## What would be the ideal configuration for a chatbot which deals with domain specific requests

[@nik202](https://forum.rasa.com/u/nik202) any update ?

[@nik202](https://forum.rasa.com/u/nik202) … I actually have more than 10 examples for each intent…but as many intents are very similar to each other (mostly vary by an entity value) , sometimes the bot is getting confused by entities and intents

[@nik202](https://forum.rasa.com/u/nik202) …Please find the following intent examples:
- intent 1: create_vdi_everything_given_except_type
  examples: |
  - create [vdi](vdi) in project [Create_Vdi](form_project_id) and add [Prathmesh.Tirodkar@lmtinfotech.com](form_member_list), [abhishek.som@lntinfotech.com](form_member_list) mem…

[@ChrisRahme](https://forum.rasa.com/u/chrisrahme) Please find the following outputs :

```
rasa --version:

Rasa Version: 2.8.1
Minimum Compatible Version: 2.8.0
Rasa SDK Version: 2.8.1
Rasa X Version: None
Python Version: 3.8.6
Operating System : Windows-10-10.0.19041-SP0
```

[@nik202](https://forum.rasa.com/u/nik202) Yes…I am using forms but also there are very similar intents which have completely different functionality :
Example :
1)Add members to project
Add members to a VDI
2)Create project
Create VDI

[@nik202](https://forum.rasa.com/u/nik202) My chatbot has very similar intents which are differentiated by the entities given…
Ex : Create a project - intent 1
Create a project with name testing1 - intent 2
create a project with name testing1 and add [akhil@gmail.com](mailto:akhil@gmail.com) - intent 3
because of which its getting confused

[@nik202](https://forum.rasa.com/u/nik202) This is my current config file which I am trying to update to increase intent and entity recognition accuracy of my bot :  
# Configuration for Rasa NLU.  
# https://rasa.com/docs/rasa/nlu/components/
language: en

pipeline:
# # No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.  
# # If you'd like to customize it, uncomment and adjust the pipeline options.

[@nik202](https://forum.rasa.com/u/nik202) Hi…Could u tell the files which i should share so that I can share accordingly

[@ChrisRahme](https://forum.rasa.com/u/chrisrahme) …Hi…Please find the following error :

```
Training model 'config1' failed.
Error: c:\users\10685557\onedrive - lti\desktop\code\collab bot\venv1\lib\site-packages\tensorflow_text\python\metrics\_text_similarity_metric_ops.so not found
```

[@nik202](https://forum.rasa.com/u/nik202) Could you help me out?

[@ChrisRahme](https://forum.rasa.com/u/chrisrahme) Thankyou… I will do it the next time…Please find the following error :

Hi,
I am not able to run configuration file with ConveRT Featurizer in Windows.
My Config File :
  
```
language: en

pipeline:
- name: WhitespaceTokenizer
- name: ConveRTFeaturizer
  model_url: https://github.com/connorbrinton/polyai-models/releases/download/v1.0/model.tar.gz
- name: RegexFeatur…
```

Hi
I have created a chatbot which performs various actions which are domain specific…I am trying to increase the intent recognition by editing the configuration…Can someone please help me out…

[@nik202](https://forum.rasa.com/u/nik202) So i need to add intent out_of_scope in nlu and give examples?  
Webex channel is just connecting to webex app.It is one of the channels available

[@nik202](https://forum.rasa.com/u/nik202) Hi…I am trying to implement two stage fallback policy,after default_ask_affirmation action when the user denies the suggestions, the action_default_ask_rephrase is not getting triggered but the intent(out_of_scope) is getting triggered as expected…Please help me out…
My config File :
# Configurati…