case sensitive bug in compilation on linux

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 AgentOps-AI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,37 @@
+<p align="center">
+  <img src="https://raw.githubusercontent.com/hackgoofer/IFS.AI/ef29cbb223b86d12d2d497057601a00f92a7cfb0/ifs.ai/public/social.png?token=GHSAT0AAAAAACFT7GCPZQCBJJOQMNYU66IOZQI4DBA" height="300" alt="IFS.AI Logo"/>
+</p>
+
+<p align="center">
+  <em> Embrace every part of you with through conversation. Inspired by Internal Family System Therapy </em>
+</p>
+
+## What is Internal Family System Therapy
+IFS is a transformative tool that conceives of every human being as a system of protective and wounded inner parts led by a core Self. We believe the mind is naturally multiple and that is a good thing. Just like members of a family, inner parts are forced from their valuable states into extreme roles within us. Self is in everyone. It can’t be damaged. It knows how to heal. 
+
+More Resources about IFS:
+- [Podcast](https://mormondiscussionpodcast.org/2023/06/internal-family-systems-therapy-talking-to-your-parts-almost-awakened-156/)
+- [Video](https://youtu.be/DdZZ7sTX840)
+
+
+## Getting Started :rocket:
+
+### Frontend:
+- Go inside ifs.ai folder
+- Copy .env.example to .env
+- Fill in .env
+- Required Services are: replicate, uploadthing
+
+### Backend:
+- Go inside ifs.py folder
+- install relevant requirements, see backend README
+- Copy .env.example to .env
+- Backend Required Services are: De-ID, Mistral, OpenAI
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/hackgoofer/IFS.AI/ef29cbb223b86d12d2d497057601a00f92a7cfb0/ifs.ai/public/social.png?token=GHSAT0AAAAAACFT7GCPZQCBJJOQMNYU66IOZQI4DBA" height="300" alt="IFS.AI Logo"/>
+</p>
+
+## ✨ Demo
+For the best demo experience, we will be launching a hosted version SOON. Stay Tuned.
+

ifs.ai/.env.example

@@ -1,3 +1,6 @@
 # uploadthing API key, get yours here: https://uploadthing.com/dashboard/
 UPLOADTHING_SECRET=
-UPLOADTHING_APP_ID=
+UPLOADTHING_APP_ID=
+
+# Replicate token, get yours here https://replicate.com/account/api-tokens
+REPLICATE_API_TOKEN=

ifs.ai/.gitignore

@@ -5,6 +5,7 @@
 /.pnp
 .pnp.js
 .yarn/install-state.gz
+.env
 
 # testing
 /coverage

ifs.ai/app/DIDVideoStream.tsx

@@ -1,40 +1,60 @@
 import { useEffect, useRef, useState } from "react";
 import { Button } from "@/components/ui/button";
+import { useToast } from "@/components/ui/use-toast";
 
 const URL = "http://localhost:5000";
 
+/**
+ * DIDVideoStream component
+ * This component handles video streaming using a direct URL.
+ * It fetches a video from a specified URL and displays it in a video element.
+ *
+ * Props:
+ * - avatarUrl: string - The URL of the avatar image to be displayed as a poster.
+ * - utterance: string - The text utterance to be sent to the server for generating the video.
+ */
 export default function DIDVideoStream({ avatarUrl, utterance }: { avatarUrl: string; utterance: string }) {
   const videoElement = useRef<HTMLVideoElement>(null);
   const [isFetching, setIsFetching] = useState(false);
-  // call client.say when utterance changes or when peer connection is 'connected'
+  const { toast } = useToast();
+
   useEffect(() => {
-    console.log("utterance or avatars changed");
     const doSay = async () => {
-      console.log("utterance or avatars changed");
-      setIsFetching(true);
-      // POST image_url and text to URL
-      const result = await fetch(`${URL}/create_talk`, {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-        },
-        body: JSON.stringify({ image_url: avatarUrl, text: utterance }),
-      });
-      setIsFetching(false);
-      const data = await result;
-      const text = await data.text();
-      console.log("setting video src to", text);
-      // TODO: get this working
-      videoElement?.current?.setAttribute("src", text);
+      try {
+        setIsFetching(true);
+
+        const response = await fetch(`${URL}/create_talk`, {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/json",
+          },
+          body: JSON.stringify({ image_url: avatarUrl, text: utterance }),
+        });
+
+        if (!response.ok) {
+          throw new Error(`HTTP error! status: ${response.status}`);
+        }
+
+        const data = await response.text();
+        console.log("Setting video src to", data);
+        videoElement?.current?.setAttribute("src", data);
+      } catch (error) {
+        console.error("Error fetching video:", error);
+        toast({ title: "Error fetching video", description: JSON.stringify(error) });
+        // Display an error message to the user or handle the error gracefully
+      } finally {
+        setIsFetching(false);
+      }
     };
+
     doSay();
-  }, [utterance, avatarUrl]);
+  }, [utterance, avatarUrl, toast]);
 
   return (
     <div>
       <div className="video-wrapper">
         <div>
-          <video poster={avatarUrl} width="400" height="400" autoPlay></video>
+          <video ref={videoElement} poster={avatarUrl} width="400" height="400" autoPlay></video>
         </div>
       </div>
       <br />

ifs.ai/app/DIDWebRTCVideoStream.tsx

@@ -4,7 +4,7 @@ import { initializeStreamingClient } from "./streaming-client-api";
 // import shadcn button:
 import { Button } from "@/components/ui/button";
 
