Spaces:
Sleeping
Sleeping
Delete dnd_database.py
Browse files- dnd_database.py +0 -26
dnd_database.py
DELETED
@@ -1,26 +0,0 @@
|
|
1 |
-
from driveapi.drive import process_pdf
|
2 |
-
|
3 |
-
from langchain.embeddings.openai import OpenAIEmbeddings
|
4 |
-
from langchain.text_splitter import CharacterTextSplitter
|
5 |
-
from langchain.vectorstores import FAISS
|
6 |
-
|
7 |
-
def create_dnd_database(file_list):
|
8 |
-
raw_text = ''
|
9 |
-
if file_list is None:
|
10 |
-
return None
|
11 |
-
for pdf in file_list:
|
12 |
-
raw_text += process_pdf(pdf)
|
13 |
-
|
14 |
-
embedding = OpenAIEmbeddings()
|
15 |
-
|
16 |
-
text_splitter = CharacterTextSplitter(
|
17 |
-
separator = "\n",
|
18 |
-
chunk_size = 1000,
|
19 |
-
chunk_overlap = 200,
|
20 |
-
length_function = len,
|
21 |
-
)
|
22 |
-
texts = text_splitter.split_text(raw_text)
|
23 |
-
print('Length of text: ' + str(len(raw_text)))
|
24 |
-
db = FAISS.from_texts(texts, embedding)
|
25 |
-
|
26 |
-
return db
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|