Update app.py

app.py

@@ -1,18 +1,19 @@
-from flask import Flask, request, jsonify
+from fastapi import FastAPI, File, Form, UploadFile
+from pydantic import BaseModel
 import docx
 import fitz  # PyMuPDF for PDF extraction
 from transformers import AutoTokenizer, AutoModel
 import torch
-import os
+import io
 
-app = Flask(__name__)
+app = FastAPI()
 
 # Load the Hugging Face tokenizer and model for semantic textual similarity
 tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
 model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
 
 # Function to extract text from PDF
-def extract_text_from_pdf(pdf_path):
+def extract_text_from_pdf(pdf_path: io.BytesIO):
     doc = fitz.open(pdf_path)
     text = ""
     for page in doc:
@@ -20,7 +21,7 @@ def extract_text_from_pdf(pdf_path):
     return text
 
 # Function to extract text from DOCX
-def extract_text_from_docx(docx_path):
+def extract_text_from_docx(docx_path: io.BytesIO):
     doc = docx.Document(docx_path)
     text = ""
     for para in doc.paragraphs:
@@ -36,28 +37,22 @@ def get_similarity_score(text1, text2):
     similarity_score = torch.nn.functional.cosine_similarity(sentence_embeddings[0], sentence_embeddings[1], dim=0)
     return similarity_score.item()
 
-# API endpoint to process the resume and calculate similarity with LIC profile
-@app.route('/score_resume', methods=['POST'])
-def score_resume():
-    if 'file' not in request.files:
-        return jsonify({"error": "No file part"}), 400
-    file = request.files['file']
-    lic_profile = request.form.get('lic_profile', '')  # LIC profile text to compare against
-    
+# FastAPI endpoint to process the resume and calculate similarity with LIC profile
+@app.post("/score_resume/")
+async def score_resume(file: UploadFile = File(...), lic_profile: str = Form(...)):
+    file_content = await file.read()
+
     if file.filename.endswith('.pdf'):
-        resume_text = extract_text_from_pdf(file)
+        resume_text = extract_text_from_pdf(io.BytesIO(file_content))
     elif file.filename.endswith('.docx'):
-        resume_text = extract_text_from_docx(file)
+        resume_text = extract_text_from_docx(io.BytesIO(file_content))
     else:
-        return jsonify({"error": "Invalid file type. Please upload a PDF or DOCX file."}), 400
+        return {"error": "Invalid file type. Please upload a PDF or DOCX file."}
 
     if not lic_profile:
-        return jsonify({"error": "LIC profile text is required."}), 400
+        return {"error": "LIC profile text is required."}
     
     # Calculate the similarity score between resume and LIC profile
     score = get_similarity_score(resume_text, lic_profile)
     
-    return jsonify({"similarity_score": score})
-
-if __name__ == '__main__':
-    app.run(debug=True)
+    return {"similarity_score": score}