Add VSCode settings, update dependencies, and enhance document processing with image handling

.vscode/extensions.json

@@ -0,0 +1,3 @@
+{
+  "recommendations": ["denoland.vscode-deno"]
+}

.vscode/settings.json

@@ -0,0 +1,22 @@
+{
+  "deno.enablePaths": ["supabase/functions"],
+  "deno.lint": true,
+  "deno.unstable": [
+    "bare-node-builtins",
+    "byonm",
+    "sloppy-imports",
+    "unsafe-proto",
+    "webgpu",
+    "broadcast-channel",
+    "worker-options",
+    "cron",
+    "kv",
+    "ffi",
+    "fs",
+    "http",
+    "net"
+  ],
+  "[typescript]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  }
+}

app/dashboard/documents/[id]/page.tsx

@@ -25,11 +25,7 @@ import { redirect } from "next/navigation";
 import { remark } from "remark";
 import remarkHtml from "remark-html";
 
-export default async function DocumentPage({
+export default async function DocumentPage(props: { params: { id: string } }) {
-  params,
-}: {
-  params: { id: string };
-}) {
   const supabase = await createClient();
 
   const {
@@ -40,11 +36,13 @@ export default async function DocumentPage({
     return redirect("/login");
   }
 
+  const { id } = await props.params;
+
   // Fetch the document details based on the ID from params
   const { data: document, error } = await supabase
     .from("documents")
     .select("*")
-    .eq("id", params.id)
+    .eq("id", id)
     .single();
 
   if (error || !document) {

app/dashboard/upload/process/route.ts

@@ -2,10 +2,22 @@ import { createClient } from "@/utils/supabase/server";
 import { NextResponse } from "next/server";
 import { Mistral } from "@mistralai/mistralai";
 import { redirect } from "next/navigation";
+import { ChatCompletionChoice } from "@mistralai/mistralai/models/components";
+import pLimit from "p-limit";
 
 const apiKey = process.env.MISTRAL_API_KEY;
 const client = new Mistral({ apiKey: apiKey });
 
+const PROCESSING_PROMPT = `
+You are a document processing AI. Your task is to process the Markdown text scanned from a document page and return it in a clean and structured format.
+
+The textual page data should only be returned in valid Markdown format. Use proper headings and subheadings to structure the content.
+Any images should be included.
+Do not return the Markdown as a code block, only as a raw string, without any new lines.
+
+The Markdown should be human-readable and well-formatted.
+`;
+
 export async function POST(request: Request) {
   const supabase = await createClient();
   const formData = await request.formData();
@@ -33,15 +45,126 @@ export async function POST(request: Request) {
     },
   });
 
+  const limit = pLimit(1); // Limit to 1 concurrent request (adjust as needed)
+
+  const promises: Promise<any>[] = [];
+
+  for (const page of ocrResponse.pages) {
+    const pagePromise = limit(async () => {
+      const response = await client.chat.complete({
+        model: "mistral-small-latest",
+        messages: [
+          {
+            role: "user",
+            content: [
+              {
+                type: "text",
+                text: PROCESSING_PROMPT,
+              },
+            ],
+          },
+        ],
+      });
+
+      if (!response.choices) {
+        console.error("No choices in response");
+        return;
+      }
+
+      const imageData: { [key: string]: string } = {};
+
+      if (page.images.length > 0) {
+        for (const img of page.images) {
+          imageData[img.id] = img.imageBase64!;
+        }
+      }
+
+      if (response.choices[0].message.content) {
+        const markdown = replaceImagesInMarkdown(
+          response.choices[0].message.content.toString(),
+          imageData
+        );
+
+        return {
+          ...page,
+          markdown,
+        };
+      } else {
+        console.error("Message content is undefined");
+      }
+    });
+
+    promises.push(pagePromise);
+  }
+
+  const results = await Promise.all(promises);
+  const sortedResults = results.sort((a, b) => a.index - b.index);
+
   const { data, error } = await supabase
     .from("documents")
     .update({
-      ocr_data: ocrResponse,
+      ocr_data: sortedResults,
     })
     .eq("id", id);
   if (error) {
     console.error(error);
     return NextResponse.json({ error: error.message }, { status: 500 });
   }
-  return redirect(`/dashboard/documents/${id}`); // Redirect to the document page after processing
+  return NextResponse.json({
+    id,
+  });
+}
+
+interface OCRResponse {
+  pages: {
+    markdown: string;
+    images: { id: string; image_base64: string }[];
+  }[];
+}
+
+function replaceImagesInMarkdown(
+  markdownStr: string,
+  imagesDict: { [key: string]: string }
+): string {
+  /**
+   * Replace image placeholders in markdown with base64-encoded images.
+   *
+   * Args:
+   *   markdownStr: Markdown text containing image placeholders
+   *   imagesDict: Dictionary mapping image IDs to base64 strings
+   *
+   * Returns:
+   *    Markdown text with images replaced by base64 data
+   */
+  for (const [imgName, base64Str] of Object.entries(imagesDict)) {
+    markdownStr = markdownStr.replace(
+      new RegExp(`!\\[${imgName}\\]\\(${imgName}\\)`, "g"),
+      `![${imgName}](${base64Str})`
+    );
+  }
+  return markdownStr;
+}
+
+function getCombinedMarkdown(ocrResponse: OCRResponse): string {
+  /**
+   * Combine OCR text and images into a single markdown document.
+   *
+   * Args:
+   *   ocrResponse: Response from OCR processing containing text and images
+   *
+   * Returns:
+   *   Combined markdown string with embedded images
+   */
+  const markdowns: string[] = [];
+  // Extract images from page
+  for (const page of ocrResponse.pages) {
+    const imageData: { [key: string]: string } = {};
+    for (const img of page.images) {
+      imageData[img.id] = img.image_base64;
+    }
+    // Replace image placeholders with actual images
+    markdowns.push(replaceImagesInMarkdown(page.markdown, imageData));
+  }
+
+  return markdowns.join("\n\n");
 }

