How to Build an AI Assistant with OpenAI & Python by Shaw Talebi

Integrating an External API with a Chatbot Application using LangChain and Chainlit by Tahreem Rasul

You can see, you are getting a reply from custom action which is written in python. In the same python script, you can connect to your backend database and return a response. Also, you can call an external API using additional python packages.

Yes, because of its simplicity, extensive library and ability to process languages, Python has become the preferred language for building chatbots. Artificial intelligence is used to construct a computer program known as “a chatbot” that simulates human chats with users. It employs a technique known as NLP to comprehend the user’s inquiries and offer pertinent information. Chatbots have various functions in customer service, information retrieval, and personal support. When an end-user writes or says something, Dialogflow matches the end-user expression to the best intent in your agent.

Notable Points Before You Train AI with Your Own Data1. You can train the AI chatbot on any platform, whether Windows, macOS, Linux, or ChromeOS. In this article, I’m using Windows 11, but the steps are nearly identical for other platforms.

With regards to natural language processing (NLP), the grandfather of NLP integration was written in Python. NLP research has always been focused on making chatbots smarter and smarter. If you want to train the AI chatbot with new data, delete the files inside the “docs” folder and add new ones. You can also add multiple files, but make sure to add clean data to get a coherent response.

We will be using Sequence to Sequence model architecture for our Language Translation model using Python. By following the above command, both Rasa and Rasa X will be installed in your system. Lastly, you don’t need to touch the code unless you want to change the API key or the OpenAI model for further customization.

Contribute to RajdeepBiswas/Ten_Minute_ChatBot_Python development by creating an account on GitHub.

Before we go ahead and create the chatbot, let us next, programmatically call the qnamaker. With closed models like GPT-3.5 and GPT-4, it is pretty difficult for small players to build anything of substance using LLMs since accessing the GPT model API can be quite expensive. Write a function to invoke the render_app function and start the application when the script is executed. Write the function that renders the chat history in the main content area of the Streamlit app.

Chatbots analyze customer inputs and reply with an appropriate mapped response. To train the chatbot, you can use recurrent neural networks with the intents JSON dataset, while the implementation can be handled using Python. Whether you want your chatbot to be domain-specific or open-domain depends on its purpose. As these chatbots process more interactions, their intelligence and accuracy also increase. For this project we’ll add training data in the three files in the data folder. We’ll write some custom actions in the actions.py file in the actions folder.

It might take 10 to 15 minutes to complete the process, so please keep patience. If you get any error, run the below command again and make sure Visual Studio is correctly installed along with the two components mentioned above. Next, run the setup file and make sure to enable the checkbox for “Add Python.exe to PATH.” After that, click on “Install Now” and follow the usual steps to install Python. Next, install the necessary libraries to build the chatbot. You will explore Llama 2’s conversational capabilities by building a chatbot using Streamlit and Llama 2.

On Windows, I would recommend Notepad++ (Download). Along with Python, Pip is also installed simultaneously on your system. In this section, we will learn how to upgrade it to the latest version.

To restart the AI chatbot server, simply move to the Desktop location again and run the below command. To start a data science project, first decide what sort of data science project you want to undertake, such as data cleaning, data analysis or data visualization. Then, find a good dataset on a website like data.world or data.gov. From there, you can analyze the data and communicate your results. This project involves identifying and extracting emotions from multiple sound files containing human speech.

The domain.yml file for this project can be found here. Rasa provides a basic sample project how to make chatbot in python to get started. Inside a new project folder, run the below command to set up the project.

When an end-user starts a conversation with the chatbot, this latter tries to match the incoming expressions to one of its Intents. 4- In your computer/virtual environment, create an app.py file and import these credentials, together with other useful libraries. However, we still have a major problem here, your machine should remain running all the time to allow the application to answer users’ requests. Sentiment analysis in its most basic form involves working out whether the user is having a good experience or not. In-case you want Rasa to call external server via REST API or API call, you can define your Custom Actions here. Remember you can create multiple Python Script for Rasa Custom Action.

