Question and Answering Model with TensorFlow
Switch branches/tags
Nothing to show
Clone or download
Latest commit 5f52636 Jul 13, 2018

Note, this repo is deprecated.

If you are interested in further enhancements and investigations, just watch Next repo.

Approaching a Chatbot Service

Join the chat at Docker Pulls Docker Stars Docker Layers

chatoper banner

Part 1: Introduction

Part 2: Bot Engine

Part 3: Bot Model

This repository is align with Part 3: Bot Model.

Train and serve QA Model with TensorFlow

Tested with TensorFlow#0.11.0rc2, Python#3.5.

Install Nvidia Drivers, CUDNn, Python, TensorFlow on Ubuntu 16.04


Inspired and inherited from DeepQA.

Install deps

pip install -r requirements.txt

Install TensorFlow

pip install —-upgrade $TF_BINARY_URL

Pre-process data

Process data, build vocabulary, word embedding, conversations, etc.

cp config.sample.ini config.ini
python deepqa2/dataset/

Sample Corpus

Train Model

Train language model with Seq2seq.

cp config.sample.ini config.ini # modify keys
python deepqa2/

Serve Model

Provide RESt API to access language model.

cd DeepQA2/save/deeplearning.cobra.vulcan.20170127.175256/deepqa2/serve
cp db.sample.sqlite3 db.sqlite3 
python runserver

Access Service with RESt API

POST /api/v1/question HTTP/1.1
Content-Type: application/json
Authorization: Basic YWRtaW46cGFzc3dvcmQxMjM=
Cache-Control: no-cache

{"message": "good to know"}

  "rc": 0,
  "msg": "hello"

Train with Docker



docker pull samurais/deepqa2:latest
cd DeepQA2