app/layout.tsx

@@ -7,6 +7,7 @@ import { Geist } from "next/font/google";
 import { ThemeProvider } from "next-themes";
 import Link from "next/link";
 import "./globals.css";
+import { Toaster } from "@/components/ui/sonner";
 
 const defaultUrl = process.env.VERCEL_URL
   ? `https://${process.env.VERCEL_URL}`
@@ -38,6 +39,7 @@ export default function RootLayout({
           disableTransitionOnChange
         >
           {children}
+          <Toaster />
           <ThemeSwitcher />
         </ThemeProvider>
       </body>

components/UploadZone.tsx

@@ -1,49 +1,83 @@
 "use client";
 import { createClient } from "@/utils/supabase/client";
-import { CloudUpload } from "lucide-react";
+import { CloudUpload, LoaderCircle } from "lucide-react";
+import { useState } from "react";
+import { toast } from "sonner";
+import { SSE } from "sse.js";
 
 export default function UploadZone({ user }: { user?: { id: string } }) {
   const supabase = createClient();
+  const [uploading, setUploading] = useState(false);
+  const [status, setStatus] = useState("");
 
   const onUpload = async (file: File) => {
-    const uuid = crypto.randomUUID();
+    setUploading(true);
+    setStatus("Uploading...");
 
-    const { data: fileData, error: fileError } = await supabase.storage
+    const { data, error } = await supabase.auth.getSession();
-      .from("documents")
-      .upload(`${user!.id}/${uuid}.pdf`, file);
-
-    if (fileError) {
-      console.error(fileError);
-      return;
-    }
-
-    console.log("File uploaded successfully:", fileData);
-
-    const { data, error } = await supabase.from("documents").insert({
-      id: uuid,
-      file_name: file.name,
-      owner: user!.id,
-      raw_file: fileData.id,
-    });
 
     if (error) {
-      console.error(error);
+      toast.error("Failed to get user session.");
+      setUploading(false);
       return;
     }
 
-    console.log("Document inserted successfully:", data);
+    const body = new FormData();
+    body.append("file", file);
+    body.append("jwt", data.session?.access_token || "");
 
-    // process file at /dashboard/upload/process
+    const edgeFunctionUrl = `${process.env.NEXT_PUBLIC_SUPABASE_URL}/functions/v1/process-document`;
-    const formData = new FormData();
+
-    formData.append("file", file);
+    // Start listening to the SSE stream
-    formData.append("fileName", file.name);
+    const eventSource = new SSE(edgeFunctionUrl, {
-    formData.append("id", uuid);
+      payload: body,
-    const response = await fetch("/dashboard/upload/process", {
+      headers: {
-      method: "POST",
+        apikey: process.env.NEXT_PUBLIC_SUPABASE_ANON_KEY!,
-      body: formData,
+        Authorization: `Bearer ${process.env.NEXT_PUBLIC_SUPABASE_ANON_KEY}`,
+        "Content-Type": "application/json",
+      },
     });
-    const result = await response.json();
+
-    console.log("File processed successfully:", result);
+    eventSource.onmessage = (event) => {
+      const data = JSON.parse(event.data);
+      console.log("SSE Message:", data);
+
+      if (data.message) {
+        setStatus(data.message);
+      }
+    };
+
+    eventSource.addEventListener("status", (event) => {
+      const data = JSON.parse(event.data);
+      console.log("Status Event:", data);
+
+      setStatus(data.message);
+    });
+
+    eventSource.addEventListener("error", (event) => {
+      console.error("SSE Error:", event);
+      toast.error("An error occurred while processing the document.");
+      setUploading(false);
+      eventSource.close();
+    });
+
+    eventSource.addEventListener("complete", (event) => {
+      const data = JSON.parse(event.data);
+      console.log("Processing Complete:", data);
+      toast.success("Document processing complete!");
+      setUploading(false);
+      eventSource.close();
+    });
+
+    // Invoke the serverless function
+    supabase.functions.invoke("process-document", {
+      body,
+      method: "POST",
+    });
+
+    toast.info(
+      "Document is being processed in the background. You will be notified when it's ready."
+    );
   };
 
   return (
@@ -53,13 +87,22 @@ export default function UploadZone({ user }: { user?: { id: string } }) {
           htmlFor="dropzone-file"
           className="flex flex-col items-center justify-center w-full h-64 border-2 border-muted border-dashed rounded-lg cursor-pointer bg-muted/50"
         >
-          <div className="flex flex-col items-center justify-center pt-5 pb-5">
+          {uploading ? (
-            <CloudUpload className="w-10 h-10 mb-4 text-slate-400" />
+            <div className="flex flex-col items-center justify-center pt-5 pb-5">
-            <p className="mb-2 text-sm text-slate-400">
+              <LoaderCircle className="w-10 h-10 mb-4 text-slate-400 animate-spin" />
-              <span className="font-semibold">Click to upload</span> or drag and
+              <p className="mb-2 text-sm text-slate-400">{status}</p>
-              drop
+            </div>
-            </p>
+          ) : (
-          </div>
+            <>
+              <div className="flex flex-col items-center justify-center pt-5 pb-5">
+                <CloudUpload className="w-10 h-10 mb-4 text-slate-400" />
+                <p className="mb-2 text-sm text-slate-400">
+                  <span className="font-semibold">Click to upload</span> or drag
+                  and drop
+                </p>
+              </div>
+            </>
+          )}
           <input
             id="dropzone-file"
             type="file"

