Smart QA Service

Quickly launch an intelligent customer service system with Flask, LLM, RAG, including frontend, backend, and admin console.

Deploy the OpenKF Service

1. Download repository code

Clone the repository:

git clone https://github.com/open-kf/smart-qa-service.git && cd smart-qa-service

2. Configure variables of .env

Before starting the OpenKF service, you need to modify the related configurations for the program to initialize correctly.

cp env_template .env

The variables in .env

DISKCACHE_DIR="diskcache_dir"
SQLITE_DB_DIR="sqlite_dir"
SQLITE_DB_NAME="mydatabase.sqlite3"
MAX_CRAWL_PARALLEL_REQUEST=5
CHROMA_DB_DIR="chroma_dir"
CHROMA_COLLECTION_NAME="mychroma_collection"
OPENAI_API_KEY="xxxx"
GPT_MODEL_NAME="gpt-3.5-turbo"
OPENAI_EMBEDDING_MODEL_NAME="text-embedding-3-small"
MAX_QUERY_SIZE=200
RECALL_TOP_K=3
MAX_HISTORY_QUERY_SIZE=5
HISTORY_EXPIRE_TIME=10800
MAX_EMBEDDING_INPUT=2048
SITE_TITLE="your site title"
STATIC_DIR="web"
URL_PREFIX="http://your-server-ip:7000/"
MEDIA_DIR="media_dir"

• Modify OPENAI_API_KEY to your own key, which can be obtained by logging into the OpenAI dashboard:
• Modify SITE_TITLE to your website's name.
• Modify URL_PREFIX according to your website's domain.

3. Deploy OpenKF using Docker

docker-compose up --build

4. Deploy OpenKF from source code

4.1 Set up the Python running environment

It is recommended to install Python-related dependencies in a Python virtual environment to avoid affecting dependencies of other projects.

Create and activate a virtual environment

If you have not yet created a virtual environment, you can create one with the following command:

python3 -m venv myenv

After creation, activate the virtual environment:

source myenv/bin/activate

Install dependencies with pip

Once the virtual environment is activated, you can use pip to install the required dependencies.

pip install -r requirements.txt

4.2 Create SQLite Database

The OpenKF service uses SQLite as its storage DB. Before starting the OpenKF service, you need to execute the following command to initialize the database and add the default configuration for admin console.

python3 create_sqlite_db.py

4.3 Start the service

If you have completed the steps above, you can try to start the OpenKF service by executing the following command.

• Start single process:

python smart_qa_app.py

• Start multiple processes:

sh start.sh

Note

• The service port for OpenKF is 7000. During the first test, please try not to change the port so that you can quickly experience the entire product process.
• We recommend starting the OpenKF service using start.sh in multi-process mode for a smoother user experience.

Configure the admin console

1. Login to the admin console

Access the admin console through the link http://your-server-ip:7000/open-kf-admin/ to reach the login page. The default username and password are admin and open_kf_AIGC@2024 (can be checked in create_sqlite_db.py).

After logging in successfully, you will be able to see the configuration page of the admin console.

On the page http://your-server-ip:7000/open-kf-admin/#/, you can set the following configurations:

• Choose the LLM base, currently only the gpt-3.5-turbo option is available, which will be gradually expanded.
• Initial Messages
• Suggested Messages
• Message Placeholder
• Profile Picture (upload a picture)
• Display name
• Chat icon (upload a picture)

2. Import your data

After submitting the website URL, once the server retrieves the list of all web page URLs via crawling, you can select the web page URLs you need as the knowledge base (all selected by default).

You can actively refresh the page http://your-server-ip:7000/open-kf-admin/#/source in your browser to get the progress of web page URL processing. After the content of theweb page URL has been crawled, and the Embedding calculation and storage are completed, you can see the corresponding Size in the admin console, and the Status will also be updated to Stored.

3. Test the chatbot

After importing website data in the admin console, you can experience the chatbot service through the link http://your-server-ip:7000/open-kf-chatbot/.

4. Embed on your website

Through the admin console link http://your-server-ip:7000/open-kf-admin/#/embed, you can see the detailed tutorial for configuring the iframe in your website.

OpenIM chatbot

5. View the user's chatbot visit history

Through the admin console link http://your-server-ip:7000/open-kf-admin/#/dashboard, you can view the historical request records of all users within a specified time range.

The frontend of admin console and chatbot

The OpenKF service integrates 2 frontend modules, and their source code information is as follows:

admin console

Code Repository

An intuitive web-based admin interface for Smart QA Service, offering comprehensive control over content, configuration, and user interactions. Enables effortless management of the knowledge base, real-time monitoring of queries and feedback, and continuous improvement based on user insights.

chatbot

Code Repository

An HTML5 interface for Smart QA Service designed for easy integration into websites via iframe, providing users direct access to a tailored knowledge base without leaving the site, enhancing functionality and immediate query resolution.