✨ 7 AI Libraries EVERY Dev Needs to Know (to be a wiz)🧙‍♂️ 🪄

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


// Provide context...
useMakeCopilotReadable(...)

// in your component...
<CopilotProvider>
    <CopilotTextarea/>
</CopilotProvider>`
```

Star CopilotTextarea ⭐️


---


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



![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/61mwfvsi4n9rnjet0j52.png)

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



```tsx 
# Create an assistant
assistant = client.beta.assistants.create(
    instructions=assistant_prompt_instruction,
    model="gpt-4-1106-preview",
    tools=[{
        "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"]
            }
        }
    }]
)
```
Star Tavily ⭐️


---


## 3. Pezzo.ai - Observability, Cost & Prompt Engineering Platform



![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/nxvbgi5zkghkb0t64npw.jpeg)

Centralized platform for managing your OpenAI calls. 

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

Free & easy to integrate. 

```tsx 
const prompt = await pezzo.getPrompt("AnalyzeSentiment");
const response = await openai.chat.completions.create(prompt);
```
Star Pezzo ⭐️


---
## 4. [CopilotPortal](https://github.com/RecursivelyAI/CopilotKit): Embed an actionable LLM chatbot inside your app. 



![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/szzmw5l8c9m4bce23bd3.png)


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.


```tsx
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">
      <CopilotSidebarUIProvider>

        <YourContent />

      </CopilotSidebarUIProvider>
    </CopilotProvider>
  );
}
```

Star CopilotPortal ⭐️


---

## 5. LangChain - Pull together AIs into action chains. 
![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/8s87kvm5jt5wmsv702r1.png)

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.

```tsx
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(
    input_variables=["food"],
    template=template,
)

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

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

print("-----------")

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

```

Star LangChain ⭐️



---

## 6. [Weaviate](https://github.com/weaviate/weaviate) - Vector Database for AI-Enhanced Projects


![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/brp7plpkk9sy44ubc14t.png)

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.


```tsx 
import weaviate
import json

client = weaviate.Client(
    embedded_options=weaviate.embedded.EmbeddedOptions(),
)

uuid = client.data_object.create({

})

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

print(json.dumps(obj, indent=2))
```

Star Weaviate ⭐️


---

## 7. [PrivateGPT](https://github.com/imartinez/privateGPT) - Chat with your Docs, 100% privately 💡


![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/ap81ce5j9chc5c543jl6.jpg)

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.


```tsx 
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)
print(result)

```

Star PrivateGPT ⭐️


---

## [Bonus Library]. SwirlSearch - AI powered search. 


![Image description](https://dev-to-uploads.s3.amazonaws.com/uploads/articles/extnr9oxhubs6m9x817a.png)

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.