components/nav-actions.tsx

@@ -2,6 +2,7 @@
 
 import * as React from "react";
 import {
+  ALargeSmall,
   ArrowDown,
   ArrowUp,
   Bell,
@@ -112,6 +113,14 @@ export function NavActions({ pages }: { pages: any[] }) {
       {/* <div className="text-muted-foreground hidden font-medium md:inline-block">
         Edit Oct 08
       </div> */}
+      <Popover>
+        <PopoverTrigger asChild>
+          <Button variant="ghost" size="icon" className="h-7 w-7">
+            <ALargeSmall />
+          </Button>
+        </PopoverTrigger>
+        <PopoverContent></PopoverContent>
+      </Popover>
       <Popover>
         <PopoverTrigger asChild>
           <Button variant="ghost" size="icon" className="h-7 w-7">

components/ui/sonner.tsx

@@ -0,0 +1,25 @@
+"use client"
+
+import { useTheme } from "next-themes"
+import { Toaster as Sonner, ToasterProps } from "sonner"
+
+const Toaster = ({ ...props }: ToasterProps) => {
+  const { theme = "system" } = useTheme()
+
+  return (
+    <Sonner
+      theme={theme as ToasterProps["theme"]}
+      className="toaster group"
+      style={
+        {
+          "--normal-bg": "var(--popover)",
+          "--normal-text": "var(--popover-foreground)",
+          "--normal-border": "var(--border)",
+        } as React.CSSProperties
+      }
+      {...props}
+    />
+  )
+}
+
+export { Toaster }

package.json

@@ -30,12 +30,15 @@
     "kokoro-js": "^1.2.0",
     "lucide-react": "^0.486.0",
     "next": "latest",
-    "next-themes": "^0.4.3",
+    "next-themes": "^0.4.6",
+    "p-limit": "^6.2.0",
     "prettier": "^3.3.3",
     "react": "19.0.0",
     "react-dom": "19.0.0",
     "remark": "^15.0.1",
     "remark-html": "^16.0.1",
+    "sonner": "^2.0.3",
+    "sse.js": "^2.6.0",
     "tw-animate-css": "^1.2.5",
     "zod": "^3.24.2"
   },

supabase/.gitignore

@@ -0,0 +1,8 @@
+# Supabase
+.branches
+.temp
+
+# dotenvx
+.env.keys
+.env.local
+.env.*.local

