Feature/setting

app/config.py

@@ -0,0 +1,12 @@
+from dotenv import load_dotenv
+import os
+
+INDEX_PATH = "data/faiss_index"
+UPLOAD_DIR = "data/uploads"
+
+os.makedirs(UPLOAD_DIR, exist_ok=True)
+os.makedirs(INDEX_PATH, exist_ok=True)
+
+load_dotenv()
+
+

app/main.py

@@ -0,0 +1,35 @@
+from dotenv import load_dotenv
+from fastapi import FastAPI, UploadFile, File, HTTPException
+from services.embedding_service import embed_pdf
+from services.task_service import generate_task
+import os
+
+
+load_dotenv()
+
+app = FastAPI()
+
+INDEX_PATH = "data/faiss_index"
+UPLOAD_DIR = "data/uploads"
+
+os.makedirs(UPLOAD_DIR, exist_ok=True)
+os.makedirs(INDEX_PATH, exist_ok=True)
+
+@app.post("/upload")
+async def upload_pdf(file: UploadFile = File(...)):
+    if not file.filename.endswith(".pdf"):
+        raise HTTPException(status_code=400, detail="PDF 파일만 업로드 가능합니다.")
+
+    file_path = os.path.join(UPLOAD_DIR, file.filename)
+
+    with open(file_path, "wb") as f:
+        content = await file.read()
+        f.write(content)
+
+    chunk_count = embed_pdf(file_path, INDEX_PATH)
+    return {"message": f"{chunk_count}개의 청크가 임베딩되어 저장되었습니다."}
+
+@app.get("/generate-task")
+async def get_task(prompt: str):
+    result = generate_task(prompt, INDEX_PATH)
+    return {"task": result}

app/routes.py

@@ -0,0 +1,35 @@
+from dotenv import load_dotenv
+from fastapi import APIRouter, UploadFile, File, HTTPException
+from services.embedding_service import embed_file
+from services.task_service import generate_task
+from app.config import UPLOAD_DIR, INDEX_PATH
+import os
+
+router = APIRouter()
+ALLOWED_EXTENSIONS = {".pdf", ".txt",".html", ".json", ".docx", ".xlsx", ".pptx"}
+
+@router.post("/upload")
+async def upload_file(file: UploadFile = File(...)):
+    ext = os.path.splitext(file.filename)[1].lower()
+    if ext not in ALLOWED_EXTENSIONS:
+        raise HTTPException(
+            status_code=400,
+            detail="지원하지 않는 파일 형식입니다. PDF, TXT, HTML, JSON, DOCX, XLSX, PPTX만 업로드 가능합니다."
+        )
+
+    os.makedirs(UPLOAD_DIR, exist_ok=True)
+    file_path = os.path.join(UPLOAD_DIR, file.filename)
+
+    with open(file_path, "wb") as f:
+        content = await file.read()
+        f.write(content)
+
+    # TODO: 확장자별 다른 임베딩 함수로 변경 가능
+    chunk_count = embed_file(file_path, INDEX_PATH)
+
+    return {"message": f"{chunk_count}개의 청크가 임베딩되어 저장되었습니다."}
+
+@router.get("/generate-task")
+async def get_task(prompt: str):
+    result = generate_task(prompt, INDEX_PATH)
+    return {"task": result}

main.py

@@ -1,35 +1,7 @@
-from dotenv import load_dotenv
-from fastapi import FastAPI, UploadFile, File, HTTPException
-from services.embedding_service import embed_pdf
-from services.task_service import generate_task
-import os
-
-
-load_dotenv()
+from fastapi import FastAPI
+from app.routes import router
 
 app = FastAPI()
+app.include_router(router)
 
-INDEX_PATH = "data/faiss_index"
-UPLOAD_DIR = "data/uploads"
-
-os.makedirs(UPLOAD_DIR, exist_ok=True)
-os.makedirs(INDEX_PATH, exist_ok=True)
-
-@app.post("/upload")
-async def upload_pdf(file: UploadFile = File(...)):
-    if not file.filename.endswith(".pdf"):
-        raise HTTPException(status_code=400, detail="PDF 파일만 업로드 가능합니다.")
-
-    file_path = os.path.join(UPLOAD_DIR, file.filename)
-
-    with open(file_path, "wb") as f:
-        content = await file.read()
-        f.write(content)
-
-    chunk_count = embed_pdf(file_path, INDEX_PATH)
-    return {"message": f"{chunk_count}개의 청크가 임베딩되어 저장되었습니다."}
-
-@app.get("/generate-task")
-async def get_task(prompt: str):
-    result = generate_task(prompt, INDEX_PATH)
-    return {"task": result}
+#uvicorn main:app --reload : 실행 명령어

services/embedding_service.py

@@ -1,17 +1,38 @@
-from langchain_community.document_loaders import PyPDFLoader
+from langchain.document_loaders import (
+    PyPDFLoader,
+    TextLoader,
+    UnstructuredHTMLLoader,
+    JSONLoader,
+    UnstructuredFileLoader,
+)
+
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
 
-def embed_pdf(file_path: str, index_path: str) -> int:
-    loader = PyPDFLoader(file_path)
+def embed_file(file_path: str, index_path: str) -> int:
+    ext = file_path.split(".")[-1].lower()
+
+    if ext == "pdf":
+        loader = PyPDFLoader(file_path)
+    elif ext == "txt":
+        loader = TextLoader(file_path)
+    elif ext == "html":
+        loader = UnstructuredHTMLLoader(file_path)
+    elif ext == "json":
+        loader = JSONLoader(file_path)
+    elif ext in ["docx", "xlsx", "pptx"]:
+        loader = UnstructuredFileLoader(file_path)
+    else:
+        raise ValueError(f"지원하지 않는 파일 형식입니다: {ext}")
+
     docs = loader.load()
 
     splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     chunks = splitter.split_documents(docs)
 
     embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
     vectorstore = FAISS.from_documents(chunks, embeddings)
-
     vectorstore.save_local(index_path)
+
     return len(chunks)