Commit
Β·
8af059d
1
Parent(s):
d296422
Update app.py
Browse files
app.py
CHANGED
@@ -46,7 +46,7 @@ def get_csv_file(docs):
|
|
46 |
def get_json_file(docs):
|
47 |
pass
|
48 |
|
49 |
-
|
50 |
# λ¬Έμλ€μ μ²λ¦¬νμ¬ ν
μ€νΈ μ²ν¬λ‘ λλλ ν¨μμ
λλ€.
|
51 |
def get_text_chunks(documents):
|
52 |
text_splitter = RecursiveCharacterTextSplitter(
|
@@ -57,17 +57,7 @@ def get_text_chunks(documents):
|
|
57 |
|
58 |
documents = text_splitter.split_documents(documents) # λ¬Έμλ€μ μ²ν¬λ‘ λλλλ€.
|
59 |
return documents # λλ μ²ν¬λ₯Ό λ°νν©λλ€.
|
60 |
-
'''
|
61 |
-
def get_text_chunks(documents):
|
62 |
-
text_splitter = RecursiveCharacterTextSplitter(
|
63 |
-
chunk_size=1000, # μ²ν¬μ ν¬κΈ°λ₯Ό μ§μ ν©λλ€.
|
64 |
-
chunk_overlap=200, # μ²ν¬ μ¬μ΄μ μ€λ³΅μ μ§μ ν©λλ€.
|
65 |
-
length_function=len # ν
μ€νΈμ κΈΈμ΄λ₯Ό μΈ‘μ νλ ν¨μλ₯Ό μ§μ ν©λλ€.
|
66 |
-
)
|
67 |
|
68 |
-
documents = [doc for doc in documents if doc.strip()] # λΉ ν
μ€νΈλ₯Ό μ κ±°ν©λλ€.
|
69 |
-
text_chunks = text_splitter.split_documents(documents) # λ¬Έμλ€μ μ²ν¬λ‘ λλλλ€.
|
70 |
-
return text_chunks # λλ μ²ν¬λ₯Ό λ°νν©λλ€.
|
71 |
|
72 |
# ν
μ€νΈ μ²ν¬λ€λ‘λΆν° λ²‘ν° μ€ν μ΄λ₯Ό μμ±νλ ν¨μμ
λλ€.
|
73 |
def get_vectorstore(text_chunks):
|
|
|
46 |
def get_json_file(docs):
|
47 |
pass
|
48 |
|
49 |
+
|
50 |
# λ¬Έμλ€μ μ²λ¦¬νμ¬ ν
μ€νΈ μ²ν¬λ‘ λλλ ν¨μμ
λλ€.
|
51 |
def get_text_chunks(documents):
|
52 |
text_splitter = RecursiveCharacterTextSplitter(
|
|
|
57 |
|
58 |
documents = text_splitter.split_documents(documents) # λ¬Έμλ€μ μ²ν¬λ‘ λλλλ€.
|
59 |
return documents # λλ μ²ν¬λ₯Ό λ°νν©λλ€.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
|
|
|
|
|
|
|
61 |
|
62 |
# ν
μ€νΈ μ²ν¬λ€λ‘λΆν° λ²‘ν° μ€ν μ΄λ₯Ό μμ±νλ ν¨μμ
λλ€.
|
63 |
def get_vectorstore(text_chunks):
|