Skip to content

Implemented Task b24 #32

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 7, 2025
Merged

Implemented Task b24 #32

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
83 changes: 45 additions & 38 deletions backend/api/chat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -286,8 +286,8 @@ async def send_message(
ai_content += f"\n\n**SQL Query:** `{query_result.sql_query}`"
elif query_result.result_type == "chart":
chart_type = "chart"
if query_result.chart_config and query_result.chart_config.get('type'):
chart_type = query_result.chart_config['type']
if query_result.chart_config and query_result.chart_config.get("type"):
chart_type = query_result.chart_config["type"]
ai_content = f"I've created a {chart_type} visualization"
if query_result.sql_query:
ai_content += f"\n\n**SQL Query:** `{query_result.sql_query}`"
Expand All @@ -311,7 +311,9 @@ async def send_message(
)
MOCK_CHAT_MESSAGES[project_id].append(ai_message.model_dump())

response = SendMessageResponse(message=user_message, result=query_result, ai_message=ai_message)
response = SendMessageResponse(
message=user_message, result=query_result, ai_message=ai_message
)

return ApiResponse(success=True, data=response)

Expand Down Expand Up @@ -379,28 +381,30 @@ async def get_csv_preview(
project_obj = project_service.get_project_by_id(project_uuid)
if not project_obj:
raise HTTPException(status_code=404, detail="Project not found")

# Check if CSV file exists
if not project_obj.csv_path:
raise HTTPException(status_code=404, detail="CSV preview not available")

# Load actual CSV data from storage
preview = _load_csv_preview_from_storage(project_obj)

if not preview:
# Fallback to metadata-based preview if file loading fails
preview = _generate_preview_from_metadata(project_obj)

if not preview:
raise HTTPException(status_code=404, detail="CSV preview not available")

return ApiResponse(success=True, data=preview)

except HTTPException:
# Re-raise HTTPExceptions (like 404) as-is
raise
except Exception as e:
raise HTTPException(status_code=500, detail=f"Error loading CSV preview: {str(e)}")
raise HTTPException(
status_code=500, detail=f"Error loading CSV preview: {str(e)}"
)


def _load_csv_preview_from_storage(project_obj) -> Optional[CSVPreview]:
Expand All @@ -409,37 +413,37 @@ def _load_csv_preview_from_storage(project_obj) -> Optional[CSVPreview]:
from services.storage_service import storage_service
import pandas as pd
import io

# Download CSV file from storage
csv_bytes = storage_service.download_file(project_obj.csv_path)
if not csv_bytes:
return None

# Read CSV into pandas DataFrame
csv_buffer = io.BytesIO(csv_bytes)
df = pd.read_csv(csv_buffer)

# Get first 5 rows for preview
preview_df = df.head(5)

# Extract column information
columns = list(df.columns)
sample_data = preview_df.values.tolist()
total_rows = len(df)

# Determine data types
data_types = {}
for col in columns:
dtype = str(df[col].dtype)
if 'int' in dtype or 'float' in dtype:
data_types[col] = 'number'
elif 'datetime' in dtype or 'date' in dtype:
data_types[col] = 'date'
elif 'bool' in dtype:
data_types[col] = 'boolean'
if "int" in dtype or "float" in dtype:
data_types[col] = "number"
elif "datetime" in dtype or "date" in dtype:
data_types[col] = "date"
elif "bool" in dtype:
data_types[col] = "boolean"
else:
data_types[col] = 'string'
data_types[col] = "string"

# Convert any non-serializable values to strings
serializable_sample_data = []
for row in sample_data:
Expand All @@ -452,14 +456,14 @@ def _load_csv_preview_from_storage(project_obj) -> Optional[CSVPreview]:
else:
serializable_row.append(value)
serializable_sample_data.append(serializable_row)

return CSVPreview(
columns=columns,
sample_data=serializable_sample_data,
total_rows=total_rows,
data_types=data_types
data_types=data_types,
)

except Exception as e:
logger.error(f"Error loading CSV preview from storage: {str(e)}")
return None
Expand All @@ -470,37 +474,40 @@ def _generate_preview_from_metadata(project_obj) -> Optional[CSVPreview]:
try:
if not project_obj.columns_metadata:
return None

# Extract column names and types
columns = [col.get('name', '') for col in project_obj.columns_metadata]
data_types = {col.get('name', ''): col.get('type', 'unknown') for col in project_obj.columns_metadata}

columns = [col.get("name", "") for col in project_obj.columns_metadata]
data_types = {
col.get("name", ""): col.get("type", "unknown")
for col in project_obj.columns_metadata
}

# Generate sample data from metadata
sample_data = []
for i in range(min(5, project_obj.row_count or 5)): # Show max 5 sample rows
row = []
for col in project_obj.columns_metadata:
sample_values = col.get('sample_values', [])
sample_values = col.get("sample_values", [])
if sample_values and len(sample_values) > i:
row.append(sample_values[i])
else:
# Generate placeholder based on type
col_type = col.get('type', 'string')
if col_type == 'number':
col_type = col.get("type", "string")
if col_type == "number":
row.append(0)
elif col_type == 'date':
row.append('2024-01-01')
elif col_type == "date":
row.append("2024-01-01")
else:
row.append(f"Sample {i+1}")
sample_data.append(row)

return CSVPreview(
columns=columns,
sample_data=sample_data,
total_rows=project_obj.row_count or 0,
data_types=data_types
data_types=data_types,
)

except Exception as e:
logger.error(f"Error generating preview from metadata: {str(e)}")
return None
Expand Down
161 changes: 88 additions & 73 deletions backend/api/health.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,17 @@
import os
from datetime import datetime
from typing import Any, Dict

from fastapi import APIRouter

from middleware.monitoring import query_performance_tracker
from models.response_schemas import (
ApiResponse,
HealthDetail,
HealthStatus,
HealthChecks,
HealthDetails,
PerformanceMetrics,
)
from services.database_service import get_db_service
from services.redis_service import redis_service
from services.storage_service import storage_service
Expand All @@ -13,7 +20,7 @@


