openeuler/audioqna repository overview

⁠Quick reference

• The offical OPEA docker images

• Maintained by: openEuler CloudNative SIG⁠

• Where to get help: openEuler CloudNative SIG⁠, openEuler⁠

⁠OPEA | openEuler

Current OPEA docker images are built on the openEuler⁠⁠. This repository is free to use and exempted from per-user rate limits.

OPEA is an open platform project that lets you create open, multi-provider, robust, and composable GenAI solutions that harness the best innovation across the ecosystem.

The OPEA platform includes:

• Detailed framework of composable building blocks for state-of-the-art generative AI systems including LLMs, data stores, and prompt engines

• Architectural blueprints of retrieval-augmented generative AI component stack structure and end-to-end workflows

• A four-step assessment for grading generative AI systems around performance, features, trustworthiness, and enterprise-grade readiness

Read more about OPEA at opea.dev⁠ and explore the OPEA technical documentation at opea-project.github.io⁠

⁠Supported tags and respective Dockerfile links

The tag of each AudioQnA docker image is consist of the version of AudioQnA and the version of basic image. The details are as follows

⁠Usage

The AudioQnA service can be effortlessly deployed on Intel Gaudi2, Intel Xeon Scalable Processors and Nvidia GPU.

Two types of AudioQnA pipeline are supported now: AudioQnA with/without Rerank. And the AudioQnA without Rerank pipeline (including Embedding, Retrieval, and LLM) is offered for Xeon customers who can not run rerank service on HPU yet require high performance and accuracy.

Quick Start Deployment Steps:

1. Set up the environment variables.
2. Run Docker Compose.
3. Consume the AudioQnA Service.

⁠Quick Start: 1.Setup Environment Variable

To set up environment variables for deploying AudioQnA services, follow these steps:

1. Set the required environment variables:

   # Example: host_ip="192.168.1.1"
   export host_ip="External_Public_IP"
   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
   export no_proxy="Your_No_Proxy"
   export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
   

   Copy

2. If you are in a proxy environment, also set the proxy-related environment variables:

   export http_proxy="Your_HTTP_Proxy"
   export https_proxy="Your_HTTPs_Proxy"
   

   Copy

3. Set up other environment variables:

   Get set_env.sh here: set_env.sh⁠

   # on Xeon
   source set_env.sh
   

   Copy

⁠Quick Start: 2.Run Docker Compose

Select the compose.yaml file that matches your hardware.

CPU example:

docker compose -f compose.yml up -d

It will automatically download the docker image on docker hub:

docker pull openeuler/audioqna:latest
docker pull openeuler/audioqna-ui:latest

⁠QuickStart: 3.Consume the AudioQnA Service

Test the AudioQnA megaservice by recording a .wav file, encoding the file into the base64 format, and then sending the base64 string to the megaservice endpoint. The megaservice will return a spoken response as a base64 string. To listen to the response, decode the base64 string and save it as a .wav file.

# voice can be "default" or "male"
curl http://${host_ip}:3008/v1/audioqna \
  -X POST \
  -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "max_tokens":64, "voice":"default"}' \
  -H 'Content-Type: application/json' | sed 's/^"//;s/"$//' | base64 -d > output.wav