quivr/backend/modules/analytics/repository/analytics.py
Stan Girard 3400b8633f
feat(analytics): rely on sql rather that python loop for brains (#2437)
This pull request refactors the get_brains_usages method in the
Analytics class. The changes include improving code readability,
optimizing database queries, and fixing potential bugs.

<!--
ELLIPSIS_HIDDEN
-->


----

| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit f0ad664673. |
|--------|--------|

### Summary:
This PR optimizes the `get_brains_usages` method in the `Analytics`
class by reducing database calls and improving code readability.

**Key points**:
- Refactored `get_brains_usages` method in `Analytics` class.
- Optimized database query to fetch chat history in one go.
- Improved code readability and formatting.


----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)



<!--
ELLIPSIS_HIDDEN
-->
2024-04-17 07:24:03 -07:00

57 lines
1.8 KiB
Python

from collections import defaultdict
from datetime import datetime, timedelta
from typing import Optional
from uuid import UUID
from models.settings import get_supabase_client
from modules.analytics.entity.analytics import BrainsUsages, Range, Usage
from modules.brain.service.brain_user_service import BrainUserService
brain_user_service = BrainUserService()
class Analytics:
def __init__(self):
supabase_client = get_supabase_client()
self.db = supabase_client
def get_brains_usages(
self, user_id: UUID, graph_range: Range, brain_id: Optional[UUID] = None
) -> BrainsUsages:
user_brains = brain_user_service.get_user_brains(user_id)
if brain_id is not None:
user_brains = [brain for brain in user_brains if brain.id == brain_id]
usage_per_day = defaultdict(int)
brain_ids = [brain.id for brain in user_brains]
chat_history = (
self.db.from_("chat_history")
.select("*")
.in_("brain_id", brain_ids)
.execute()
).data
for chat in chat_history:
message_time = datetime.strptime(
chat["message_time"], "%Y-%m-%dT%H:%M:%S.%f"
)
usage_per_day[message_time.date()] += 1
start_date = datetime.now().date() - timedelta(days=graph_range)
all_dates = [start_date + timedelta(days=i) for i in range(graph_range)]
for date in all_dates:
usage_per_day[date] += 0
usages = sorted(
[
Usage(date=date, usage_count=count)
for date, count in usage_per_day.items()
if start_date <= date <= datetime.now().date()
],
key=lambda usage: usage.date,
)
return BrainsUsages(usages=usages)