freebirdscrew / ai_chatbot_python

AI ChatBot using Python Tensorflow and Natural Language Processing (NLP) along side TFLearn

Hi there, We are FreeBirds Crew 👋

We a Learner, Software Engineer and Teacher!

• 🔭 We are currently working as Software Engineer and Data Analyst.
• 🌱 We are currently learning everything 🤣
• 👯 We are looking to collaborate with other content creators
• 🥅 2020 Goals: Contribute more to Open Source projects and Grow my YouTube Channel
• ⚡ Fun fact: Admin love to draw and play guitar and write Songs/Poetry.

Connect with us:

Languages and Tools:

---

📺 Latest YouTube Videos

• 🔴Data Science Crash Course from Scratch using Python | Google Colab Notebook | ML Algorithms Compare
• Google's Quick Draw Implementation using Python and Deep Learning | Doodle Dataset | Tensorflow CNN
• ChatBot Using Python Tensorflow and NLP | Contextual ChatBot | Basics of ChatBot and Working Explain
• IBM Face Recognition Using Python and OpenCV - Part -1| Ada Boost Algorithm | Machine Learning

---

ai_chatbot_python's Issues

how to deploy the model to android?

me and my team has make chatbot using NLP and also this time we are confused about how to deploy our model to android using tensorflow lite could you tell us how to deploy the model to andoroid

Feature req: Please integrate apipie.ai

Users want access to as much AI as they can get, they dont want to manage 50 accounts, they want the fastest AI they want the cheapest AI, and you can provide all of that for them with this update.

in addition to or in place of integrating with any aggregators - Please integrate APIpie so devs can access them all from one place/subscription and plus it also provides:

-The most affordable, reliable and fastest AI available
-One API to access ~500 Models and growing
-Language, embedding, voice, image, vision and more
-Global AI load balancing, route queries based on price or latency
-Redundancy for major models providing the greatest up time possible
-Global reporting of AI availability, pricing and performance

Its the same API format as openai, just change the domain name and your API key and enjoy a plethora of models without changing any of your code other than how you handle the models list.

This is a win win for everyone, any new AI's from any providers will be automatically integrated into your stack with this one integration. Not to mention all the other advantages.

How to train?

List index out of range.

It is showing list index out of range error while training the model with training and testing data.

ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (27, 2) + inhomogeneous part.

Shuffling Randomly and Converting into Numpy Array for Faster Processing......

ValueError Traceback (most recent call last)
Cell In[22], line 3
1 print("Shuffling Randomly and Converting into Numpy Array for Faster Processing......")
2 random.shuffle(training)
----> 3 training = np.array(training)
5 print("Creating Train and Test Lists.....")
6 train_x = list(training[:,0])

ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (27, 2) + inhomogeneous part.

Questions about usage

By using a list for train, how could the processor tell whether the sentance is a Q or an A?
How could I use the “intents.json” instead of using a list for train?
How could I make a contextual chatbot?
Did I miss any demo? Cause I only got 1 runnable py file which was named after "Chatterbot.py".