supabase/config.toml

@@ -0,0 +1,308 @@
+# For detailed configuration reference documentation, visit:
+# https://supabase.com/docs/guides/local-development/cli/config
+# A string used to distinguish different Supabase projects on the same host. Defaults to the
+# working directory name when running `supabase init`.
+project_id = "neuro-read"
+
+[api]
+enabled = true
+# Port to use for the API URL.
+port = 54321
+# Schemas to expose in your API. Tables, views and stored procedures in this schema will get API
+# endpoints. `public` and `graphql_public` schemas are included by default.
+schemas = ["public", "graphql_public"]
+# Extra schemas to add to the search_path of every request.
+extra_search_path = ["public", "extensions"]
+# The maximum number of rows returns from a view, table, or stored procedure. Limits payload size
+# for accidental or malicious requests.
+max_rows = 1000
+
+[api.tls]
+# Enable HTTPS endpoints locally using a self-signed certificate.
+enabled = false
+
+[db]
+# Port to use for the local database URL.
+port = 54322
+# Port used by db diff command to initialize the shadow database.
+shadow_port = 54320
+# The database major version to use. This has to be the same as your remote database's. Run `SHOW
+# server_version;` on the remote database to check.
+major_version = 15
+
+[db.pooler]
+enabled = false
+# Port to use for the local connection pooler.
+port = 54329
+# Specifies when a server connection can be reused by other clients.
+# Configure one of the supported pooler modes: `transaction`, `session`.
+pool_mode = "transaction"
+# How many server connections to allow per user/database pair.
+default_pool_size = 20
+# Maximum number of client connections allowed.
+max_client_conn = 100
+
+# [db.vault]
+# secret_key = "env(SECRET_VALUE)"
+
+[db.migrations]
+# Specifies an ordered list of schema files that describe your database.
+# Supports glob patterns relative to supabase directory: "./schemas/*.sql"
+schema_paths = []
+
+[db.seed]
+# If enabled, seeds the database after migrations during a db reset.
+enabled = true
+# Specifies an ordered list of seed files to load during db reset.
+# Supports glob patterns relative to supabase directory: "./seeds/*.sql"
+sql_paths = ["./seed.sql"]
+
+[realtime]
+enabled = true
+# Bind realtime via either IPv4 or IPv6. (default: IPv4)
+# ip_version = "IPv6"
+# The maximum length in bytes of HTTP request headers. (default: 4096)
+# max_header_length = 4096
+
+[studio]
+enabled = true
+# Port to use for Supabase Studio.
+port = 54323
+# External URL of the API server that frontend connects to.
+api_url = "http://127.0.0.1"
+# OpenAI API Key to use for Supabase AI in the Supabase Studio.
+openai_api_key = "env(OPENAI_API_KEY)"
+
+# Email testing server. Emails sent with the local dev setup are not actually sent - rather, they
+# are monitored, and you can view the emails that would have been sent from the web interface.
+[inbucket]
+enabled = true
+# Port to use for the email testing server web interface.
+port = 54324
+# Uncomment to expose additional ports for testing user applications that send emails.
+# smtp_port = 54325
+# pop3_port = 54326
+# admin_email = "admin@email.com"
+# sender_name = "Admin"
+
+[storage]
+enabled = true
+# The maximum file size allowed (e.g. "5MB", "500KB").
+file_size_limit = "50MiB"
+
+# Image transformation API is available to Supabase Pro plan.
+# [storage.image_transformation]
+# enabled = true
+
+# Uncomment to configure local storage buckets
+# [storage.buckets.images]
+# public = false
+# file_size_limit = "50MiB"
+# allowed_mime_types = ["image/png", "image/jpeg"]
+# objects_path = "./images"
+
+[auth]
+enabled = true
+# The base URL of your website. Used as an allow-list for redirects and for constructing URLs used
+# in emails.
+site_url = "http://127.0.0.1:3000"
+# A list of *exact* URLs that auth providers are permitted to redirect to post authentication.
+additional_redirect_urls = ["https://127.0.0.1:3000"]
+# How long tokens are valid for, in seconds. Defaults to 3600 (1 hour), maximum 604,800 (1 week).
+jwt_expiry = 3600
+# If disabled, the refresh token will never expire.
+enable_refresh_token_rotation = true
+# Allows refresh tokens to be reused after expiry, up to the specified interval in seconds.
+# Requires enable_refresh_token_rotation = true.
+refresh_token_reuse_interval = 10
+# Allow/disallow new user signups to your project.
+enable_signup = true
+# Allow/disallow anonymous sign-ins to your project.
+enable_anonymous_sign_ins = false
+# Allow/disallow testing manual linking of accounts
+enable_manual_linking = false
+# Passwords shorter than this value will be rejected as weak. Minimum 6, recommended 8 or more.
+minimum_password_length = 6
+# Passwords that do not meet the following requirements will be rejected as weak. Supported values
+# are: `letters_digits`, `lower_upper_letters_digits`, `lower_upper_letters_digits_symbols`
+password_requirements = ""
+
+[auth.rate_limit]
+# Number of emails that can be sent per hour. Requires auth.email.smtp to be enabled.
+email_sent = 2
+# Number of SMS messages that can be sent per hour. Requires auth.sms to be enabled.
+sms_sent = 30
+# Number of anonymous sign-ins that can be made per hour per IP address. Requires enable_anonymous_sign_ins = true.
+anonymous_users = 30
+# Number of sessions that can be refreshed in a 5 minute interval per IP address.
+token_refresh = 150
+# Number of sign up and sign-in requests that can be made in a 5 minute interval per IP address (excludes anonymous users).
+sign_in_sign_ups = 30
+# Number of OTP / Magic link verifications that can be made in a 5 minute interval per IP address.
+token_verifications = 30
+
+# Configure one of the supported captcha providers: `hcaptcha`, `turnstile`.
