Skip to content

Refactor main.py to dynamically import pipeline classes only when needed #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
HyperNaser wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Refactor main.py to dynamically import pipeline classes only when needed #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,6 @@
import argparse
from dotenv import load_dotenv
from src.vector_store import get_embedding_model, create_chromadb_vector_store
from src.config import config
from src.pipelines import IngestionPipeline, RetrievalPipeline, ScrapingPipeline


def main():
Expand All @@ -16,16 +14,20 @@ def main():
args = parser.parse_args()

if args.scrape:
from src.pipelines.scraping_pipeline import ScrapingPipeline
ScrapingPipeline(docs_path=config.DOCS_PATH).run()
return

print("Initializing embedding model and vector store context...")
from src.vector_store import get_embedding_model, create_chromadb_vector_store
embedding_model = get_embedding_model(model_name=config.MODEL_NAME, device=config.DEVICE)
vector_store = create_chromadb_vector_store(embedding_model=embedding_model, persist_directory=config.DB_PATH)

if args.ingest:
from src.pipelines.ingestion_pipeline import IngestionPipeline
IngestionPipeline(vector_store=vector_store, docs_path=config.DOCS_PATH, with_previews=True, overwrite=True).run()
elif args.query:
from src.pipelines.retrieval_pipeline import RetrievalPipeline
RetrievalPipeline(vector_store=vector_store, app_config=config).run()

if __name__ == "__main__":
Expand Down
5 changes: 0 additions & 5 deletions src/pipelines/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +0,0 @@
from .ingestion_pipeline import IngestionPipeline
from .retrieval_pipeline import RetrievalPipeline
from .scraping_pipeline import ScrapingPipeline

__all__ = ["IngestionPipeline", "RetrievalPipeline", "ScrapingPipeline"]