DEV Community

Cover image for ✨ 7 AI Libraries EVERY Dev Needs to Know (to be a wiz)πŸ§™β€β™‚οΈ πŸͺ„
uliyahoo for CopilotKit

Posted on

✨ 7 AI Libraries EVERY Dev Needs to Know (to be a wiz)πŸ§™β€β™‚οΈ πŸͺ„


These days, any dev can build powerful things with AI.

No need to be a ML expert.

Here are the 7 best libraries you can use to supercharge your development and to impress users with state-of-the-art AI features.

These can give your project magical powers, so DON'T FORGET TO STAR & SUPPORT THEM 🌟

Image description

1. CopilotTextarea - AI-powered Writing in React Apps

Image description

A drop-in replacement for any react <textarea> with the features of Github CopilotX.

Autocompletes, insertions, edits.

Can be fed any context in real time or by the developer ahead of time.

import { CopilotTextarea } from "@copilotkit/react-textarea";
import { CopilotProvider } from "@copilotkit/react-core";

// Provide context...

// in your component...
Enter fullscreen mode Exit fullscreen mode

Star CopilotTextarea ⭐️

2. Tavily GPT Researcher - Get an LLM to Search the Web & Databases

Image description

Tavily enables you to add GPT-powered research and content generation tools to your React applications, enhancing their data processing and content creation capabilities.

# Create an assistant
assistant = client.beta.assistants.create(
        "type": "function",
        "function": {
            "name": "tavily_search",
            "description": "Get information on recent events from the web.",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "The search query to use. For example: 'Latest news on Nvidia stock performance'"},
                "required": ["query"]
Enter fullscreen mode Exit fullscreen mode

Star Tavily ⭐️

3. - Observability, Cost & Prompt Engineering Platform

Image description

Centralized platform for managing your OpenAI calls.

Optimize your prompts & token use. Keep track of your AI use.

Free & easy to integrate.

const prompt = await pezzo.getPrompt("AnalyzeSentiment");
const response = await;
Enter fullscreen mode Exit fullscreen mode

Star Pezzo ⭐️

4. CopilotPortal: Embed an actionable LLM chatbot inside your app.

Image description

A context-aware LLM chatbot inside your application that answers questions and takes actions.

Get a working chatBot with a few lines of code, then customize and embed as deeply as you need to.

import "@copilotkit/react-ui/styles.css";
import { CopilotProvider } from "@copilotkit/react-core";
import { CopilotSidebarUIProvider } from "@copilotkit/react-ui";

export default function App(): JSX.Element {
  return (
  <CopilotProvider chatApiEndpoint="/api/copilotkit/chat">

        <YourContent />

Enter fullscreen mode Exit fullscreen mode

Star CopilotPortal ⭐️

5. LangChain - Pull together AIs into action chains.

Image description

Easy-to-use API and library for adding LLMs into apps.

Link together different AI components and models.

Easily embed context and semantic data for powerful integrations.

from langchain.llms import OpenAI
from langchain import PromptTemplate
llm = OpenAI(model_name="text-davinci-003", openai_api_key="YourAPIKey")  # Notice "food" below, that is a placeholder for another value later
template = """ I really want to eat {food}. How much should I eat? Respond in one short sentence """

prompt = PromptTemplate(

final_prompt = prompt.format(food="Chicken")

print(f"Final Prompt: {final_prompt}")


print(f"LLM Output: {llm(final_prompt)}")

Enter fullscreen mode Exit fullscreen mode

Star LangChain ⭐️

6. Weaviate - Vector Database for AI-Enhanced Projects

Image description

Weaviate is a vector database optimized for fast, efficient searches across large datasets.

It supports integration with AI models and services from providers like OpenAI and Hugging Face, enabling advanced tasks such as data classification and natural language processing.

It's a cloud-native solution and highly scalable to meet evolving data demands.

import weaviate
import json

client = weaviate.Client(

uuid = client.data_object.create({


obj = client.data_object.get_by_id(uuid, class_name='MyClass')

print(json.dumps(obj, indent=2))
Enter fullscreen mode Exit fullscreen mode

Star Weaviate ⭐️

7. PrivateGPT - Chat with your Docs, 100% privately πŸ’‘

Image description

PrivateGPT allows for secure, GPT-driven document interaction within your applications, ensuring data privacy and enhancing context-aware processing capabilities.

PrivateGPT ensures privacy by locally processing and storing documents and context, without sending data to external servers.

from privategpt import PrivateGPT, DocumentIngestion, ChatCompletion

client = PrivateGPT(api_key='your_api_key')

def process_documents_and_chat(query, documents):
    ingestion_result = DocumentIngestion(client, documents)
    chat_result = ChatCompletion(client, query, context=ingestion_result.context)
    return chat_result

documents = ['doc1.txt', 'doc2.txt']
query = "What is the summary of the documents?"
result = process_documents_and_chat(query, documents)

Enter fullscreen mode Exit fullscreen mode

Star PrivateGPT ⭐️

[Bonus Library]. SwirlSearch - AI powered search.

Image description

LLM-powered search, summaries and output.

Searches multiple content sources simultaneously into integrated output.

Powerful for tailored in-app integrations of various data sources.

Star SwirlSearch ⭐️

Thanks for reading!

I hope these help you build some awesome stuff with AI.

Please like if you enjoyed & comment any other libraries or topics you would like to see.

Top comments (26)

uliyahoo profile image

Hey people πŸ‘‹

Hope you enjoyed the article! Don't forget to give it some reaction for support.

Let me know if there are any libraries you wish I included & what you'd like to see written about next!

Cheers 🍾🫑

best_codes profile image
Best Codes

Hmm… I think this is a case of a good listicle! I gave it a like and bookmark!

srbhr profile image
Saurabh Rai

That is an excellent list. I love all the projects. πŸ’–
Awesome Open Source πŸ”₯

uliyahoo profile image

Yes! These projects are all incredible and Open Source is the way!

nevodavid profile image
Nevo David

CopilotKit is interesting!
What can I do with it?

uliyahoo profile image

Thanks for the question,

It's a library for integrating AI into react apps.

You can:

  1. Easily insert a GPT chatBot that takes actions & answers questions

  2. Turn any into an AI-powered

Lmk if you have any more Q's about it πŸ‘©β€πŸŒΎ

steven0121 profile image

Great list!
Thank you for sharing!

uliyahoo profile image

Thanks for checking it out 😬

dasheck0 profile image
Stefan Neidig

Cool list. Thanks for sharing. Personally, I prefer Quivr over PrivateGPT. Otherwise great list.

qualar_mechanics profile image
Atai Barkai

I think a lot of these can work together well πŸ‘€
Very cool list!

uliyahoo profile image

Yup! Understated point.

The kinds of projects that even junior devs can build by mixing these libraries is hard to grasp.

fernandezbaptiste profile image

Nice repos! Thanks for sharing :D

uliyahoo profile image

Thanks for reading!

marisogo profile image

Great compilation, thanks for sharing!

uliyahoo profile image

Thanks for checking it out :)

david00112 profile image

CopilotKit looks pretty nice!

uliyahoo profile image

She is very nice 😍

nathan_tarbert profile image
Nathan Tarbert

Nice to see Swirl in the list :)

uliyahoo profile image

It's a great project 😬

guybuildingai profile image
Jeffrey Ip

Don't forget! For serious hardcore AI engineers only :)

matijasos profile image
Matija Sosic

nice list!

uliyahoo profile image


ranjancse profile image
Ranjan Dailata is really great. I simply love it.

uliyahoo profile image

Yup. My favorite observability library

thatanjan profile image
Anjan Shomodder

Thanks.πŸ™ I really needed the first one