Chatbot - GitLite

KO | EN

gitlite — search

#javascript #python #machine-learning #deep-learning #linux #windows #awesome #kubernetes #vue #awesome-list #pytorch #openai #mcp #open-source

Chatbot

(★ 868)

Python ChatBot 💬

파일 탐색기

최종 버전 다운로드 (.zip)

- - bug_report.md
  - feature_request.md
- - codeql-analysis.yml
  - python-publish.yml
- - __init__.py
- - robot.png
  - send.png
  - user.png
- - __init__.py
- - __init__.py
- __init__.py
- constants.py
- grammar_corrector.py
- mapper.py
- version.py
- _config.yml
- CNAME
- README.md
- Example.py
- Example.template
- get_set_memory_example.py
- get_set_memory_example.template
- ChatBot AI.png
- ChatBot AI.svg
- ChatBot AI.xml
- clothing.gif
- demo.gif
- demo_gui.gif
- reminder.gif
- - alice.txt
  - raven.txt
- __init__.py
- spell-testset1.txt
- spell-testset2.txt
- spellcheck.py
- test_ai_advanced.py
- test_ai_integration.py
- test_ollama_setup.py
.gitignore
_config.yml
CNAME
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
OLLAMA_SETUP.md
PULL_REQUEST_TEMPLATE.md
README.md
requirement.txt
setup.cfg
setup.py
TODO.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/ahmadfaizalbh/Chatbot

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd Chatbot

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install chatbotAI

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install chatbotAI

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

pip install -r requirement.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

[![Downloads](https://static.pepy.tech/badge/chatbotai)](https://pepy.tech/project/chatbotai)
[![PyPI version](https://badge.fury.io/py/chatbotAI.svg)](https://badge.fury.io/py/chatbotAI)
![Upload Python Package](https://github.com/ahmadfaizalbh/Chatbot/workflows/Upload%20Python%20Package/badge.svg)
[![CodeQL](https://github.com/ahmadfaizalbh/Chatbot/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/ahmadfaizalbh/Chatbot/actions/workflows/codeql-analysis.yml)

# ChatBotAI
Python chatbot AI that helps in creating a python based chatbot with
minimal coding. This provides both bots AI and chat handler and also
allows easy integration of REST API's and python function calls which
makes it unique and more powerful in functionality. This AI provides
numerous features like learn, memory, conditional switch, topic-based
conversation handling, etc.

## 🚀 NEW: Ollama Integration
Now supports **Ollama with Llama 3.2** for state-of-the-art AI responses!
- No training required - uses pretrained models
- Coherent, human-like conversations
- Local inference (no API costs)
- See `OLLAMA_SETUP.md` for installation instructions

![Demo GUI](https://raw.githubusercontent.com/ahmadfaizalbh/Chatbot/master/images/demo_gui.gif)

![Demo](https://raw.githubusercontent.com/ahmadfaizalbh/Chatbot/master/images/demo.gif)
![Clothing assistance](https://raw.githubusercontent.com/ahmadfaizalbh/Chatbot/master/images/clothing.gif)
![Reminder](https://raw.githubusercontent.com/ahmadfaizalbh/Chatbot/master/images/reminder.gif)

## Installation

Install from PyPI (includes Ollama setup):
```sh
pip install chatbotAI
```
*During installation, you'll be prompted to install Ollama for AI responses.*

### Install from GitHub (Source)
1. Clone the repository:
```sh
git clone https://github.com/ahmadfaizalbh/Chatbot.git
cd Chatbot
```
2. Install dependencies:
```sh
pip install -r requirement.txt
```
3. Install package:
```sh
python setup.py install
```

## Demo
```shell
>>> from chatbot import demo
>>> demo()
Hi, how are you?
> i'm fine
Nice to know that you are fine  
> quit
Thank you for talking with me.
>>> 
```

## Sample Code (with wikipedia search API integration)

```python
from chatbot import Chat, register_call
import wikipedia

@register_call("whoIs")
def who_is(session, query):
    try:
        return wikipedia.summary(query)
    except Exception:
        for new_query in wikipedia.search(query):
            try:
                return wikipedia.summary(new_query)
            except Exception:
                pass
    return "I don't know about "+query

first_question="Hi, how are you?"
Chat("examples/Example.template").converse(first_question)
```

For Detail on how to build Facebook messenger bot checkout  [Facebook Integration.ipynb](https://github.com/ahmadfaizalbh/Meetup-Resources/blob/master/Facebook%20Integration.ipynb)

For Jupyter notebook Chatbot checkout [Infobot built using NLTK-Chatbot](https://github.com/ahmadfaizalbh/Meetup-Resources/blob/master/How%20to%20build%20a%20bot.ipynb)

#### Sample Apps
1. A sample facebook messenger bot built using [messengerbot](https://github.com/geeknam/messengerbot/pulls), [Django](https://github.com/django/django) and [NLTK-Chatbot](#chatbot) is available here [Facebook messenger bot](https://github.com/ahmadfaizalbh/FacebookMessengerBot/)
2. A sample microsoft bot built using [Microsoft Bot Connector Rest API - v3.0](https://docs.botframework.com/en-us/restapi/connector/#navtitle), [Django](https://github.com/django/django) and [NLTK-Chatbot](#chatbot) is available here [Microsoft Chatbot](https://github.com/ahmadfaizalbh/Microsoft-chatbot/)

