Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -22,39 +22,18 @@ def get_pdf_text(pdf_docs):
|
|
| 22 |
pdf_doc = pdf_loader.load() # ํ
์คํธ๋ฅผ ์ถ์ถํฉ๋๋ค.
|
| 23 |
return pdf_doc # ์ถ์ถํ ํ
์คํธ๋ฅผ ๋ฐํํฉ๋๋ค.
|
| 24 |
|
| 25 |
-
|
|
|
|
| 26 |
def get_text_file(docs):
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
with open(temp_filepath, "wb") as f:
|
| 30 |
-
f.write(docs.getvalue())
|
| 31 |
-
text_loader = TextLoader(temp_filepath)
|
| 32 |
-
text_doc = text_loader.load()
|
| 33 |
-
return text_doc
|
| 34 |
-
|
| 35 |
-
|
| 36 |
def get_csv_file(docs):
|
| 37 |
-
|
| 38 |
-
temp_filepath = os.path.join(temp_dir.name, docs.name)
|
| 39 |
-
with open(temp_filepath, "wb") as f:
|
| 40 |
-
f.write(docs.getvalue())
|
| 41 |
-
csv_loader = CSVLoader(temp_filepath)
|
| 42 |
-
csv_doc = csv_loader.load()
|
| 43 |
-
return csv_doc
|
| 44 |
|
| 45 |
def get_json_file(docs):
|
| 46 |
-
|
| 47 |
-
temp_filepath = os.path.join(temp_dir.name, docs.name)
|
| 48 |
-
with open(temp_filepath, "wb") as f:
|
| 49 |
-
f.write(docs.getvalue())
|
| 50 |
-
json_loader = JSONLoader(temp_filepath,
|
| 51 |
-
jq_schema='.scans[].relationships',
|
| 52 |
-
text_content=False)
|
| 53 |
-
|
| 54 |
-
json_doc = json_loader.load()
|
| 55 |
-
# print('json_doc = ',json_doc)
|
| 56 |
-
return json_doc
|
| 57 |
|
|
|
|
| 58 |
# ๋ฌธ์๋ค์ ์ฒ๋ฆฌํ์ฌ ํ
์คํธ ์ฒญํฌ๋ก ๋๋๋ ํจ์์
๋๋ค.
|
| 59 |
def get_text_chunks(documents):
|
| 60 |
text_splitter = RecursiveCharacterTextSplitter(
|
|
|
|
| 22 |
pdf_doc = pdf_loader.load() # ํ
์คํธ๋ฅผ ์ถ์ถํฉ๋๋ค.
|
| 23 |
return pdf_doc # ์ถ์ถํ ํ
์คํธ๋ฅผ ๋ฐํํฉ๋๋ค.
|
| 24 |
|
| 25 |
+
# ๊ณผ์
|
| 26 |
+
# ์๋ ํ
์คํธ ์ถ์ถ ํจ์๋ฅผ ์์ฑ
|
| 27 |
def get_text_file(docs):
|
| 28 |
+
pass
|
| 29 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
def get_csv_file(docs):
|
| 31 |
+
pass
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
def get_json_file(docs):
|
| 34 |
+
pass
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
|
| 36 |
+
|
| 37 |
# ๋ฌธ์๋ค์ ์ฒ๋ฆฌํ์ฌ ํ
์คํธ ์ฒญํฌ๋ก ๋๋๋ ํจ์์
๋๋ค.
|
| 38 |
def get_text_chunks(documents):
|
| 39 |
text_splitter = RecursiveCharacterTextSplitter(
|