+# [auth.captcha]
+# enabled = true
+# provider = "hcaptcha"
+# secret = ""
+
+[auth.email]
+# Allow/disallow new user signups via email to your project.
+enable_signup = true
+# If enabled, a user will be required to confirm any email change on both the old, and new email
+# addresses. If disabled, only the new email is required to confirm.
+double_confirm_changes = true
+# If enabled, users need to confirm their email address before signing in.
+enable_confirmations = false
+# If enabled, users will need to reauthenticate or have logged in recently to change their password.
+secure_password_change = false
+# Controls the minimum amount of time that must pass before sending another signup confirmation or password reset email.
+max_frequency = "1s"
+# Number of characters used in the email OTP.
+otp_length = 6
+# Number of seconds before the email OTP expires (defaults to 1 hour).
+otp_expiry = 3600
+
+# Use a production-ready SMTP server
+# [auth.email.smtp]
+# enabled = true
+# host = "smtp.sendgrid.net"
+# port = 587
+# user = "apikey"
+# pass = "env(SENDGRID_API_KEY)"
+# admin_email = "admin@email.com"
+# sender_name = "Admin"
+
+# Uncomment to customize email template
+# [auth.email.template.invite]
+# subject = "You have been invited"
+# content_path = "./supabase/templates/invite.html"
+
+[auth.sms]
+# Allow/disallow new user signups via SMS to your project.
+enable_signup = false
+# If enabled, users need to confirm their phone number before signing in.
+enable_confirmations = false
+# Template for sending OTP to users
+template = "Your code is {{ .Code }}"
+# Controls the minimum amount of time that must pass before sending another sms otp.
+max_frequency = "5s"
+
+# Use pre-defined map of phone number to OTP for testing.
+# [auth.sms.test_otp]
+# 4152127777 = "123456"
+
+# Configure logged in session timeouts.
+# [auth.sessions]
+# Force log out after the specified duration.
+# timebox = "24h"
+# Force log out if the user has been inactive longer than the specified duration.
+# inactivity_timeout = "8h"
+
+# This hook runs before a token is issued and allows you to add additional claims based on the authentication method used.
+# [auth.hook.custom_access_token]
+# enabled = true
+# uri = "pg-functions://<database>/<schema>/<hook_name>"
+
+# Configure one of the supported SMS providers: `twilio`, `twilio_verify`, `messagebird`, `textlocal`, `vonage`.
+[auth.sms.twilio]
+enabled = false
+account_sid = ""
+message_service_sid = ""
+# DO NOT commit your Twilio auth token to git. Use environment variable substitution instead:
+auth_token = "env(SUPABASE_AUTH_SMS_TWILIO_AUTH_TOKEN)"
+
+# Multi-factor-authentication is available to Supabase Pro plan.
+[auth.mfa]
+# Control how many MFA factors can be enrolled at once per user.
+max_enrolled_factors = 10
+
+# Control MFA via App Authenticator (TOTP)
+[auth.mfa.totp]
+enroll_enabled = false
+verify_enabled = false
+
+# Configure MFA via Phone Messaging
+[auth.mfa.phone]
+enroll_enabled = false
+verify_enabled = false
+otp_length = 6
+template = "Your code is {{ .Code }}"
+max_frequency = "5s"
+
+# Configure MFA via WebAuthn
+# [auth.mfa.web_authn]
+# enroll_enabled = true
+# verify_enabled = true
+
+# Use an external OAuth provider. The full list of providers are: `apple`, `azure`, `bitbucket`,
+# `discord`, `facebook`, `github`, `gitlab`, `google`, `keycloak`, `linkedin_oidc`, `notion`, `twitch`,
+# `twitter`, `slack`, `spotify`, `workos`, `zoom`.
+[auth.external.apple]
+enabled = false
+client_id = ""
+# DO NOT commit your OAuth provider secret to git. Use environment variable substitution instead:
+secret = "env(SUPABASE_AUTH_EXTERNAL_APPLE_SECRET)"
+# Overrides the default auth redirectUrl.
+redirect_uri = ""
+# Overrides the default auth provider URL. Used to support self-hosted gitlab, single-tenant Azure,
+# or any other third-party OIDC providers.
+url = ""
+# If enabled, the nonce check will be skipped. Required for local sign in with Google auth.
+skip_nonce_check = false
+
+# Use Firebase Auth as a third-party provider alongside Supabase Auth.
+[auth.third_party.firebase]
+enabled = false
+# project_id = "my-firebase-project"
+
+# Use Auth0 as a third-party provider alongside Supabase Auth.
+[auth.third_party.auth0]
+enabled = false
+# tenant = "my-auth0-tenant"
+# tenant_region = "us"
+
+# Use AWS Cognito (Amplify) as a third-party provider alongside Supabase Auth.
+[auth.third_party.aws_cognito]
+enabled = false
+# user_pool_id = "my-user-pool-id"
+# user_pool_region = "us-east-1"
+
+# Use Clerk as a third-party provider alongside Supabase Auth.
+[auth.third_party.clerk]
+enabled = false
+# Obtain from https://clerk.com/setup/supabase
+# domain = "example.clerk.accounts.dev"
+
+[edge_runtime]
+enabled = true
+# Configure one of the supported request policies: `oneshot`, `per_worker`.
+# Use `oneshot` for hot reload, or `per_worker` for load testing.
+policy = "oneshot"
+# Port to attach the Chrome inspector for debugging edge functions.
+inspector_port = 8083
+# The Deno major version to use.
+deno_version = 1
+
+# [edge_runtime.secrets]
+# secret_key = "env(SECRET_VALUE)"
+
+[analytics]
+enabled = true
+port = 54327
+# Configure one of the supported backends: `postgres`, `bigquery`.
+backend = "postgres"
+
+# Experimental features may be deprecated any time
+[experimental]
+# Configures Postgres storage engine to use OrioleDB (S3)
+orioledb_version = ""
+# Configures S3 bucket URL, eg. <bucket_name>.s3-<region>.amazonaws.com
+s3_host = "env(S3_HOST)"
+# Configures S3 bucket region, eg. us-east-1
+s3_region = "env(S3_REGION)"
+# Configures AWS_ACCESS_KEY_ID for S3 bucket
+s3_access_key = "env(S3_ACCESS_KEY)"
+# Configures AWS_SECRET_ACCESS_KEY for S3 bucket
+s3_secret_key = "env(S3_SECRET_KEY)"

