
+            for c_idx,val in enumerate(row,1):
+                cell=ws.cell(row=r_idx,column=c_idx,value=val)
+                cell.border=bdr;cell.alignment=Alignment(horizontal="center",vertical="center",wrap_text=True)
+                if r_idx==1: cell.fill=PatternFill("solid",fgColor="1A1A2E");cell.font=Font(color="00E5A0",bold=True,size=10)
+                else: cell.font=Font(size=10)
         for col in ws.columns:
-            w = max((len(str(c.value or "")) for c in col), default=8)
-            ws.column_dimensions[col[0].column_letter].width = min(w + 4, 40)
+            w=max((len(str(c.value or "")) for c in col),default=8)
+            ws.column_dimensions[col[0].column_letter].width=min(w+4,40)
     if not wb.sheetnames: wb.create_sheet("Sheet1")
     wb.save(path)