pradeepmvn / rasa_stack_quickstart

:rocket: Easiest way to get started with Rasa stack. A full stack web based chatbot on top of rasa stack.

Rasa Stack Quickstart

A full stack web based Conversational chatbot on top of rasa stack.

kudos to RASAHQ for putting a great stack together. This is an attempt to create some tutorials on top of rasa stack with real examples.

All the examples in this repo uses

• Rasa NLU : for Natural Language Understanding
• Rasa Core : For Conversation/Dialogue management
• Rasa UI: An administrative user interface

Weather chatbot

rasa_stack_quickstart's Issues

Stuck at docker-compose up

I'm stuck at - docker-compose up , first I was not able to use the command so I wrote sudo docker-compose up and it started downloading but it got stuck at step 8/15 , I had to stop it forcefully after waiting for half an hour. Please help me

migrating from 0.9.0a3 to 0.10.1 RASA-CORE

What should be done to move to the latest 0.10.1 with its change of API re: RasaCoreServer?

(Great project!)

From where the data of weather graped?

From where the data of weather graped?
Does the webhook call any api?
I didn't any API here. Can you please show me some way?

issues with options (rasa-ui)

See issue reported here: paschmann/rasa-ui#96

In other words, I wasn't able to produce a widget like the one posted in the pic in the project page (no options and no input row at the bottom).

Rasa Core Error: Connection Refused (Cisco AnyConnect/Docker Issue?)

Hello! Thank you for this wonderful repo, it really is amazingly useful for us. I have randomly ran into an issue and I am unsure what's causing it. When I run docker-compose up to run the application, Rasa Core does not connect to the endpoint properly: the connection is refused. Here is the log:

rasa-ui_1         | > [email protected] start /opt/rasaui
rasa-ui_1         | > node server/server.js
rasa-ui_1         | 
rasa-ui_1         | Rasa UI Server: http://localhost:5001
rasa-ui_1         | 
rasa-ui_1         | Express server listening on port 5001
rasa-core_1       | WARNING:py.warnings:/usr/local/lib/python3.5/site-packages/h5py/__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
rasa-core_1       |   from ._conv import register_converters as _register_converters
rasa-core_1       | 
rasa-nlu_1        | 2018-07-13 16:56:09+0000 [-] "172.19.0.5" - - [13/Jul/2018:16:56:08 +0000] "GET /config HTTP/1.1" 200 666 "-" "-"
rasa-ui_1         | 
**rasa-ui_1         | Rasa Core Error: Error: connect ECONNREFUSED 172.19.0.4:5005
rasa-ui_1         | Using connection string from: process.env.rasacoreendpoint**
rasa-ui_1         | 
rasa-ui_1         | 
rasa-ui_1         | Rasa NLU Connected
rasa-ui_1         | Using connection string from: process.env.rasanluendpoint
rasa-ui_1         | Rasa NLU Server: http://rasa-nlu:5000
rasa-ui_1         | 
rasa-ui_1         | 
rasa-ui_1         | Postgres DB Connected
rasa-ui_1         | Using connection string from: package.json
rasa-ui_1         | Postgres Server: null:null
rasa-ui_1         | Database:rasaui
rasa-ui_1         | Schema:public
rasa-ui_1         | 
rasa-core_1       | 2018-07-13 16:56:10.672874: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
rasa-core_1       | 2018-07-13 16:56:10+0000 [-] Log opened.
rasa-core_1       | 2018-07-13 16:56:10+0000 [-] Site starting on 5005
rasa-core_1       | 2018-07-13 16:56:10+0000 [-] Starting factory <twisted.web.server.Site object at 0x7f1431d31f28>

I was messing with some things when this happened, but upon the reversion of those changes it didn't correct itself. I should note that the issues started when I used Cisco AnyConnect as I am currently on the network using the VPN. However, disconnecting that doesn't seem to fix the issue now.

Things I have tried:

• changing the port number from 5005 to 5006 and reflecting this everywhere else in the project code
• disconnecting from the VPN and running again
• pulling the repo fresh and running again
• manually running docker kill on all processes and port connections, and running again

Out of 50+ attempts at re-running the docker-compose up command since this issue started occurring, it successfully connected once. Then it promptly failed again next time. I suspect the VPN has messed with the routes in some permanent way that I need to correct.

Please let me know if I can supply more information! Thank you

edit:
Have found this post: https://stackoverflow.com/questions/41739675/unable-to-connect-to-docker-on-anyconnect-vpn

Will look into those solutions and update if I solve it

edit2:
Alright I'm back...no success.

Things I've Tried Part 2:

• Closing VPN session entirely.
• Removing all containers, images, bridges, networks, etc. Everything, fresh clean and then rebuilt. Same thing

So either the VPN messed something up so deeply that I cannot figure it out, or its a red herring..because now the VPN isn't even running and the issue persists!

rasa-core - docker build error in step #9

I am not building the docker image using docker-compose file. But, building the individual ones using the respective docker file under core, nlu and ui.
When I built the rasa-core image using Jenkins and it failed on the below step.
I fixed it by removing one of the "RUN" from the command and jenkins job moved on from that error. (i used my own copy of this repo to fix it). Is this fix suppose to be here too ? I was not sure,

Here is the error.
Step 9/15 : RUN RUN python -m pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-1.8.0-cp35-cp35m-linux_x86_64.whl
---> Running in 48e2f28061af
�[91m/bin/sh: 1: RUN: not found

getting some data missing() error, generated error is empty.

