Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,8 +1,16 @@
|
|
|
|
|
| 1 |
from fastapi import FastAPI
|
| 2 |
from pydantic import BaseModel
|
| 3 |
from transformers import pipeline
|
| 4 |
|
| 5 |
-
# ✅
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
question_extractor = pipeline("text-classification", model="textattack/bert-base-uncased-MRPC")
|
| 7 |
|
| 8 |
app = FastAPI()
|
|
@@ -14,11 +22,11 @@ class OCRText(BaseModel):
|
|
| 14 |
def extract_question(data: OCRText):
|
| 15 |
text = data.text
|
| 16 |
lines = text.split("\n")
|
| 17 |
-
|
|
|
|
| 18 |
ranked_lines = sorted(lines, key=lambda line: question_extractor(line)[0]['score'], reverse=True)
|
| 19 |
top_sentences = [line for line in ranked_lines[:3] if len(line) > 10]
|
| 20 |
-
|
| 21 |
question_text = " ".join(top_sentences)
|
| 22 |
-
|
| 23 |
-
return {"extracted_question": question_text}
|
| 24 |
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
from fastapi import FastAPI
|
| 3 |
from pydantic import BaseModel
|
| 4 |
from transformers import pipeline
|
| 5 |
|
| 6 |
+
# ✅ Step 1: Set a Custom Cache Directory (Writable)
|
| 7 |
+
os.environ["TRANSFORMERS_CACHE"] = "/app/cache"
|
| 8 |
+
os.environ["HF_HOME"] = "/app/cache"
|
| 9 |
+
|
| 10 |
+
# ✅ Step 2: Ensure Cache Directory Exists
|
| 11 |
+
os.makedirs("/app/cache", exist_ok=True)
|
| 12 |
+
|
| 13 |
+
# ✅ Step 3: Load Model from Hugging Face
|
| 14 |
question_extractor = pipeline("text-classification", model="textattack/bert-base-uncased-MRPC")
|
| 15 |
|
| 16 |
app = FastAPI()
|
|
|
|
| 22 |
def extract_question(data: OCRText):
|
| 23 |
text = data.text
|
| 24 |
lines = text.split("\n")
|
| 25 |
+
|
| 26 |
+
# Use AI Model to Identify Question Parts
|
| 27 |
ranked_lines = sorted(lines, key=lambda line: question_extractor(line)[0]['score'], reverse=True)
|
| 28 |
top_sentences = [line for line in ranked_lines[:3] if len(line) > 10]
|
| 29 |
+
|
| 30 |
question_text = " ".join(top_sentences)
|
|
|
|
|
|
|
| 31 |
|
| 32 |
+
return {"extracted_question": question_text}
|