I’ve formatted our custom API’s documentation into a Python dictionary called scoopsie_api_docs. This dictionary includes the API’s base URL and details our four endpoints under the endpoints key. The dictionary is then turned into a JSON string using json.dumps, indented by 2 spaces for readability.

In the meantime, I will show you how to set up polling in this next section. In a previous article I wrote about how I created a conversational chatbot with OpenAI. That is exactly the experience I want to create in this article. For ChromeOS, you can use the excellent Caret app (Download) to edit the code. After the installation is done, let’s install Gradio. Gradio allows you to quickly develop a friendly web interface so that you can demo your AI chatbot.

We use the Rasa framework and the FOURSQUARE Places API to make a chat bot that searches for restaurants and coffee houses

So it’s recommended to copy and paste the API key to a Notepad file for later use. After that, install PyPDF2 and PyCryptodome to parse PDF files. Open the Terminal and run the below command to install the OpenAI library. First off, you need to install Python along with Pip on your computer by following our linked guide. Make sure to enable the checkbox for “Add Python.exe to PATH” during installation. Modern businesses strive to deliver highly personalized services to their customers, which would not be possible without some form of customer categorization or segmentation.

The possibilities are endless with AI and you can do anything you want. If you want to learn how to use ChatGPT on Android and iOS, head to our linked article. And to learn about all the cool things you can do with ChatGPT, go follow our curated article.

As for the packages, you can use recommenderlab, ggplot2, reshape2 and data.table. PrivateGPT can be used offline without connecting to any online servers or adding any API keys from OpenAI or Pinecone. To facilitate this, it runs an LLM model locally on your computer. So, you will have to download a GPT4All-J-compatible LLM model on your computer. I have added detailed steps below for you to follow. The function sets the essential variables like chat_dialogue, pre_prompt, llm, top_p, max_seq_len, and temperature in the session state.

To run PrivateGPT locally on your machine, you need a moderate to high-end machine. To give you a brief idea, I tested PrivateGPT on an entry-level desktop PC with an Intel 10th-gen i3 processor, and it took close to 2 minutes to respond to queries. Currently, it only relies on the CPU, which makes the performance even worse.

If everything works as intended you are ready to add this bot to any of the supported channels. Finally, choose a name for the folder holding your serverless Function App and press enter. Now we need to install a few extensions that will help us create a Function App and push it to Azure, namely we want Azure CLI Tools and Azure Functions.

• Have a penchant to solve everyday computing problems.
• We should make sure to use Python version either 3.7 or 3.8.
• You can see, you are getting a reply from custom action which is written in python.
• In our case, we could have the breakfast count be fetched from a database.

Once all the dependencies are installed, run the below command to create local embeddings and vectorstore. This process will take a few seconds depending on the corpus of data added ChatGPT to “source_documents.” macOS and Linux users may have to use python3 instead of python in the command below. The domain.yml file describes the environment of the chat bot.

It also handles the selection of the Llama 2 model based on the user’s choice. Here, we demonstrate how Streamlit can be used to build decent user interfaces ChatGPT App for LLM applications with just a few lines of code. RASA is very easy to set up and you can quickly get started with your own personalized chatbot.

Your custom-trained ChatGPT-powered AI chatbot is ready. To start, you can ask the AI chatbot what the document is about. First, open the Terminal and run the below command to move to the Desktop. It’s where I saved the “docs” folder and “app.py” file. Now, open a code editor like Sublime Text or launch Notepad++ and paste the below code. Once again, I have taken great help from armrrs on Google Colab and tweaked the code to make it compatible with PDF files and create a Gradio interface on top.

In the left side, you can try to chat with your bot and on the right side you can see, which intent and reply is getting responded. You can type “hi” and in reply from bot, you will receive some response. You can copy the public URL and share it with your friends and family. The link will be live for 72 hours, but you also need to keep your computer turned on since the server instance is running on your computer. Once the LLM has processed the data, you will find a local URL.

We’ve only scratched the surface so far, but this is a great starting point. Topics like bot commands weren’t even covered in this article. A lot more documentation and helpful information can be found on the official discord.py API Reference page.

