pdf extractor corrected

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies for pdf extraction if needed
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

routers/extraction.py

@@ -1,24 +1,20 @@
-from fastapi import APIRouter, HTTPException
-from pydantic import BaseModel
-from services.pdf_extractor import extract_resume_from_path
+import io
+from fastapi import APIRouter, HTTPException, File, UploadFile
+from services.pdf_extractor import extract_resume_from_stream
 
 router = APIRouter(prefix="/extract-resume", tags=["extraction"])
 
 
-class ExtractRequest(BaseModel):
-    file_path: str
-
-
 @router.post("")
-def extract_resume(request: ExtractRequest):
+async def extract_resume(file: UploadFile = File(...)):
     """
-    Receives the absolute path of an uploaded PDF (written by NestJS),
-    extracts and structures its text, and returns it to NestJS.
+    Receives an uploaded PDF file stream, extracts and structures its text,
+    and returns it to NestJS.
     """
     try:
-        result = extract_resume_from_path(request.file_path)
+        content = await file.read()
+        pdf_stream = io.BytesIO(content)
+        result = extract_resume_from_stream(pdf_stream)
         return result
-    except FileNotFoundError:
-        raise HTTPException(status_code=404, detail="File not found at provided path.")
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Extraction failed: {str(e)}")

services/pdf_extractor.py

@@ -14,9 +14,9 @@ SECTION_KEYWORDS = {
 }
 
 
-def extract_resume_from_path(file_path: str) -> dict:
+def extract_resume_from_stream(stream) -> dict:
     """
-    Opens a PDF with pdfplumber, extracts text page by page,
+    Opens a PDF with pdfplumber from a stream, extracts text page by page,
     detects basic metadata, and identifies resume sections.
     """
     text_pages = []
@@ -24,7 +24,7 @@ def extract_resume_from_path(file_path: str) -> dict:
     has_images = False
     page_count = 0
 
-    with pdfplumber.open(file_path) as pdf:
+    with pdfplumber.open(stream) as pdf:
         page_count = len(pdf.pages)
 
         for page in pdf.pages: