Adding audio and image/video files needed for loading the Gradio UI, …

…and update the UI Python function (#1034)

Signed-off-by: Chun Tao <chun.tao@intel.com>
Signed-off-by: rbrugaro <rita.brugarolas.brufau@intel.com>
Signed-off-by: ZePan110 <ze.pan@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Signed-off-by: chen, suyue <suyue.chen@intel.com>
Co-authored-by: rbrugaro <rita.brugarolas.brufau@intel.com>
Co-authored-by: ZePan110 <ze.pan@intel.com>
Co-authored-by: kevinintel <hanwen.chang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>

AvatarChatbot/.gitignore

@@ -4,3 +4,5 @@
 *.log
 docker_compose/intel/cpu/xeon/data
 docker_compose/intel/hpu/gaudi/data
+inputs/
+outputs/

AvatarChatbot/README.md

@@ -75,7 +75,7 @@ The AvatarChatbot service can be deployed on either Intel Gaudi2 AI Accelerator
 
 ### Deploy AvatarChatbot on Gaudi
 
-Refer to the [Gaudi Guide](./docker_compose/intel/hpu/gaudi/README.md) for instructions on deploying AvatarChatbot on Gaudi.
+Refer to the [Gaudi Guide](./docker_compose/intel/hpu/gaudi/README.md) for instructions on deploying AvatarChatbot on Gaudi, and on setting up an UI for the application.
 
 ### Deploy AvatarChatbot on Xeon
 

AvatarChatbot/docker_compose/intel/cpu/xeon/README.md

@@ -96,9 +96,9 @@ export ANIMATION_SERVICE_PORT=3008
 ```bash
 export DEVICE="cpu"
 export WAV2LIP_PORT=7860
-export INFERENCE_MODE='wav2lip+gfpgan'
+export INFERENCE_MODE='wav2lip_only'
 export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-export FACE="assets/img/avatar5.png"
+export FACE="assets/img/avatar1.jpg"
 # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
 export AUDIO='None'
 export FACESIZE=96
@@ -188,13 +188,16 @@ The output file will be saved in the current working directory, as `${PWD}` is m
 
 ## Gradio UI
 
-Follow the instructions in [Build Mega Service of AudioQnA on Gaudi](https://github.com/opea-project/GenAIExamples/blob/main/AudioQnA/docker_compose/intel/hpu/gaudi/README.md) to build necessary Docker images and start the AudioQnA MegaService with the endpoint `http://localhost:3008/v1/audioqna`. Then run the following command to start the Gradio UI:
-
 ```bash
-cd GenAIExamples/AvatarChatbot/docker/ui/gradio
-python3 app_gradio_demo.py
+cd $WORKPATH/GenAIExamples/AvatarChatbot
+python3 ui/gradio/app_gradio_demo_avatarchatbot.py
 ```
 
+The UI can be viewed at http://${host_ip}:7861  
+<img src="../../../../assets/img/UI.png" alt="UI Example" width="60%">  
+In the current version v1.0, you need to set the avatar figure image/video and the DL model choice in the environment variables before starting AvatarChatbot backend service and running the UI. Please just customize the audio question in the UI.  
+\*\* We will enable change of avatar figure between runs in v2.0
+
 ## Troubleshooting
 
 ```bash

AvatarChatbot/docker_compose/intel/hpu/gaudi/README.md

@@ -96,9 +96,9 @@ export ANIMATION_SERVICE_PORT=3008
 ```bash
 export DEVICE="hpu"
 export WAV2LIP_PORT=7860
-export INFERENCE_MODE='wav2lip+gfpgan'
+export INFERENCE_MODE='wav2lip_only'
 export CHECKPOINT_PATH='/usr/local/lib/python3.10/dist-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-export FACE="assets/img/avatar5.png"
+export FACE="assets/img/avatar1.jpg"
 # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
 export AUDIO='None'
 export FACESIZE=96
@@ -188,14 +188,25 @@ The output file will be saved in the current working directory, as `${PWD}` is m
 
 ## Gradio UI
 
-Follow the instructions in [Build Mega Service of AudioQnA on Gaudi](https://github.com/opea-project/GenAIExamples/blob/main/AudioQnA/docker_compose/intel/hpu/gaudi/README.md) to build necessary Docker images and start the AudioQnA MegaService with the endpoint `http://localhost:3008/v1/audioqna`. Then run the following command to start the Gradio UI:
+```bash
+sudo apt update
+sudo apt install -y yasm pkg-config libx264-dev nasm
+cd $WORKPATH
+git clone https://github.com/FFmpeg/FFmpeg.git
+cd FFmpeg
+sudo ./configure --enable-gpl --enable-libx264 && sudo make -j$(nproc-1) && sudo make install && hash -r
+pip install gradio==4.38.1 soundfile
+```
 
 ```bash
-cd GenAIExamples/AvatarChatbot/docker/ui/gradio
-python3 app_gradio_demo.py
+cd $WORKPATH/GenAIExamples/AvatarChatbot
+python3 ui/gradio/app_gradio_demo_avatarchatbot.py
 ```
 
-The UI can be viewed at http://${host_ip}:7861
+The UI can be viewed at http://${host_ip}:7861  
+<img src="../../../../assets/img/UI.png" alt="UI Example" width="60%">  
+In the current version v1.0, you need to set the avatar figure image/video and the DL model choice in the environment variables before starting AvatarChatbot backend service and running the UI. Please just customize the audio question in the UI.  
+\*\* We will enable change of avatar figure between runs in v2.0
 
 ## Troubleshooting
 

AvatarChatbot/tests/test_compose_on_gaudi.sh

@@ -127,15 +127,17 @@ function stop_docker() {
 
 
 function main() {
-
     stop_docker
+    echo y | docker builder prune --all
+    echo y | docker image prune
+
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
     start_services
     # validate_microservices
     validate_megaservice
     # validate_frontend
-    stop_docker
 
+    stop_docker
     echo y | docker builder prune --all
     echo y | docker image prune