If you have downloaded a different model, you can define it under “MODEL_PATH”. Since we are using the default model, no change is needed. Once you hit create, there will be an auto validation step and then your resources will be deployed. We will get the values from the curl section of qnamaker.ai service published page. Once we are done with the training it is time to test the QnA maker.

Let’s set up the APIChain to connect with our previously created fictional ice-cream store’s API. The APIChain module from LangChain provides the from_llm_and_api_docs() method, that lets us load a chain from just an LLM and the api docs defined previously. We’ll continue using the gpt-3.5-turbo-instruct model from OpenAI for our LLM. When you create a run, you need to periodically retrieve the Run object to check the status of the run. You need to poll in order to determine what your agent should do next. OpenAI plans to add support for streaming to make this simpler.

The list of commands also installs some additional libraries we’ll be needing. Once the training is completed, the model is stored in the models/ folder. Now that the model is trained, we are good to test the chatbot. To start running the chatbot on the command line, use the following command.

To briefly add, you will need Python, Pip, OpenAI, and Gradio libraries, an OpenAI API key, and a code editor like Notepad++. All these tools may seem intimidating at first, but believe me, the steps are easy and can be deployed by anyone. In a breakthrough announcement, OpenAI recently introduced the ChatGPT API to developers and the public. Particularly, the new “gpt-3.5-turbo” model, which powers ChatGPT Plus has been released at a 10x cheaper price, and it’s extremely responsive as well. You can foun additiona information about ai customer service and artificial intelligence and NLP. Basically, OpenAI has opened the door for endless possibilities and even a non-coder can implement the new ChatGPT API and create their own AI chatbot.

Build a ChatGPT-esque Web App in Pure Python using Reflex

Easy Diffusion simplifies things with a user-friendly interface. A new desktop artificial intelligence app has me rethinking my stance on generative AIs place in my productivity workflow. Write a function to render the sidebar content of the Streamlit app. To get a Replicate token key, you must first register an account on Replicate using your GitHub account. Putting it all together, in one terminal we run the command below. Having done with the basic set up, its time to set up the next component, the FOURSQUARE API.

• For further details on Chainlit’s decorators and how to effectively utilize them, refer back to my previous article where I delve into these topics extensively.
• The components and the policies to be used by the models are defined in the config.yml file.
• You can also copy the public URL and share it with your friends and family.
• Library compatibility is a significant issue we’ll all need to watch going forward.

Rasa NLU has different components for recognizing intents and entities, most of which have some additional dependencies. Rasa X is a tool that helps you build, improve, and deploy AI Assistants that are powered by the Rasa framework. Now, run the code again in the Terminal, and it will create a new “index.json” file. Here, the old “index.json” file will be replaced automatically. Next, click on “Create new secret key” and copy the API key. Do note that you can’t copy or view the entire API key later on.

A common practice to store these types of tokens would be to use some sort of hidden file that your program pulls the string from so that they aren’t committed to a VCS. Python-dotenv is a popular package that does this for us. Let’s go ahead and install this package so that we can secure our token. You’ll get prompted with a menu to name your server. You can name the server anything you want, but I typically name it after the bot and treat it like a development environment. Before we get into coding a Discord bot’s version of “Hello World,” we need to set up a few other things first.

Of course, we can modify and tune it to make it way cooler. You can create a QnA Maker knowledge base (KB) from your own content, such as FAQs or product manuals. The function performs a debounce mechanism to prevent frequent and excessive API queries from a user’s input.

We will purposefully call our implementation an Agent and refer to the OpenAI SDK implementation as an Assistant to easily distinguish between the two. Simply feed the information to the AI to assume that role. Right-click on the “app.py” file and choose “Edit with Notepad++“. Make sure to replace the “Your API key” text with your own API key generated above.

While you don’t have to be a programmer, a basic understanding of logic would help you see what the code is doing. To sum up, if you want to use ChatGPT to make money, go ahead and build a tech product. Ever since OpenAI launched ChatGPT, things have changed dramatically in the tech landscape. The OpenAI Large Language Model (LLM) is so powerful that it can do multiple things, including creative work like writing essays, number crunching, code writing, and more. People are now using ChatGPT’s insane AI capabilities to make money on the side.