Basit Anwer commited on
Commit
4bee647
·
1 Parent(s): 7174068

Updated Readme.md

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -14,22 +14,22 @@ mechanism, which gets relevant information from ZIR Semantic Search.
14
 
15
  # Table of contents
16
 
17
- * [Rasa Bot & Zir](#rasa-bot--zir)
18
- * [Setup & Play](#setup--play)
19
- + [Set-up Rasa](#set-up-rasa)
20
- + [Set-up repo](#set-up-repo)
21
- + [Running the demo](#running-the-demo)
22
- * [Customizing the bot](#customizing-the-bot)
23
- + [Data](#data)
24
- + [Rasa Custom Action](#rasa-custom-action)
25
 
26
  ## Rasa Bot & Zir
27
 
28
  [Rasa](https://rasa.com/) is the leading conversational AI platform, for
29
- personalized conversations at scale. Developers provide the questsions they
30
- expect the end customer to ask and Rasa bot, using AI, predicts and matches the
31
  what the customer intended to ask. With this information at hand, developers can
32
- easily match what the bot should respond.
33
 
34
  This is all well unless when the customer asks a valid question the developer
35
  did not expect, for such a scenario Rasa provides a
@@ -41,13 +41,13 @@ did not expect, for such a scenario Rasa provides a
41
  > option to either respond with a default message or attempt to disambiguate the
42
  > user input.
43
 
44
- Using the mechanism the bot can ask a fallback action and search through the reviews
45
- uploaded in [Zir-AI](https://zir-ai.com) with the help of
46
  [custom actions](https://rasa.com/docs/rasa/custom-actions). If the reviews have
47
- the relavent information, it is shown as a result otherwise if the confidence of
48
- the question to reviews available is low, we fallback to a generic statement.
49
 
50
- The end results sums up to be this:
51
 
52
  ## Setup & Play
53
 
@@ -59,7 +59,7 @@ the dependencies rasa requires.
59
 
60
  Follow the
61
  [rasa installation instrcutions](https://rasa.com/docs/rasa/installation) or
62
- copy paste the following commands in terminal
63
 
64
  ```bash
65
  pip3 install -U pip
@@ -83,7 +83,7 @@ Python Path : /bin/python3
83
 
84
  ### Set-up repo
85
 
86
- To install dependecies for this repository to work install python dependencies
87
  from requirements.txt
88
 
89
  ```bash
@@ -100,14 +100,14 @@ rasa train
100
 
101
  ### Running the demo
102
 
103
- While running the model, you are require to run the rasa action server along
104
  with the rasa bot. So in one terminal run
105
 
106
  ```bash
107
  rasa run actions
108
  ```
109
 
110
- In another terminal you can either play with the bot in your `shell` or on the
111
  browser.
112
 
113
  To talk to the bot in shell run
@@ -131,20 +131,20 @@ Use the following information to customize the bot and the source of data.
131
  ### Data
132
 
133
  Data for the bot is sourced from [OpinRank](https://github.com/kavgan/OpinRank/)
134
- and reviews for Hotel Jumeirah is specifically used for this bot. Reviews are
135
  parsed from https://github.com/amin3141/zir-souffle. Use `hotels.py` to generate
136
  the output `json` and the `reviews.db`.
137
 
138
- Create a corpus on [Zir AI](http://zir-ai.com) and upload all the `json` files.
139
- Create an api key for access and note down the following information
140
 
141
- - Api key
142
  - corpus id
143
- - customer id
144
 
145
  ### Rasa Custom Action
146
 
147
- Use the above collected information and replace the information in
148
  `actions/actions.py` and you're good to go.
149
 
150
  ```python
 
14
 
15
  # Table of contents
16
 
17
+ - [Rasa Bot & Zir](#rasa-bot--zir)
18
+ - [Setup & Play](#setup--play)
19
+ - [Set-up Rasa](#set-up-rasa)
20
+ - [Set-up repo](#set-up-repo)
21
+ - [Running the demo](#running-the-demo)
22
+ - [Customizing the bot](#customizing-the-bot)
23
+ - [Data](#data)
24
+ - [Rasa Custom Action](#rasa-custom-action)
25
 
26
  ## Rasa Bot & Zir
27
 
28
  [Rasa](https://rasa.com/) is the leading conversational AI platform, for
29
+ personalized conversations at scale. Developers provide the questions they
30
+ expect the end customer to ask and the Rasa bot, using AI, predicts and matches
31
  what the customer intended to ask. With this information at hand, developers can
32
+ easily match what the bot should respond to.
33
 
34
  This is all well unless when the customer asks a valid question the developer
35
  did not expect, for such a scenario Rasa provides a
 
41
  > option to either respond with a default message or attempt to disambiguate the
42
  > user input.
43
 
44
+ Using the mechanism the bot can ask a fallback action and search through the
45
+ reviews uploaded in [Zir-AI](https://zir-ai.com) with the help of
46
  [custom actions](https://rasa.com/docs/rasa/custom-actions). If the reviews have
47
+ the relevant information is shown as a result otherwise if the confidence of the
48
+ question to reviews available is low, we fallback to a generic statement.
49
 
50
+ The results sum up to be this:
51
 
52
  ## Setup & Play
53
 
 
59
 
60
  Follow the
61
  [rasa installation instrcutions](https://rasa.com/docs/rasa/installation) or
62
+ copy-paste the following commands in terminal
63
 
64
  ```bash
65
  pip3 install -U pip
 
83
 
84
  ### Set-up repo
85
 
86
+ To install dependencies for this repository to work install python dependencies
87
  from requirements.txt
88
 
89
  ```bash
 
100
 
101
  ### Running the demo
102
 
103
+ While running the model, you are required to run the rasa action server along
104
  with the rasa bot. So in one terminal run
105
 
106
  ```bash
107
  rasa run actions
108
  ```
109
 
110
+ In another terminal, you can either play with the bot in your `shell` or on the
111
  browser.
112
 
113
  To talk to the bot in shell run
 
131
  ### Data
132
 
133
  Data for the bot is sourced from [OpinRank](https://github.com/kavgan/OpinRank/)
134
+ and reviews for Hotel Jumeirah are specifically used for this bot. Reviews are
135
  parsed from https://github.com/amin3141/zir-souffle. Use `hotels.py` to generate
136
  the output `json` and the `reviews.db`.
137
 
138
+ Create a corpus on [Zir AI](http://zir-ai.com) and upload all the `JSON files.
139
+ Create an API key for access and note down the following information
140
 
141
+ - API key
142
  - corpus id
143
+ - customer-id
144
 
145
  ### Rasa Custom Action
146
 
147
+ Use the above-collected information and replace the information in
148
  `actions/actions.py` and you're good to go.
149
 
150
  ```python