Docs update

README.md

@@ -10,6 +10,10 @@ AI models a new attack vector for hackers. They can use AI models to generate ma
 ## Solution
 OpenShield a transparent proxy that sits between your AI model and the client. It provides rate limiting, content filtering, and keyword filtering for AI models.
 
+![Input flow](https://github.com/openshieldai/openshield/docs/assets/input.svg)
+
+![Output flow](https://github.com/openshieldai/openshield/docs/assets/output.svg)
+
 You can chain multiple AI models together to create a pipeline before hitting the foundation model.
 
 ## Features

server/server.go

@@ -3,14 +3,15 @@ package server
 import (
 	"context"
 	"fmt"
-	"github.com/gofiber/fiber/v2/middleware/limiter"
-	"github.com/openshieldai/openshield/lib/openai"
-	"golang.org/x/sync/errgroup"
 	"os"
 	"os/signal"
 	"syscall"
 	"time"
 
+	"github.com/gofiber/fiber/v2/middleware/limiter"
+	"github.com/openshieldai/openshield/lib/openai"
+	"golang.org/x/sync/errgroup"
+
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/fiber/v2/middleware/logger"
 	"github.com/gofiber/fiber/v2/middleware/requestid"