Spaces:
Sleeping
Sleeping
Ammar-Abdelhady-ai
commited on
Commit
•
b244901
1
Parent(s):
fa09cc6
main.py
CHANGED
@@ -10,25 +10,6 @@ from transformers import pipeline
|
|
10 |
|
11 |
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
12 |
print("\n\n definition 2")
|
13 |
-
def fit_threads(text):
|
14 |
-
define.join()
|
15 |
-
|
16 |
-
######## Handel Sumarization model
|
17 |
-
|
18 |
-
a = threading.Thread(target=summarization, args=(text[0],))
|
19 |
-
b = threading.Thread(target=summarization, args=(text[1],))
|
20 |
-
c = threading.Thread(target=summarization, args=(text[-1],))
|
21 |
-
|
22 |
-
# Start all threads
|
23 |
-
a.start()
|
24 |
-
b.start()
|
25 |
-
c.start()
|
26 |
-
|
27 |
-
# Wait for all threads to finish
|
28 |
-
a.join()
|
29 |
-
b.join()
|
30 |
-
c.join()
|
31 |
-
print("Summarization Done")
|
32 |
|
33 |
|
34 |
|
@@ -47,10 +28,7 @@ df_vect = vectorizer.transform(x)
|
|
47 |
######### using summarizer model
|
48 |
summ_data = []
|
49 |
|
50 |
-
|
51 |
-
global summ_data
|
52 |
-
part = summarizer(text, max_length=150, min_length=30, do_sample=False)
|
53 |
-
summ_data.append(part[0]["summary_text"].replace("\xa0", ""))
|
54 |
|
55 |
print("start api code")
|
56 |
app = FastAPI(project_name="cv")
|
@@ -61,6 +39,7 @@ async def read_root():
|
|
61 |
|
62 |
@app.post("/prediction")
|
63 |
async def detect(cv: UploadFile, number_of_jobs: int):
|
|
|
64 |
|
65 |
if (type(number_of_jobs) != int) or (number_of_jobs < 1) or (number_of_jobs > df.shape[0]):
|
66 |
raise HTTPException(
|
@@ -72,13 +51,16 @@ async def detect(cv: UploadFile, number_of_jobs: int):
|
|
72 |
status_code=415, detail="Please inter PDF file "
|
73 |
)
|
74 |
|
75 |
-
|
76 |
-
|
|
|
77 |
cv_data = extract_text_from_pdf(await cv.read())
|
78 |
index = len(cv_data)//3
|
79 |
text = [cv_data[:index], cv_data[index:2*index], cv_data[2*index:]]
|
80 |
-
|
81 |
-
|
|
|
|
|
82 |
data = " .".join(summ_data)
|
83 |
summ_data.clear()
|
84 |
cv_vect = vectorizer.transform([data])
|
|
|
10 |
|
11 |
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
|
12 |
print("\n\n definition 2")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
|
15 |
|
|
|
28 |
######### using summarizer model
|
29 |
summ_data = []
|
30 |
|
31 |
+
|
|
|
|
|
|
|
32 |
|
33 |
print("start api code")
|
34 |
app = FastAPI(project_name="cv")
|
|
|
39 |
|
40 |
@app.post("/prediction")
|
41 |
async def detect(cv: UploadFile, number_of_jobs: int):
|
42 |
+
print("pf")
|
43 |
|
44 |
if (type(number_of_jobs) != int) or (number_of_jobs < 1) or (number_of_jobs > df.shape[0]):
|
45 |
raise HTTPException(
|
|
|
51 |
status_code=415, detail="Please inter PDF file "
|
52 |
)
|
53 |
|
54 |
+
print("pf2")
|
55 |
+
|
56 |
+
summ_data =[]
|
57 |
cv_data = extract_text_from_pdf(await cv.read())
|
58 |
index = len(cv_data)//3
|
59 |
text = [cv_data[:index], cv_data[index:2*index], cv_data[2*index:]]
|
60 |
+
for i in text:
|
61 |
+
part = summarizer(i, max_length=150, min_length=30, do_sample=False)
|
62 |
+
summ_data.append(part[0]["summary_text"].replace("\xa0", ""))
|
63 |
+
print("pf3")
|
64 |
data = " .".join(summ_data)
|
65 |
summ_data.clear()
|
66 |
cv_vect = vectorizer.transform([data])
|