-
Notifications
You must be signed in to change notification settings - Fork 0
/
create_database.py
59 lines (43 loc) · 1.56 KB
/
create_database.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.schema import Document
from langchain.vectorstores.chroma import Chroma
import os
import shutil
from langchain_community.document_loaders import DirectoryLoader
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
CHROMA_PATH = "chroma"
DATA_PATH = "data"
def main():
generate_data_store()
def generate_data_store():
documents = load_documents()
chunks = split_text(documents)
save_to_chroma(chunks)
def load_documents():
loader = DirectoryLoader(DATA_PATH, glob="*.pdf")
documents = loader.load()
return documents
def split_text(documents: list[Document]):
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200,
length_function=len,
#add_start_index=True,
)
chunks = text_splitter.split_documents(documents)
print(f"Split {len(documents)} documents into {len(chunks)} chunks.")
return chunks
def save_to_chroma(chunks: list[Document]):
# Clear out the database first.
if os.path.exists(CHROMA_PATH):
shutil.rmtree(CHROMA_PATH)
embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
# Create a new DB from the documents.
db = Chroma.from_documents(documents=chunks,
embedding=embeddings,
persist_directory=CHROMA_PATH)
db.persist()
db = None
print(f"Saved {len(chunks)} chunks to {CHROMA_PATH}.")
if __name__ == "__main__":
main()