git clone https://github.com/castorini/Anserini.git

Your directory structure should look like

.
├── Anserini
├── Castor
├── Castor-data
└── models

cd Anserini
mvn package
cd ..

This creates anserini-0.0.1-SNAPSHOT.jar at Anserini/target

We highly recommend the use of virtualenv as the dependencies are subjected to frequent changes.

Install the dependency packages:

cd Castor
pip install -r requirements.txt

• Download the TrecQA lucene index
• Download the Google word2vec file from here

python ./anserini_dependency/RetrieveSentences.py

Possible parameters are:

Note: Either a query or a topic must be passed in as an argument; they can't be both empty.

NB: The speech UI cannot be run in Ubuntu. To test the pipeline in Ubuntu, make the following changes:

• Comment out the JavaScript part and run the Bash script
• Make a REST API query to the endpoint using Postman, Curl etc.

cd anserini_dependency/js
npm install
cd ../..

• Flask is used as the server for the API
• Copy config.cfg.example to config.cfg and make necessary changes, such as setting the index path and API keys.

./run_ui.sh

• This is the documentation for the API call to send a question to the model and get back the predicted answer.
• The request body fields are: question(required )num_hits(optional) and k(optional).

# REQUEST:
HTTP Method: POST
Endpoint: [host]:[port]/answer
Content-Type: application/json
text of body in raw format:
{
    "question": "What is the birthdate of Einstein?",
    "num_hits": 50,
    "k": 30
}

• The response body contains answers which is a list of objects with two fields - passage, score.

# RESPONSE:
Content-Type: application/json
text of body in raw format:
{
  "answers": [
                {"passage": "Einstein was born in the 1800s", 'score': 0.976},
                {"passage": "Einstein was a physicist", 'score': 0.524}
            ]
}