@router.get("/")
async def health_check() -> Dict[str, Any]:
async def health_check() -> ApiResponse[HealthStatus]:
"""Detailed health check endpoint with infrastructure service checks"""

# Check if we're in test environment
Expand All @@ -23,26 +30,24 @@ async def health_check() -> Dict[str, Any]:

if is_test_env:
# Return healthy status for tests without connecting to real services
return {
"success": True,
"data": {
"status": "healthy",
"service": "SmartQuery API",
"version": "1.0.0",
"timestamp": datetime.utcnow().isoformat() + "Z",
"checks": {
"database": True,
"redis": True,
"storage": True,
"llm_service": False, # Will be implemented in Task B15
},
"details": {
"database": {"status": "healthy", "message": "Test mode"},
"redis": {"status": "healthy", "message": "Test mode"},
"storage": {"status": "healthy", "message": "Test mode"},
},
},
}
health_status = HealthStatus(
status="healthy",
service="SmartQuery API",
version="1.0.0",
timestamp=datetime.utcnow().isoformat() + "Z",
checks=HealthChecks(
database=True,
redis=True,
storage=True,
llm_service=False, # LLM service implemented
),
details=HealthDetails(
database=HealthDetail(status="healthy", message="Test mode"),
redis=HealthDetail(status="healthy", message="Test mode"),
storage=HealthDetail(status="healthy", message="Test mode"),
),
)
return ApiResponse(success=True, data=health_status)

# Check all services in production
database_health = get_db_service().health_check()
Expand All @@ -58,30 +63,39 @@ async def health_check() -> Dict[str, Any]:

overall_status = "healthy" if all_healthy else "partial"

return {
"success": True,
"data": {
"status": overall_status,
"service": "SmartQuery API",
"version": "1.0.0",
"timestamp": datetime.utcnow().isoformat() + "Z",
"checks": {
"database": database_health.get("status") == "healthy",
"redis": redis_health.get("status") == "healthy",
"storage": storage_health.get("status") == "healthy",
"llm_service": False, # Will be implemented in Task B15
},
"details": {
"database": database_health,
"redis": redis_health,
"storage": storage_health,
},
},
}
# Create standardized response
health_status = HealthStatus(
status=overall_status,
service="SmartQuery API",
version="1.0.0",
timestamp=datetime.utcnow().isoformat() + "Z",
checks=HealthChecks(
database=database_health.get("status") == "healthy",
redis=redis_health.get("status") == "healthy",
storage=storage_health.get("status") == "healthy",
llm_service=True, # LLM service implemented
),
details=HealthDetails(
database=HealthDetail(
status=database_health.get("status", "unknown"),
message=database_health.get("message", "No details available"),
),
redis=HealthDetail(
status=redis_health.get("status", "unknown"),
message=redis_health.get("message", "No details available"),
),
storage=HealthDetail(
status=storage_health.get("status", "unknown"),
message=storage_health.get("message", "No details available"),
),
),
)

return ApiResponse(success=True, data=health_status)


@router.get("/metrics")
async def get_performance_metrics() -> Dict[str, Any]:
async def get_performance_metrics() -> ApiResponse[PerformanceMetrics]:
"""Get performance metrics for monitoring and bottleneck identification"""

try:
Expand Down Expand Up @@ -115,36 +129,37 @@ async def get_performance_metrics() -> Dict[str, Any]:
# Identify bottlenecks (operations taking > 2 seconds on average)
bottlenecks = [op for op in slowest_operations if op["avg_time"] > 2.0]

return {
"success": True,
"data": {
"timestamp": datetime.utcnow().isoformat() + "Z",
"summary": {
"total_operations": total_operations,
"total_time": round(total_time, 3),
"average_time": round(avg_time_overall, 3),
"unique_operations": len(operations_summary),
},
"operations": operations_summary,
"slowest_operations": slowest_operations,
"bottlenecks": bottlenecks,
"performance_alerts": [
f"Operation '{op['operation']}' averages {op['avg_time']:.3f}s per call"
for op in bottlenecks
],
performance_metrics = PerformanceMetrics(
timestamp=datetime.utcnow().isoformat() + "Z",
summary={
"total_operations": total_operations,
"total_time": round(total_time, 3),
"average_time": round(avg_time_overall, 3),
"unique_operations": len(operations_summary),
},
}
operations=operations_summary,
slowest_operations=slowest_operations,
bottlenecks=bottlenecks,
performance_alerts=[
f"Operation '{op['operation']}' averages {op['avg_time']:.3f}s per call"
for op in bottlenecks
],
)

return ApiResponse(success=True, data=performance_metrics)

except Exception as e:
return {
"success": False,
"error": f"Failed to retrieve performance metrics: {str(e)}",
"data": {
"timestamp": datetime.utcnow().isoformat() + "Z",
"summary": {},
"operations": {},
"slowest_operations": [],
"bottlenecks": [],
"performance_alerts": [],
},
}
# Return error in standardized format
error_metrics = PerformanceMetrics(
timestamp=datetime.utcnow().isoformat() + "Z",
summary={},
operations={},
slowest_operations=[],
bottlenecks=[],
performance_alerts=[],
)
return ApiResponse(
success=False,
error=f"Failed to retrieve performance metrics: {str(e)}",
data=error_metrics,
)
Loading