supabase/functions/process-document.ts

@@ -0,0 +1,285 @@
+import "jsr:@supabase/functions-js/edge-runtime.d.ts";
+import { createClient } from "jsr:@supabase/supabase-js@2";
+import { Mistral } from "npm:@mistralai/mistralai";
+import pLimit from "npm:p-limit";
+
+export const corsHeaders = {
+  "Access-Control-Allow-Origin": "*",
+  "Access-Control-Allow-Headers":
+    "authorization, x-client-info, apikey, content-type",
+};
+
+const apiKey = Deno.env.get("MISTRAL_API_KEY");
+const client = new Mistral({
+  apiKey: apiKey,
+});
+const PROCESSING_PROMPT = `
+You are a document processing AI. Your task is to process the Markdown text scanned from a document page and return it in a clean and structured format.
+
+The textual page data should only be returned in valid Markdown format. Use proper headings and subheadings to structure the content.
+Any images should be included.
+Do not return the Markdown as a code block, only as a raw string, without any new lines.
+
+The Markdown should be human-readable and well-formatted.
+`;
+
+Deno.serve(async (req) => {
+  console.log("Request received:", req.method);
+
+  if (req.method === "OPTIONS") {
+    return new Response("ok", { headers: corsHeaders });
+  }
+
+  if (req.method === "POST") {
+    console.log("Processing POST request...");
+
+    const { body, writable } = new TransformStream();
+    const writer = writable.getWriter();
+
+    // Set up the SSE response
+    const headers = new Headers({
+      "Content-Type": "text/event-stream",
+      "Cache-Control": "no-cache",
+      Connection: "keep-alive",
+      ...corsHeaders,
+    });
+
+    const sendEvent = async (event: string, data: any) => {
+      const message = `event: ${event}\ndata: ${JSON.stringify(data)}\n\n`;
+      console.log("Sending event:", message);
+      await writer.write(new TextEncoder().encode(message));
+    };
+
+    // Start streaming updates
+    sendEvent("status", { message: "Initializing..." });
+
+    try {
+      const supabase = createClient(
+        Deno.env.get("SUPABASE_URL"),
+        Deno.env.get("SUPABASE_ANON_KEY")
+      );
+
+      const formData = await req.formData();
+      const file = formData.get("file");
+      const jwt = formData.get("jwt");
+      const fileName = file.name;
+      const uuid = crypto.randomUUID();
+
+      console.log("Generated UUID:", uuid);
+      sendEvent("status", { message: "Generated UUID", uuid });
+
+      const user = await supabase.auth.getUser(jwt);
+      console.log("Authenticated user:", user);
+      sendEvent("status", { message: "Authenticated user", user });
+
+      const { data: storageData, error: storageError } = await supabase.storage
+        .from("documents")
+        .upload(`${user!.id}/${uuid}.pdf`, file);
+
+      if (storageError) {
+        console.error("Error uploading file to storage:", storageError);
+        sendEvent("error", {
+          message: "Error uploading file to storage",
+          error: storageError,
+        });
+        throw new Error("File upload failed");
+      } else {
+        console.log("File uploaded to storage:", storageData);
+        sendEvent("status", {
+          message: "File uploaded to storage",
+          storageData,
+        });
+      }
+
+      const { error: docError } = await supabase.from("documents").insert({
+        id: uuid,
+        file_name: file.name,
+        owner: user!.id,
+        raw_file: storageData.id,
+        is_processing: true,
+      });
+
+      if (docError) {
+        console.error("Error inserting document record:", docError);
+        sendEvent("error", {
+          message: "Error inserting document record",
+          error: docError,
+        });
+        throw new Error("Document record insertion failed");
+      } else {
+        console.log("Document record inserted successfully.");
+        sendEvent("status", {
+          message: "Document record inserted successfully",
+        });
+      }
+
+      console.log("Uploading file to Mistral...");
+      sendEvent("status", { message: "Uploading file to Mistral..." });
+
+      const uploaded_pdf = await client.files.upload({
+        file: {
+          fileName,
+          content: file,
+        },
+        purpose: "ocr",
+      });
+      console.log("File uploaded to Mistral:", uploaded_pdf);
+      sendEvent("status", {
+        message: "File uploaded to Mistral",
+        uploaded_pdf,
+      });
+
+      const signedUrl = await client.files.getSignedUrl({
+        fileId: uploaded_pdf.id,
+      });
+      console.log("Generated signed URL:", signedUrl);
+      sendEvent("status", { message: "Generated signed URL", signedUrl });
+
+      console.log("Processing OCR...");
+      sendEvent("status", { message: "Processing OCR..." });
+
+      const ocrResponse = await client.ocr.process({
+        model: "mistral-ocr-latest",
+        document: {
+          type: "document_url",
+          documentUrl: signedUrl.url,
+        },
+      });
+      console.log("OCR response received:", ocrResponse);
+      sendEvent("status", { message: "OCR response received", ocrResponse });
+
+      const limit = pLimit(1);
+      const promises = [];
+
+      for (const page of ocrResponse.pages) {
+        console.log("Processing page:", page.index);
+        sendEvent("status", { message: `Processing page ${page.index}` });
+
+        const pagePromise = limit(async () => {
+          console.log(`Processing page ${page.index} with Mistral...`);
+
+          const response = await client.chat.complete({
+            model: "mistral-small-latest",
+            messages: [
+              {
+                role: "user",
+                content: [
+                  {
+                    type: "text",
+                    text: PROCESSING_PROMPT,
+                  },
+                ],
+              },
+            ],
+          });
+
+          if (!response.choices) {
+            console.error("No choices in response for page:", page.index);
+            sendEvent("error", {
+              message: `No choices in response for page ${page.index}`,
+            });
+            return;
+          }
+
+          console.log("Response received for page:", page.index);
+          sendEvent("status", {
+            message: `Response received for page ${page.index}`,
+          });
+
+          const imageData = {};
+          if (page.images.length > 0) {
+            console.log(
+              `Processing ${page.images.length} images for page ${page.index}...`
+            );
+            sendEvent("status", {
+              message: `Processing images for page ${page.index}`,
+            });
+            for (const img of page.images) {
+              imageData[img.id] = img.imageBase64;
+            }
+          }
+
+          if (response.choices[0].message.content) {
+            console.log("Generating Markdown for page:", page.index);
+            sendEvent("status", {
+              message: `Generating Markdown for page ${page.index}`,
+            });
+            const markdown = replaceImagesInMarkdown(
+              response.choices[0].message.content.toString(),
+              imageData
+            );
+            return {
+              ...page,
+              markdown,
+            };
+          } else {
+            console.error("Message content is undefined for page:", page.index);
+            sendEvent("error", {
+              message: `Message content is undefined for page ${page.index}`,
+            });
+          }
+        });
+
+        promises.push(pagePromise);
+      }
+
+      console.log("Waiting for all pages to be processed...");
+      sendEvent("status", {
+        message: "Waiting for all pages to be processed...",
+      });
+      const results = await Promise.all(promises);
+      console.log("All pages processed. Results:", results);
+      sendEvent("status", { message: "All pages processed", results });
+
+      const sortedResults = results.sort((a, b) => a.index - b.index);
+      console.log("Sorted results:", sortedResults);
+      sendEvent("status", { message: "Sorted results", sortedResults });
+
+      const { data, error } = await supabase
+        .from("documents")
+        .update({
+          ocr_data: sortedResults,
+          is_processing: false,
+        })
+        .eq("id", uuid);
+
+      if (error) {
+        console.error("Error updating document record:", error);
+        sendEvent("error", {
+          message: "Error updating document record",
+          error,
+        });
+        throw new Error("Document record update failed");
+      }
+
+      console.log("Document record updated successfully.");
+      sendEvent("status", { message: "Document record updated successfully" });
+      sendEvent("status", { completed: true, uuid });
+    } catch (error) {
+      console.error("Error during processing:", error);
+      sendEvent("error", { message: "Error during processing", error });
+    } finally {
+      console.log("Closing SSE stream...");
+      await writer.close();
+    }
+
+    return new Response(body, { headers });
+  }
+
+  console.error("Method not allowed:", req.method);
+  return new Response("Method not allowed", {
+    status: 405,
+  });
+});
+
+function replaceImagesInMarkdown(markdownStr, imagesDict) {
+  console.log("Replacing images in Markdown...");
+  for (const [imgName, base64Str] of Object.entries(imagesDict)) {
+    markdownStr = markdownStr.replace(
+      new RegExp(`!\\[${imgName}\\]\\(${imgName}\\)`, "g"),
+      `![${imgName}](${base64Str})`
+    );
+  }
+  console.log("Image replacement complete.");
+  return markdownStr;
+}

