Jugalbandi API is a system of APIs that allows users to build Q&A style applications on their private and public datasets. The system creates Open API 3.0 specification endpoints using FastAPI.

To use the code, you need to follow these steps:

1. Clone the repository from GitHub:

   git clone https://github.com/DJP-Digital-Jaaduii-Pitara/sakhi-utility-service.git

2. The code requires Python 3.7 or higher and some additional python packages. To install these packages, run the following command in your terminal:

   pip install requirements.txt

3. You will need a OCI account to store the audio file for response.

4. create another file .env which will hold the development credentials and add the following variables. Update the azure openai details, OCI object storage details and bhashini endpoint URL and API Key.

   OPENAI_API_VERSION=<AZURE_OPENAI_API_VERSION>
   OPENAI_API_BASE=<AZURE_OPENAI_BASE_URL>
   OPENAI_API_TYPE=azure 
   GPT_MODEL=<AZURE_OPENAI_MODEL_NAME>
   OPENAI_API_KEY=<your_openai_key>
   LOG_LEVEL=<log_level>  # INFO, DEBUG, ERROR
   BHASHINI_ENDPOINT_URL=<your_bhashini_endpoint_url>
   BHASHINI_API_KEY=<your_bhashini_api_key>
   OCI_ENDPOINT_URL=<oracle_bucket_name>
   OCI_REGION_NAME=<oracle_region_name>
   OCI_BUCKET_NAME=<oracle_bucket_name>
   OCI_SECRET_ACCESS_KEY=<oracle_secret_access_key>
   OCI_ACCESS_KEY_ID=<oracle_access_key_id>
   TELEMETRY_ENDPOINT_URL=<TELEMETRY_ENDPOINT_URL> 
   TELEMETRY_LOG_ENABLED=<TELEMETRY_LOG_ENABLED> 

Once the above installation steps are completed, run the following command in home directory of the repository in terminal

uvicorn main:app

API is used to extract context information of chosen attributes from an user's query. To achieve the same, Few-shot learning has been implemented which requires a set of 'examples' and necessary 'instructions' to be given to LLM (openAI) in order to generate an answer in the instructed format. Configuration of 'instructions' and 'examples' are available in 'config.ini'.

en,bn,gu,hi,kn,ml,mr,or,pa,ta,te

Required inputs are 'text', 'audio' and 'language'.

Either of the 'text'(string) or 'audio'(string) should be present. If both the values are given, exception is thrown. Another requirement is that the 'language' should be same as the one given in text and audio (i.e, if you pass English as 'language', then your 'text'/'audio' should contain queries in English language). The audio should either contain a publicly downloadable url of mp3 file or base64 encoded text of the mp3.

{
    "text": "ನನ್ನ ಮಗುವಿಗೆ ವಾಟರ್ ಪೇಂಟಿಂಗ್ ಅನ್ನು ಹೇಗೆ ಕಲಿಸುವುದು",
    "language": "kn"
}

{
    "input": {
        "sourceText": "ನನ್ನ ಮಗುವಿಗೆ ವಾಟರ್ ಪೇಂಟಿಂಗ್ ಅನ್ನು ಹೇಗೆ ಕಲಿಸುವುದು",
        "englishText": "How to Teach My Child Water Painting"
    },
    "context": {
        "category": [
            "Activities"
        ],
        "persona": [
            "Parent"
        ],
        "age": [
            "3-5"
        ],
        "keywords": [
            "water painting"
        ],
        "domain": [
            "Aesthetic and Cultural Development"
        ],
        "curricularGoal": [
            "CG-12: Children develop abilities and sensibilities in visual and performing arts and express their emotions through art in meaningful and joyful ways"
        ]
    }
}

API is used to achieve translation of text/audio from one language to another language in text/audio format. To achieve the same, Bhashini has been integrated. OCI object storage has been used to store translated audio files when audio is chosen as target output format.

en,bn,gu,hi,kn,ml,mr,or,pa,ta,te

Required inputs are 'input.text', 'input.audio', 'input.language', 'output.language' and 'output.format'.

Either of the 'text'(string) or 'audio'(string) should be present in the 'input'. If both the values are given, exception is thrown. Another requirement is that the 'input.language' should be same as the one given in text and audio (i.e, if you pass English as 'input.language', then your 'text'/'audio' should contain queries in English language). The audio should either contain a publicly downloadable url of mp3 file or base64 encoded text of the mp3. If 'output.language' is not passed in the request, 'English' will be the default value. 'output.format' can only take 'text'/'audio' as values. If 'output.format' is not passed in the request, 'text' will be the default value.

{
    "input": {
        "text": "How to Teach Kids to Play Games",
        "language": "en"
    },
    "output": {
        "language": "kn",
        "format": "text"
    }
}

{
    "translation": {
        "text": "ಮಕ್ಕಳಿಗೆ ಆಟವಾಡಲು ಕಲಿಸುವುದು ಹೇಗೆ?",
        "audio": null
    }
}

This repository comes with a Dockerfile. You can use this dockerfile to deploy your version of this application to Cloud Run. Make the necessary changes to your dockerfile with respect to your new changes. (Note: The given Dockerfile will deploy the base code without any error, provided you added the required environment variables (mentioned in the .env file) to either the Dockerfile or the cloud run revision)

• We are currently in the alpha stage and hence need all the inputs, feedbacks and contributions we can.
• Kindly visit our project board to see what is it that we are prioritizing.

sudo apt-get update
sudo apt-get install ca-certificates curl gnupg
sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg

# Add the repository to Apt sources:
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update

$ sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin	

$ sudo apt install python3-pip

$ git clone https://github.com/DJP-Digital-Jaaduii-Pitara/sakhi-utility-service.git

$ cd sakhi-utility-service

$ sudo docker build -t sakhiutilityimage .

$ sudo docker run -d -p 8000:8000 --name sakhi-utility-service \
-e OPENAI_API_VERSION=$AZURE_OPENAI_API_VERSION 
-e OPENAI_API_BASE=$AZURE_OPENAI_BASE_URL
-e OPENAI_API_TYPE=azure 
-e GPT_MODEL=$AZURE_OPENAI_MODEL_NAME
-e OPENAI_API_KEY=$OPENAI_API_KEY \
-e LOG_LEVEL=INFO  \
-e BHASHINI_ENDPOINT_URL=$BHASHINI_ENDPOINT_URL \
-e BHASHINI_API_KEY=$BHASHINI_API_KEY \
-e OCI_ENDPOINT_URL=$OCI_ENDPOINT_URL \
-e OCI_REGION_NAME=$OCI_REGION_NAME \
-e DISABLE_NEST_ASYNCIO=True \
-e OCI_BUCKET_NAME=$OCI_BUCKET_NAME \
-e OCI_SECRET_ACCESS_KEY=$OCI_SECRET_ACCESS_KEY \
-e OCI_ACCESS_KEY_ID=$OCI_ACCESS_KEY_ID \
-e TELEMETRY_ENDPOINT_URL=$TELEMETRY_ENDPOINT_URL \
-e TELEMETRY_LOG_ENABLED=$TELEMETRY_LOG_ENABLED \
sakhiutilityimage