From 7cba8f6de5e71a028539d48f16a1cad2e7769a8d Mon Sep 17 00:00:00 2001
From: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Date: Fri, 21 Jun 2024 13:08:54 -0700
Subject: [PATCH] backend - new endpoint to show cache hit stats

---
 .../analytics_endpoints.py                    | 103 ++++++++++++++++++
 litellm/proxy/proxy_server.py                 |   4 +
 2 files changed, 107 insertions(+)
 create mode 100644 litellm/proxy/analytics_endpoints/analytics_endpoints.py

diff --git a/litellm/proxy/analytics_endpoints/analytics_endpoints.py b/litellm/proxy/analytics_endpoints/analytics_endpoints.py
new file mode 100644
index 0000000000..ebb7d43acf
--- /dev/null
+++ b/litellm/proxy/analytics_endpoints/analytics_endpoints.py
@@ -0,0 +1,103 @@
+#### Analytics Endpoints #####
+from datetime import datetime, timedelta, timezone
+from typing import List, Optional
+
+import fastapi
+from fastapi import APIRouter, Depends, Header, HTTPException, Request, status
+
+import litellm
+from litellm._logging import verbose_proxy_logger
+from litellm.proxy._types import *
+from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
+
+router = APIRouter()
+
+
+@router.get(
+    "/global/activity/cache_hits",
+    tags=["Budget & Spend Tracking"],
+    dependencies=[Depends(user_api_key_auth)],
+    responses={
+        200: {"model": List[LiteLLM_SpendLogs]},
+    },
+    include_in_schema=False,
+)
+async def get_global_activity(
+    start_date: Optional[str] = fastapi.Query(
+        default=None,
+        description="Time from which to start viewing spend",
+    ),
+    end_date: Optional[str] = fastapi.Query(
+        default=None,
+        description="Time till which to view spend",
+    ),
+):
+    """
+    Get number of cache hits, vs misses
+
+    {
+        "daily_data": [
+                const chartdata = [
+                {
+                    date: 'Jan 22',
+                    cache_hits: 10,
+                    llm_api_calls: 2000
+                },
+                {
+                    date: 'Jan 23',
+                    cache_hits: 10,
+                    llm_api_calls: 12
+                },
+        ],
+        "sum_cache_hits": 20,
+        "sum_llm_api_calls": 2012
+    }
+    """
+    from collections import defaultdict
+
+    if start_date is None or end_date is None:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail={"error": "Please provide start_date and end_date"},
+        )
+
+    start_date_obj = datetime.strptime(start_date, "%Y-%m-%d")
+    end_date_obj = datetime.strptime(end_date, "%Y-%m-%d")
+
+    from litellm.proxy.proxy_server import llm_router, prisma_client
+
+    try:
+        if prisma_client is None:
+            raise ValueError(
+                f"Database not connected. Connect a database to your proxy - https://docs.litellm.ai/docs/simple_proxy#managing-auth---virtual-keys"
+            )
+
+        sql_query = """
+            SELECT
+                "api_key",
+                "call_type",
+                "model",
+                COUNT(*) AS total_rows,
+                SUM(CASE WHEN "cache_hit" = 'True' THEN 1 ELSE 0 END) AS cache_hit_true_rows
+            FROM "LiteLLM_SpendLogs"
+            WHERE 
+                "startTime" BETWEEN $1::date AND $2::date + interval '1 day'
+            GROUP BY 
+                "api_key",
+                "call_type",
+                "model"
+        """
+        db_response = await prisma_client.db.query_raw(
+            sql_query, start_date_obj, end_date_obj
+        )
+
+        if db_response is None:
+            return []
+
+        return db_response
+
+    except Exception as e:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail={"error": str(e)},
+        )
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 6d19766ad0..3befed9eaa 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -116,6 +116,9 @@ from litellm.exceptions import RejectedRequestError
 from litellm.integrations.slack_alerting import SlackAlerting, SlackAlertingArgs
 from litellm.llms.custom_httpx.httpx_handler import HTTPHandler
 from litellm.proxy._types import *
+from litellm.proxy.analytics_endpoints.analytics_endpoints import (
+    router as analytics_router,
+)
 from litellm.proxy.auth.auth_checks import (
     allowed_routes_check,
     common_checks,
@@ -9139,3 +9142,4 @@ app.include_router(internal_user_router)
 app.include_router(team_router)
 app.include_router(spend_management_router)
 app.include_router(caching_router)
+app.include_router(analytics_router)