Spaces:
Sleeping
Sleeping
Commit ·
6901ae8
1
Parent(s): 41c5772
Upload folder using huggingface_hub
Browse files- README.md +3 -9
- gradio_chatwithpdf.py +53 -0
README.md
CHANGED
|
@@ -1,12 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
|
| 4 |
-
colorFrom: pink
|
| 5 |
-
colorTo: pink
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
-
app_file: app.py
|
| 9 |
-
pinned: false
|
| 10 |
---
|
| 11 |
-
|
| 12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Ask_PDF
|
| 3 |
+
app_file: gradio_chatwithpdf.py
|
|
|
|
|
|
|
| 4 |
sdk: gradio
|
| 5 |
+
sdk_version: 3.44.4
|
|
|
|
|
|
|
| 6 |
---
|
|
|
|
|
|
gradio_chatwithpdf.py
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
from openai import OpenAI
|
| 3 |
+
import gradio
|
| 4 |
+
import shutil
|
| 5 |
+
import pdfplumber
|
| 6 |
+
import os
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
def read_PDF(pdf_path):
|
| 10 |
+
pdf_text = ""
|
| 11 |
+
with pdfplumber.open(pdf_path) as pdf:
|
| 12 |
+
for page in pdf.pages:
|
| 13 |
+
pdf_text += page.extract_text()
|
| 14 |
+
return pdf_text
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
def read_PDF_2(fileobj):
|
| 18 |
+
pdf_text = ""
|
| 19 |
+
|
| 20 |
+
path = "./" + os.path.basename(fileobj.name)
|
| 21 |
+
shutil.copyfile(fileobj.name, path)
|
| 22 |
+
|
| 23 |
+
with pdfplumber.open(path) as pdf:
|
| 24 |
+
for page in pdf.pages:
|
| 25 |
+
pdf_text += page.extract_text()
|
| 26 |
+
|
| 27 |
+
return pdf_text
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
def askPDF(upload_PDF, prompt):
|
| 31 |
+
client = OpenAI()
|
| 32 |
+
|
| 33 |
+
pdf_text = read_PDF_2(upload_PDF)
|
| 34 |
+
systemMessage = '"""' + pdf_text + '"""' + \
|
| 35 |
+
'\nAnswer all questions according to the text delimited in tripple quotes above'
|
| 36 |
+
completion = client.chat.completions.create(
|
| 37 |
+
model="gpt-3.5-turbo",
|
| 38 |
+
messages=[
|
| 39 |
+
{"role": "system", "content": systemMessage},
|
| 40 |
+
{"role": "user", "content": prompt}
|
| 41 |
+
]
|
| 42 |
+
)
|
| 43 |
+
|
| 44 |
+
return (completion.choices[0].message).content
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
# gradio deployment
|
| 48 |
+
demo = gradio.Interface(fn=askPDF,
|
| 49 |
+
inputs=[gradio.File(file_types=['.pdf']), 'text'],
|
| 50 |
+
outputs="text",
|
| 51 |
+
)
|
| 52 |
+
|
| 53 |
+
demo.launch()
|