utils/supabase/types.ts

@@ -14,6 +14,7 @@ export type Database = {
           created_at: string
           file_name: string
           id: string
+          is_processing: boolean
           ocr_data: Json | null
           owner: string
           raw_file: string
@@ -22,6 +23,7 @@ export type Database = {
           created_at?: string
           file_name: string
           id?: string
+          is_processing?: boolean
           ocr_data?: Json | null
           owner: string
           raw_file: string
@@ -30,6 +32,7 @@ export type Database = {
           created_at?: string
           file_name?: string
           id?: string
+          is_processing?: boolean
           ocr_data?: Json | null
           owner?: string
           raw_file?: string
@@ -52,27 +55,29 @@ export type Database = {
   }
 }
 
-type PublicSchema = Database[Extract<keyof Database, "public">]
+type DefaultSchema = Database[Extract<keyof Database, "public">]
 
 export type Tables<
-  PublicTableNameOrOptions extends
+  DefaultSchemaTableNameOrOptions extends
-    | keyof (PublicSchema["Tables"] & PublicSchema["Views"])
+    | keyof (DefaultSchema["Tables"] & DefaultSchema["Views"])
     | { schema: keyof Database },
-  TableName extends PublicTableNameOrOptions extends { schema: keyof Database }
+  TableName extends DefaultSchemaTableNameOrOptions extends {
-    ? keyof (Database[PublicTableNameOrOptions["schema"]]["Tables"] &
+    schema: keyof Database
-        Database[PublicTableNameOrOptions["schema"]]["Views"])
+  }
+    ? keyof (Database[DefaultSchemaTableNameOrOptions["schema"]]["Tables"] &
+        Database[DefaultSchemaTableNameOrOptions["schema"]]["Views"])
     : never = never,
-> = PublicTableNameOrOptions extends { schema: keyof Database }
+> = DefaultSchemaTableNameOrOptions extends { schema: keyof Database }
-  ? (Database[PublicTableNameOrOptions["schema"]]["Tables"] &
+  ? (Database[DefaultSchemaTableNameOrOptions["schema"]]["Tables"] &
-      Database[PublicTableNameOrOptions["schema"]]["Views"])[TableName] extends {
+      Database[DefaultSchemaTableNameOrOptions["schema"]]["Views"])[TableName] extends {
       Row: infer R
     }
     ? R
     : never
-  : PublicTableNameOrOptions extends keyof (PublicSchema["Tables"] &
+  : DefaultSchemaTableNameOrOptions extends keyof (DefaultSchema["Tables"] &
-        PublicSchema["Views"])
+        DefaultSchema["Views"])
-    ? (PublicSchema["Tables"] &
+    ? (DefaultSchema["Tables"] &
-        PublicSchema["Views"])[PublicTableNameOrOptions] extends {
+        DefaultSchema["Views"])[DefaultSchemaTableNameOrOptions] extends {
         Row: infer R
       }
       ? R
@@ -80,20 +85,22 @@ export type Tables<
     : never
 