HI,

With this mitie pipeline. i am unable to train bot and getting above error in rasa ui. In rasa nlu getting below error.

rasa_nlu.data_router - [Failure instance: Traceback (failure with no frames): <class 'twisted.internet.defer.CancelledError'>:

pipeline : [{ "name":"nlp_mitie", "model":"/app/data/mitie/total_word_feature_extractor.dat" }, { "name":"tokenizer_mitie" }, { "name":"ner_mitie" }, { "name":"ner_synonyms" }, { "name":"intent_entity_featurizer_regex" }, { "name":"intent_featurizer_mitie" }, { "name":"intent_classifier_sklearn", "C":[ 1, 2, 5, 10, 20, 100 ], "kernel":"linear" }]

any idea?

rasa_stack_quickstart weatherbot rasa_core Dockerfile pulling older version of requirements.txt for rasa_core

I'm trying to install docker image included with this project (Thank you for the recommendation and awesome work!) and I ran into the issue in step 10/14:

Step 10/14 : RUN pip install -r requirements.txt
 ---> Running in 45902691df67
Collecting apscheduler==3.5.0 (from -r requirements.txt (line 2))
  Downloading https://files.pythonhosted.org/packages/19/d9/ca8322005bcd84c38e38cfaf2d5bd6fb66c14b4e977e973c6bb5ac5b98c7/APScheduler-3.5.0-py2.py3-none-any.whl (60kB)
Collecting fakeredis==0.9.0 (from -r requirements.txt (line 3))
  Downloading https://files.pythonhosted.org/packages/d2/51/c5398a9e5c25f6bfd2edc0f101c610e569a618e8631b410312423193ccc7/fakeredis-0.9.0-py2.py3-none-any.whl
Collecting future==0.16.0 (from -r requirements.txt (line 4))
  Downloading https://files.pythonhosted.org/packages/00/2b/8d082ddfed935f3608cc61140df6dcbf0edea1bc3ab52fb6c29ae3e81e85/future-0.16.0.tar.gz (824kB)
Collecting graphviz==0.7.1 (from -r requirements.txt (line 5))
  Downloading https://files.pythonhosted.org/packages/95/65/0460bcb4957e027ad31d351af170dd1759aee68c90ca598ee930ac115dd1/graphviz-0.7.1-py2.py3-none-any.whl
Collecting h5py==2.7.0 (from -r requirements.txt (line 6))
  Downloading https://files.pythonhosted.org/packages/11/6b/32cee6f59e7a03ab7c60bb250caff63e2d20c33ebca47cf8c28f6a2d085c/h5py-2.7.0.tar.gz (256kB)
Collecting jsonpickle==0.9.4 (from -r requirements.txt (line 7))
  Downloading https://files.pythonhosted.org/packages/cc/5e/6ecbd1d27524fcafeed4                                                                                                                     f6156f47a2a79e31e4bfa383e329e9ba93c7f3ee/jsonpickle-0.9.4.tar.gz (65kB)
Collecting keras==2.0.8 (from -r requirements.txt (line 8))
  Downloading https://files.pythonhosted.org/packages/67/3f/d117d6e48b19fb958936                                                                                                                     9f4bdbe883aa88943f8bb4a850559ea5c546fefb/Keras-2.0.8-py2.py3-none-any.whl (276kB                                                                                                                     )
Collecting numpy==1.14.0 (from -r requirements.txt (line 9))
  Downloading https://files.pythonhosted.org/packages/ee/66/7c2690141c520db08b6a                                                                                                                     6f852fa768f421b0b50683b7bbcd88ef51f33170/numpy-1.14.0.zip (4.9MB)
Collecting pandoc==1.0.0b2 (from -r requirements.txt (line 10))
  Downloading https://files.pythonhosted.org/packages/51/57/94440dbaed76f6fb73f4                                                                                                                     0756e484b8de645ad36f56d4d7100e03e443591a/pandoc-1.0.0b2.tar.gz (516kB)
Collecting redis==2.10.5 (from -r requirements.txt (line 11))
  Downloading https://files.pythonhosted.org/packages/08/c1/457428f7507e27ba7144                                                                                                                     758a7b716ea35766e6d602f4a0c16e443ab3d381/redis-2.10.5-py2.py3-none-any.whl (60kB                                                                                                                     )
Collecting six==1.11.0 (from -r requirements.txt (line 12))
  Downloading https://files.pythonhosted.org/packages/67/4b/141a581104b1f6397bfa                                                                                                                     78ac9d43d8ad29a7ca43ea90a2d863fe3056e86a/six-1.11.0-py2.py3-none-any.whl
Collecting tensorflow==1.4.1 (from -r requirements.txt (line 13))
  Could not find a version that satisfies the requirement tensorflow==1.4.1 (fro                                                                                                                     m -r requirements.txt (line 13)) (from versions: )
No matching distribution found for tensorflow==1.4.1 (from -r requirements.txt (                                                                                                                     line 13))
ERROR: Service 'rasa-core' failed to build: The command '/bin/sh -c pip install                                                                                                                      -r requirements.txt' returned a non-zero code: 1

I think in HEAD repo of RASA_CORE they are using tensorflow 1.8 now, check it out https://github.com/RasaHQ/rasa_core/blob/master/requirements.txt

Thanks

/bin/sh: service: not found

ERROR: Service 'rasa-ui' failed to build: The command '/bin/sh -c service postgresql start && su postgres -c " echo "\c rasaui; \i weather-insert.sql" | psql && echo "grant all on database rasaui to rasaui; grant all privileges on all tables in schema public to rasaui; grant all privileges on all sequences in schema public to rasaui "|psql rasaui" && service postgresql stop' returned a non-zero code: 127

OSE unable to start rasa-ui, which is built using the docker file

We get the error, if we use the docker file for building and deploying in OSE.

chmod: changing permissions of '/var/run/postgresql': Operation not permitted