Skip to content

Implemented Task b20: query suggestions #29

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

Merged
tanzilahmed0 merged 1 commit into from
Aug 2, 2025
Merged

Implemented Task b20: query suggestions #29

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
93 changes: 5 additions & 88 deletions backend/services/langchain_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
from models.response_schemas import QueryResult
from services.duckdb_service import duckdb_service
from services.embeddings_service import get_embeddings_service
from services.suggestions_service import get_suggestions_service
from services.project_service import get_project_service
from services.storage_service import storage_service

Expand Down Expand Up @@ -462,96 +463,12 @@ def _create_error_result(self, question: str, error_message: str) -> QueryResult
def generate_suggestions(
self, project_id: str, user_id: str
) -> List[Dict[str, Any]]:
"""Generate query suggestions based on project data."""
"""Generate query suggestions using the dedicated suggestions service."""
try:
# Use mock project data for now
project = {
"columns_metadata": [
{"name": "sales_amount", "type": "number"},
{"name": "category", "type": "string"},
{"name": "date", "type": "date"},
]
}

# Generate suggestions based on column types
suggestions = []
metadata = project.get("columns_metadata", [])

# Find numeric columns for aggregation suggestions
numeric_cols = [
col["name"]
for col in metadata
if col.get("type") in ["number", "integer", "float"]
]
categorical_cols = [
col["name"] for col in metadata if col.get("type") == "string"
]
date_cols = [
col["name"]
for col in metadata
if col.get("type") in ["date", "datetime"]
]

if numeric_cols:
suggestions.append(
{
"id": f"sug_sum_{numeric_cols[0]}",
"text": f"Show me the total {numeric_cols[0]}",
"category": "analysis",
"complexity": "beginner",
}
)

if categorical_cols:
suggestions.append(
{
"id": f"sug_group_{categorical_cols[0]}",
"text": f"Break down {numeric_cols[0]} by {categorical_cols[0]}",
"category": "analysis",
"complexity": "intermediate",
}
)

suggestions.append(
{
"id": f"sug_chart_{categorical_cols[0]}",
"text": f"Create a bar chart of {numeric_cols[0]} by {categorical_cols[0]}",
"category": "visualization",
"complexity": "intermediate",
}
)

if date_cols and numeric_cols:
suggestions.append(
{
"id": f"sug_trend_{date_cols[0]}",
"text": f"Show {numeric_cols[0]} trend over {date_cols[0]}",
"category": "visualization",
"complexity": "intermediate",
}
)

# Add general suggestions
suggestions.extend(
[
{
"id": "sug_overview",
"text": "Give me an overview of this dataset",
"category": "summary",
"complexity": "beginner",
},
{
"id": "sug_top_values",
"text": "Show me the top 10 rows",
"category": "analysis",
"complexity": "beginner",
},
]
)

return suggestions[:5] # Return top 5 suggestions

suggestions_service = get_suggestions_service()
return suggestions_service.generate_suggestions(project_id, user_id)
except Exception as e:
logger.error(f"Error generating suggestions via service: {str(e)}")
return []

def _ensure_project_embeddings(self, project_id: str, user_id: str):
Expand Down
Loading