KeyArgo
/
private-gpt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix persist db directory at ingestion

This commit is contained in:
Andrea Pinto 2023-05-12 10:37:10 +02:00
parent 39df61ca07
commit 01f55441e7
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
constants.py
View File

@ -1,7 +1,11 @@
import os
from dotenv import load_dotenv
from chromadb.config import Settings from chromadb.config import Settings
load_dotenv()
# Define the folder for storing database # Define the folder for storing database
PERSIST_DIRECTORY = 'db' PERSIST_DIRECTORY = os.environ.get('PERSIST_DIRECTORY')
# Define the Chroma settings # Define the Chroma settings
CHROMA_SETTINGS = Settings( CHROMA_SETTINGS = Settings(

3
ingest.py
View File

@ -4,7 +4,6 @@ from langchain.document_loaders import TextLoader, PDFMinerLoader, CSVLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma from langchain.vectorstores import Chroma
from langchain.embeddings import LlamaCppEmbeddings from langchain.embeddings import LlamaCppEmbeddings
from constants import PERSIST_DIRECTORY
from constants import CHROMA_SETTINGS from constants import CHROMA_SETTINGS
load_dotenv() load_dotenv()
@ -28,7 +27,7 @@ def main():
# Create embeddings # Create embeddings
llama = LlamaCppEmbeddings(model_path=llama_embeddings_model, n_ctx=model_n_ctx) llama = LlamaCppEmbeddings(model_path=llama_embeddings_model, n_ctx=model_n_ctx)
# Create and store locally vectorstore # Create and store locally vectorstore
db = Chroma.from_documents(texts, llama, persist_directory=PERSIST_DIRECTORY, client_settings=CHROMA_SETTINGS) db = Chroma.from_documents(texts, llama, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
db.persist() db.persist()
db = None db = None