Coder Social home page Coder Social logo

howl-anderson / rasa_contrib Goto Github PK

View Code? Open in Web Editor NEW
21.0 4.0 3.0 6.86 MB

rasa_contrib is a addon package for rasa. It provide some useful/powerful addition components

License: Apache License 2.0

Shell 1.68% Python 94.81% Makefile 3.51%
rasa addons components tensorflow paddlepaddle contrib

rasa_contrib's Introduction

rasa_contrib

rasa_contrib is a addon package for rasa. It provide some useful/powerful addition component.

component

Currently, it includes:

  • addons_intent_classifier_textcnn_tf

    TextCNN based intent classifier, based on TensorFlow

  • addons_intent_classifier_textcnn_paddle

    TextCNN based intent classifier, based on PaddlePaddle

  • addons_ner_bilstm_crf_tf

    Embedding+BiLSTM+CRF based NER extractor, based on TensorFlow

  • addons_ner_bilstm_crf_paddle

    Embedding+BiLSTM+CRF based NER extractor, based on PaddlePaddle

  • bert_text_featurizer get BERT-based text vector feature

  • bert_char_featurizer get BERT-based char/word vector feature

It also includes (but still work in progress):

  • MicroAddonsTokenizer

    Chinese tokenizer component, based on MicroTokenizer

  • StackedBilstmTensorFlowPolicy

    Stacked Bilstm based dialog policy, based on TensorFlow

  • StackedBilstmPaddlePolicy

    Stacked Bilstm based dialog policy, based on PaddlePaddle

how to use it

Using the class path to the place where you should given a component name in config.yaml. This is a feature of rasa, see here for more document from rasa official document.

For example, your config.yml can be:

language: "zh"

pipeline:
  - name: "rasa_contrib.nlu..TensorflowNLP"
  - name: "rasa_contrib.nlu..BilstmCrfTensorFlowEntityExtractor"
    max_steps: 600
  - name: "rasa_contrib.nlu.TextCnnTensorFlowClassifier"
    max_steps: 600

policies:
  - name: MemoizationPolicy
  - name: rasa_contrib.core.StackedBilstmTensorFlowPolicy

rasa_contrib's People

Contributors

howl-anderson avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

rasa_contrib's Issues

problem serving model

steps to reproduce:

  1. rasa train nlu
    --config ./configs/$agent/rasa_config.yml
    --nlu ./core/$agent/training_data.json
    --fixed-model-name core_$agent
    --out ./models
    --verbose
    2 . rasa run -v -m models --enable-api --port 5000

{"version":"1.5.3","status":"failure","message":"An unexpected error occurred. Error: (400, 'ParsingError', 'An unexpected error occurred. Error: SavedModel file does not exist at: /tmp/tmpoyzgq_93/nlu/addons_intent_classifier_textcnn_tf/{saved_model.pbtxt|saved_model.pb}')","reason":"ParsingError","details":{},"help":null,"code":500}

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.