## List of feature supported in bot template
1. [Memory](#memory)
2. [Get matched group](#get-matched-group)
3. [Recursion](#recursion)
4. [Condition](#condition)
5. [Change Topic](#change-topic)
6. [Interact with python function](#interact-with-python-function)
7. [REST API integration](#rest-api-integration)
8. [Topic based group](#topic-based-group)
9. [Learn](#learn)
10. [To upper case](#to-upper-case)
11. [To lower case](#to-lower-case)
12. [Capitalize](#capitalize)
13. [Previous](#previous)

---

## Memory

#### Set Memory
```
{ variable : value }
```
In think mode
```
{! variable : value }
```

#### Get Memory
```
{ variable }
```

## Get matched group
for grouping in regex refer [Python regular expression docs](https://docs.python.org/3/howto/regex.html#non-capturing-and-named-groups)
#### Get N<sup>th</sup> matched group of client pattern
```
%N
```
Example to get first matched
```
%1
```
#### Get matching named group of client pattern
```
%Client_pattern_group_name
```
Example to get matching named group `person`
```
%person
```

#### Get N<sup>th</sup> matched group of bots message pattern
```
%!N
```
Example to get first matched
```
%!1
```

#### Get matching named group of bots message pattern
```
%!Bot_pattern_group_name
```
Example to get matching named group `region`
```
%!region
```

## Recursion
Get response as if client said this new statement
```
{% chat statement %}
```
It will do a pattern match for statement

## Condition
``` 
{% if condition %} do this first {% elif condition %} do this next {% else %} do otherwise {% endif %}
```

## Change Topic
```
{% topic TopicName %}
```

## Interact with python function
##### In python 
```python
@register_call("functionName")
def function_name(session, query):
    return "response string"
```
##### In template 
```
{% call functionName: value %}
```

## REST API integration
 
### In API.json file
 ```
{
    "APIName":{
        "auth" : {
            "url":"https://your_rest_api_url/login.json",
            "method":"POST",
            "data":{
                "user":"Your_Username",
                "password":"Your_Password"
            }
        },
        "MethodName" : {
            "url":"https://your_rest_api_url/GET_method_Example.json",
            "method":"GET",
            "params":{
                "key1":"value1",
                "key2":"value2",
                ...
            },
            "value_getter":[order in which data has to be picked from json response]
        },
        "MethodName1" : {
            "url":"https://your_rest_api_url/GET_method_Example.json",
            "method":"POST",
            "data":{
                "key1":"value1",
                "key2":"value2",
                ...
            },
            "value_getter":[order in which data has to be picked from json response]
        },
        "MethodName2" : {
            ...
        },
        ...
    },
    "APIName2":{
        ...
    },
    ...
}
```
*If authentication is required only then `auth` method is needed.The `data` and `params` defined in pi.json file acts as default values and all key value pair defined in template file overrides the default value.`value_getter` consists of list of keys in order using which info from json will be collected.*

### In Template file
```
[ APIName:MethodName,Key1:value1 (,Key*:value*) ]
```
you can have any number of key value pair and all key value pair will override data or params depending on `method`, if `method` is `POST` then it overrides data and if method is `GET` then it overrides `params`.

## Topic based group 
```
{% group topicName %}
  {% block %}
      {% client %}client says {% endclient %}
      {% response %}response text{% endresponse %}
  {% endblock %}
  ...
{% endgroup %}
```

## Learn
```
{% learn %}
  {% group topicName %}
    {% block %}
        {% client %}client says {% endclient %}
        {% response %}response text{% endresponse %}
    {% endblock %}
    ...
  {% endgroup %}
  ...
{% endlearn %}
```

## To upper case
```
{% up string %}
```

## To lower case
```
{% low string %}
```

## Capitalize
```
{% cap string %}
```

## Previous
```
{% block %}
    {% client %}client's statement pattern{% endclient %}
    {% prev %}previous bot's statement pattern{% endprev %}
    {% response %}response string{% endresponse %}
{% endblock %}
```

## AI Framework

The library now uses **Ollama with Llama 3.2** for state-of-the-art AI responses.

### Features
1.  **Pretrained Models**: No training required - uses advanced language models.
2.  **Local Inference**: Runs locally without API costs or internet dependency.
3.  **Fine-tuning**: Create custom models with your own training data.
4.  **Online Learning**: The bot can learn specific responses dynamically.
5.  **Fallback Mechanism**: If no template pattern matches, Ollama generates intelligent responses.

### Usage

#### Training
You can train the bot on text files or URLs:

```python
chat = Chat()
# Train on a book or website
chat.train("https://www.gutenberg.org/files/11/11-0.txt", epochs=10)
```

#### Self-Learning
The bot can learn from interactions:

```python
chat.learn_response("What is the capital of Mars?", "Elon Musk's future home.")
```

#### AI Fallback
The AI integration is automatic. If a user query does not match any defined template pattern, the `converse` method calls `ai_converse`.
- If the model is untrained, it replies: *"I haven't been trained on enough data to answer that yet. Please train me!"*
- Once trained, it generates a response based on its vocabulary and training.

---

![Chatbot AI flow Diagram](https://raw.githubusercontent.com/ahmadfaizalbh/Chatbot/master/images/ChatBot%20AI.png)-0.txt", epochs=10)
```

#### Self-Learning
The bot can learn from interactions:

```python
chat.learn_response("What is the capital of Mars?", "Elon Musk's future home.")
```

#### AI Fallback
The AI integration is automatic. If a user query does not match any defined template pattern, the `converse` method calls `ai_converse`.
- If the model is untrained, it replies: *"I haven't been trained on enough data to answer that yet. Please train me!"*
- Once trained, it generates a response based on its vocabulary and training.

---

![Chatbot AI flow Diagram](https://raw.githubusercontent.com/ahmadfaizalbh/Chatbot/master/images/ChatBot%20AI.png)