 export type TablesInsert<
-  PublicTableNameOrOptions extends
+  DefaultSchemaTableNameOrOptions extends
-    | keyof PublicSchema["Tables"]
+    | keyof DefaultSchema["Tables"]
     | { schema: keyof Database },
-  TableName extends PublicTableNameOrOptions extends { schema: keyof Database }
+  TableName extends DefaultSchemaTableNameOrOptions extends {
-    ? keyof Database[PublicTableNameOrOptions["schema"]]["Tables"]
+    schema: keyof Database
+  }
+    ? keyof Database[DefaultSchemaTableNameOrOptions["schema"]]["Tables"]
     : never = never,
-> = PublicTableNameOrOptions extends { schema: keyof Database }
+> = DefaultSchemaTableNameOrOptions extends { schema: keyof Database }
-  ? Database[PublicTableNameOrOptions["schema"]]["Tables"][TableName] extends {
+  ? Database[DefaultSchemaTableNameOrOptions["schema"]]["Tables"][TableName] extends {
       Insert: infer I
     }
     ? I
     : never
-  : PublicTableNameOrOptions extends keyof PublicSchema["Tables"]
+  : DefaultSchemaTableNameOrOptions extends keyof DefaultSchema["Tables"]
-    ? PublicSchema["Tables"][PublicTableNameOrOptions] extends {
+    ? DefaultSchema["Tables"][DefaultSchemaTableNameOrOptions] extends {
         Insert: infer I
       }
       ? I
@@ -101,20 +108,22 @@ export type TablesInsert<
     : never
 
 export type TablesUpdate<
-  PublicTableNameOrOptions extends
+  DefaultSchemaTableNameOrOptions extends
-    | keyof PublicSchema["Tables"]
+    | keyof DefaultSchema["Tables"]
     | { schema: keyof Database },
-  TableName extends PublicTableNameOrOptions extends { schema: keyof Database }
+  TableName extends DefaultSchemaTableNameOrOptions extends {
-    ? keyof Database[PublicTableNameOrOptions["schema"]]["Tables"]
+    schema: keyof Database
+  }
+    ? keyof Database[DefaultSchemaTableNameOrOptions["schema"]]["Tables"]
     : never = never,
-> = PublicTableNameOrOptions extends { schema: keyof Database }
+> = DefaultSchemaTableNameOrOptions extends { schema: keyof Database }
-  ? Database[PublicTableNameOrOptions["schema"]]["Tables"][TableName] extends {
+  ? Database[DefaultSchemaTableNameOrOptions["schema"]]["Tables"][TableName] extends {
       Update: infer U
     }
     ? U
     : never
-  : PublicTableNameOrOptions extends keyof PublicSchema["Tables"]
+  : DefaultSchemaTableNameOrOptions extends keyof DefaultSchema["Tables"]
-    ? PublicSchema["Tables"][PublicTableNameOrOptions] extends {
+    ? DefaultSchema["Tables"][DefaultSchemaTableNameOrOptions] extends {
         Update: infer U
       }
       ? U
@@ -122,21 +131,23 @@ export type TablesUpdate<
     : never
 
 export type Enums<
-  PublicEnumNameOrOptions extends
+  DefaultSchemaEnumNameOrOptions extends
-    | keyof PublicSchema["Enums"]
+    | keyof DefaultSchema["Enums"]
     | { schema: keyof Database },
-  EnumName extends PublicEnumNameOrOptions extends { schema: keyof Database }
+  EnumName extends DefaultSchemaEnumNameOrOptions extends {
-    ? keyof Database[PublicEnumNameOrOptions["schema"]]["Enums"]
+    schema: keyof Database
+  }
+    ? keyof Database[DefaultSchemaEnumNameOrOptions["schema"]]["Enums"]
     : never = never,
-> = PublicEnumNameOrOptions extends { schema: keyof Database }
+> = DefaultSchemaEnumNameOrOptions extends { schema: keyof Database }
-  ? Database[PublicEnumNameOrOptions["schema"]]["Enums"][EnumName]
+  ? Database[DefaultSchemaEnumNameOrOptions["schema"]]["Enums"][EnumName]
-  : PublicEnumNameOrOptions extends keyof PublicSchema["Enums"]
+  : DefaultSchemaEnumNameOrOptions extends keyof DefaultSchema["Enums"]
-    ? PublicSchema["Enums"][PublicEnumNameOrOptions]
+    ? DefaultSchema["Enums"][DefaultSchemaEnumNameOrOptions]
     : never
 
 export type CompositeTypes<
   PublicCompositeTypeNameOrOptions extends
-    | keyof PublicSchema["CompositeTypes"]
+    | keyof DefaultSchema["CompositeTypes"]
     | { schema: keyof Database },
   CompositeTypeName extends PublicCompositeTypeNameOrOptions extends {
     schema: keyof Database
@@ -145,6 +156,12 @@ export type CompositeTypes<
     : never = never,
 > = PublicCompositeTypeNameOrOptions extends { schema: keyof Database }
   ? Database[PublicCompositeTypeNameOrOptions["schema"]]["CompositeTypes"][CompositeTypeName]
-  : PublicCompositeTypeNameOrOptions extends keyof PublicSchema["CompositeTypes"]
+  : PublicCompositeTypeNameOrOptions extends keyof DefaultSchema["CompositeTypes"]
-    ? PublicSchema["CompositeTypes"][PublicCompositeTypeNameOrOptions]
+    ? DefaultSchema["CompositeTypes"][PublicCompositeTypeNameOrOptions]
     : never
+
+export const Constants = {
+  public: {
+    Enums: {},
+  },
+} as const