Skip to content

Fix local LLM development setup: env loading, vector dimensions, and gitignore #44

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

Fix local LLM development setup: env loading, vector dimensions, and gitignore #44

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
3 changes: 2 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,4 +10,5 @@ backend/app.log
backend/Downloads
backend/.ipynb_checkpoints
backend/.venv
.idea
.idea
qdrant_storage/
4 changes: 3 additions & 1 deletion backend/app/core/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
from pydantic_settings import BaseSettings
from pydantic_settings import BaseSettings, SettingsConfigDict


class Settings(BaseSettings):
model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8")

# Frontend Config
FRONTEND_URL: str

Expand Down
5 changes: 3 additions & 2 deletions backend/app/services/knowledge_base_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,9 +32,10 @@ def create_knowledge_base_collection_if_not_exists():
collection_names = [col.name for col in collections.collections]

if KB_COLLECTION_NAME not in collection_names:
# Create collection with 1536 dimensions (Azure OpenAI text-embedding-ada-002)
# Create collection with Azure OpenAI text-embedding-ada-002 = 1536 / nomic-embed-text (Ollama) = 768
vector_size = 768 if settings.PROVIDER == "local" else 1536
result = create_qdrant_collection(
collection_name=KB_COLLECTION_NAME, vector_size=1536, distance="cosine"
collection_name=KB_COLLECTION_NAME, vector_size=vector_size, distance="cosine"
)
return {"status": "success", "message": result}
else:
Expand Down