Spaces:
Running
Running
File size: 1,809 Bytes
faf22ac c34ad45 faf22ac c34ad45 0dd2dc1 faf22ac | 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 | import json
import os
from langchain_core.documents import Document
from langchain_chroma import Chroma
from langchain_huggingface import HuggingFaceEmbeddings
JSON_FILE_PATH = "data/data.json"
CHROMA_DB_DIR = "chroma_data"
def main():
if not os.path.exists(JSON_FILE_PATH):
print(f"Error: File {JSON_FILE_PATH} not found.")
return
print("Reading JSON data...")
with open(JSON_FILE_PATH, "r", encoding="utf-8") as f:
chili_data = json.load(f)
print("Converting nested JSON data into LangChain Document format")
documents = []
for label, details in chili_data.items():
teks_gabungan = f"Penyakit/Kondisi: {label}\n"
if details.get("penyebab"):
teks_gabungan += "Penyebab:\n- " + "\n- ".join(details["penyebab"]) + "\n"
if details.get("gejala"):
teks_gabungan += "Gejala:\n- " + "\n- ".join(details["gejala"]) + "\n"
if details.get("penanganan"):
teks_gabungan += "Penanganan:\n- " + "\n- ".join(details["penanganan"]) + "\n"
if details.get("pencegahan"):
teks_gabungan += "Pencegahan:\n- " + "\n- ".join(details["pencegahan"]) + "\n"
doc = Document(
page_content=teks_gabungan,
metadata={"label": label}
)
documents.append(doc)
print("Memuat Embedding Model")
embeddings = HuggingFaceEmbeddings(model_name="Qwen/Qwen3-Embedding-0.6B")
print("Menyimpan data ke ChromaDB")
Chroma.from_documents(
documents=documents,
embedding=embeddings,
persist_directory=CHROMA_DB_DIR,
collection_name="chilicare_kb"
)
print(f"Berhasil! Database tersimpan di folder: {CHROMA_DB_DIR}\n")
if __name__ == "__main__":
main() |