Update app.py
Browse files
app.py
CHANGED
|
@@ -76,13 +76,14 @@ def get_json_file(json_docs):
|
|
| 76 |
|
| 77 |
# ๋ฌธ์๋ค์ ์ฒ๋ฆฌํ์ฌ ํ
์คํธ ์ฒญํฌ๋ก ๋๋๋ ํจ์์
๋๋ค.
|
| 78 |
def get_text_chunks(documents):
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
|
|
|
| 86 |
|
| 87 |
|
| 88 |
|
|
|
|
| 76 |
|
| 77 |
# ๋ฌธ์๋ค์ ์ฒ๋ฆฌํ์ฌ ํ
์คํธ ์ฒญํฌ๋ก ๋๋๋ ํจ์์
๋๋ค.
|
| 78 |
def get_text_chunks(documents):
|
| 79 |
+
text_splitter = RecursiveCharacterTextSplitter(
|
| 80 |
+
chunk_size=1000, # ์ฒญํฌ์ ํฌ๊ธฐ๋ฅผ ์ง์ ํฉ๋๋ค.
|
| 81 |
+
chunk_overlap=200, # ์ฒญํฌ ์ฌ์ด์ ์ค๋ณต์ ์ง์ ํฉ๋๋ค.
|
| 82 |
+
length_function=len # ํ
์คํธ์ ๊ธธ์ด๋ฅผ ์ธก์ ํ๋ ํจ์๋ฅผ ์ง์ ํฉ๋๋ค.
|
| 83 |
+
)
|
| 84 |
+
|
| 85 |
+
documents = text_splitter.split_documents(documents) # ๋ฌธ์๋ค์ ์ฒญํฌ๋ก ๋๋๋๋ค
|
| 86 |
+
return documents # ๋๋ ์ฒญํฌ๋ฅผ ๋ฐํํฉ๋๋ค.
|
| 87 |
|
| 88 |
|
| 89 |
|