-export default function DIDVideoStream({ avatarUrl, utterance }: { avatarUrl: string }) {
+export default function DIDVideoStream({ avatarUrl, utterance }: { avatarUrl: string; utterance: string }) {
   const videoElementRef = useRef(null);
   const [iceGatheringStatusLabel, setIceGatheringStatusLabel] = useState("");
   const [iceStatusLabel, setIceStatusLabel] = useState("");

ifs.ai/app/api/uploadthing/core.ts

@@ -1,10 +1,53 @@
 import { createUploadthing, type FileRouter } from "uploadthing/next";
 import { UploadThingError } from "uploadthing/server";
+import Replicate from "replicate";
+import { PartImageUrls } from "@/app/constants";
 
 const f = createUploadthing();
 
 const auth = (req: Request) => ({ id: "fakeUserId" }); // Fake auth function
 
+const replicate = new Replicate({
+  auth: process.env.REPLICATE_API_TOKEN,
+});
+
+async function makePartImages(inputUrl: string): Promise<PartImageUrls> {
+  const prompts = {
+    manager:
+      "A photo of a person img upclose, facing camera, looking mature confident and controlled, professional outfit, upright posture, orderly surroundings, muted background colors, symbols of achievement, sense of discipline and responsibility",
+    firefighter:
+      "A photo of a person img upclose, facing camera, fierce expression, intense eyes, firefighter, bold outfit, fiery background colors, sense of urgency and strength",
+    exile:
+      "A photo of a child img upclose, facing camera, young and extremely vulnerable, infant, eyes filled with fear and uncertainty, tattered and worn clothing, dark and shadowy background colors, bruises and scratches visible on skin, sense of deep isolation, desperately seeking safety, care, and acceptance",
+  };
+
+  return Object.fromEntries(
+    await Promise.all(
+      Object.entries(prompts).map(async ([part, prompt]) => [
+        part,
+        (
+          await replicate.run(
+            "tencentarc/photomaker:ddfc2b08d209f9fa8c1eca692712918bd449f695dabb4a958da31802a9570fe4",
+            {
+              input: {
+                prompt: prompt,
+                num_steps: 40,
+                style_name: "Photographic (Default)",
+                input_image: inputUrl,
+                num_outputs: 1,
+                guidance_scale: 5,
+                negative_prompt:
+                  "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+                style_strength_ratio: 20,
+              },
+            },
+          )
+        )[0],
+      ]),
+    ),
+  );
+}
+
 // FileRouter for your app, can contain multiple FileRoutes
 export const fileRouter = {
   // Define as many FileRoutes as you like, each with a unique routeSlug
@@ -25,9 +68,12 @@ export const fileRouter = {
       console.log("Upload complete for userId:", metadata.userId);
 
       console.log("file url", file.url);
+      const partImageUrls = await makePartImages(file.url);
+
+      console.log("Got image urls", partImageUrls);
 
       // !!! Whatever is returned here is sent to the clientside `onClientUploadComplete` callback
-      return { uploadedBy: metadata.userId, imageUrl: file.url };
+      return { uploadedBy: metadata.userId, imageUrl: file.url, partImageUrls: partImageUrls };
     }),
 } satisfies FileRouter;
 

ifs.ai/app/audio-test/page.tsx

@@ -0,0 +1,32 @@
+"use client";
+import { Input } from "@/components/ui/input";
+import { Button } from "@/components/ui/button";
+import { MicIcon, SendIcon } from "lucide-react";
+import { useState } from "react";
+import SpeechToText from "@/components/ui/speech-to-text";
+
+export default function Page() {
+  const [message, setMessage] = useState("");
+  return (
+    <main className="flex min-h-svh flex-col px-24 py-10">
+      <div className="flex w-full flex-grow basis-0 space-x-4">
+        <div className="h-full w-4/5 flex-col">
+          <div className="flex h-full flex-col justify-between">
+            <SpeechToText
+              onTranscript={(transcript: string) => {
+                console.log(transcript);
+                setMessage(transcript);
+              }}
+            />
+            <Input
+              value={message}
+              onChange={(e) => setMessage(e.target.value)}
+              placeholder="Type a message..."
+              className="flex-grow"
+            />
+          </div>
+        </div>
+      </div>
+    </main>
+  );
+}