Update app.py
Browse files
app.py
CHANGED
@@ -70,7 +70,20 @@ def generate_response(rag_chain, input_text):
|
|
70 |
|
71 |
return response
|
72 |
|
73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
|
76 |
def main() -> None:
|
@@ -86,13 +99,9 @@ def main() -> None:
|
|
86 |
|
87 |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
|
88 |
|
89 |
-
### Ken 12/11/2024 START
|
90 |
-
|
91 |
-
|
92 |
-
ldocs = loader.load()
|
93 |
-
|
94 |
-
raw_text = get_pdf(ldocs)
|
95 |
-
### Ken 12/11/2024 END
|
96 |
|
97 |
#chunks = text_splitter.split_documents(docs)
|
98 |
chunks = text_splitter.split_documents(raw_text)
|
|
|
70 |
|
71 |
return response
|
72 |
|
73 |
+
### Ken 12/11/2024 ADD START
|
74 |
+
def get_pdf(uploaded_file):
|
75 |
+
if uploaded_file :
|
76 |
+
temp_file = "./temp.pdf"
|
77 |
+
# Delete the existing temp.pdf file if it exists
|
78 |
+
if os.path.exists(temp_file):
|
79 |
+
os.remove(temp_file)
|
80 |
+
with open(temp_file, "wb") as file:
|
81 |
+
file.write(uploaded_file.getvalue())
|
82 |
+
file_name = uploaded_file.name
|
83 |
+
loader = PyPDFLoader(temp_file)
|
84 |
+
docs = loader.load()
|
85 |
+
return docs
|
86 |
+
### Ken 12/11/2024 ADD END
|
87 |
|
88 |
|
89 |
def main() -> None:
|
|
|
99 |
|
100 |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
|
101 |
|
102 |
+
### Ken 12/11/2024 ADD START
|
103 |
+
raw_text = get_pdf(docs)
|
104 |
+
### Ken 12/11/2024 ADD END
|
|
|
|
|
|
|
|
|
105 |
|
106 |
#chunks = text_splitter.split_documents(docs)
|
107 |
chunks = text_splitter.split_documents(raw_text)
|