index.html

---
title: "LangStream: an Event-Driven Developer Platform for LLM Apps"
description: An Event-Driven Developer Platform for LLM Apps
image: /images/langstream-screen-shot.png
---
<section class="hero">
	<div class="text-container">
		<h1 class="editable h1-logo">
			<div>
				Use the Power of Streaming to Connect
			</div>
				<div class="logo-slide">
					<div>
						<img  src="/images/OpenAI_Logo.svg">
					</div>
					<div>
						<img  src="/images/hf-logo-with-title.svg">
					</div>
					<div>
						<img  src="/images/vertex-ai.png">
					</div>
				</div>

			<div>
							To

			</div>
			<div class="logo-slide-2">
				<div>
					<img  src="/images/pinecone.png">
				</div>
				<div>
					<img  src="/images/milvus_Logo_ee3ae48b61.png">
				</div>
				<div>
					<img  src="/images/cassandra-vertical.webp">
				</div>
				<div>
					<img  src="/images/ds-astra-db_stacked-lockup_light-background.png">
				</div>
			</div>
			<div style="padding-top: 10px;">
				And Solve Your Day 2 Problems
			</div>
		
		</h1>
		<div class="cta button alt"><a href="/quick-start">Start Building Today</a></div>
	</div>
</section>

<div class="content">
	<section>
		<div class="container flex">
			<div class="text editable">
				<h2><strong>Build</strong> Q&A chat over unstructured text <strong>in minutes</strong></h2>
				<p class="subtext editable">Using no-code agents, you can create text-to-vector-database pipelines and prompt templating agents 
					for a variety of LLMs.</p>
				</p>
			</div>
			<div class="image">
				<img alt="A animation of a chatbot powered by LangStream" src="{{ site.baseurl }}/images/ls-chatbot-gif.gif"/>
			</div>
		</div>
	</section>
	<section>
		<div class="container flex">
			<div class="text editable">
				<h2>Use the <strong>latest</strong> Gen AI technologies</strong></h2>
				<p class="subtext editable">LangStream integrates with LLMs from OpenAI, Google Vertex AI, and 
					Hugging Face, Vector databases like Pinecone and DataStax, Python libraries
					like LangChain and LlamaIndex. 
				</p>
				</p>
			</div>
			<div class="image">
				<img alt="Logos from OpenAI, Google Vertex AI, Hugging Face, Pinecone, DataStax, Milvus, LangChain, LlamaIndex" src="{{ site.baseurl }}/images/langstream-logos-2.png" alt="Gen AI logos" />
			</div>
		</div>
	</section>

	<section>
		<div class="container flex">
			<div class="text editable">
				<h2>Manage <strong>embeddings</strong> in your vector database</strong></h2>
				<p class="subtext editable">Create pipelines that automatically create and update embeddings in your vector database
					for unstructured data (PDFs, Word documents, HTML) using proprietary and open-source embeddings models. 
				</p>
				</p>
			</div>
			<div class="image">
				<img alt="Abstract image showing vector embeddings for structured and unstructured data" src="{{ site.baseurl }}/images/vectors.jpeg" alt="Gen AI logos" />
			</div>
		</div>
	</section>


	<section>
		<div class="container flex">
			<div class="text editable">
				<h2>Code and deploy in <strong>Visual Studio Code</strong></h2>
				<p class="subtext editable">To make it easier to build LangStream apps, we have created a
					<a target="_blank" href="https://marketplace.visualstudio.com/items?itemName=DataStax.langstream">

					VS Code extension
					</a>
					that includes app deployment, app updating, log analysis, and code snippets.
				</p>
			</div>
			<div class="image">
				<img alt="Screen shot from LangStream Visual Studio Code Extension" src="{{ site.baseurl }}/images/vs-code.png" alt="Streams" />
			</div>
		</div>
	</section>
	<section>
		<div class="container flex">
			<div class="text editable">
				<h2>Declare an app and <strong>deploy</strong> it to dev or prod</h2>
				<p class="subtext editable">In LangStream an application consists of pipelines defined using 
					configuration files or Python. Deploy to a local development environment
					or to a production environment, powered by proven tech: Kubernetes and Kafka.
				</p>
			</div>
			<div class="image">
				<img src="{{ site.baseurl }}/images/ls-deploy-screen.gif" alt="Screenshot of the LangStream CLI" class="screenshot editable" />
			</div>
		</div>
	</section>

	<section>
		<div class="container flex">
			<div class="text editable">
				<h2>Bring <strong>your existing data</strong> to the LLM</h2>
				<p class="subtext editable">LangStream can tap into the data you already have when engineering a prompt to send to the LLM.
					Query SQL and no-SQL databases or use Kafka Connect connectors to access 
					the data you already have.
				</p>
			</div>
			<div class="image">
				<img src="{{ site.baseurl }}/images/data-integration-logos.png" alt="Logos for Kafka Connect, MongoDB, Cassandra, Postgres, Redis, MySQL, and Snowflake" />
			</div>
		</div>
	</section>

	<section>
		<div class="container flex">
			<div class="text editable">
				<h2>Fix your day 2 problems with an <strong>event-driven</strong> architecture</h2>
				<p class="subtext editable">LangStream is a streaming framework using an event-driven architecture
					meaning it is asynchronous, decoupled, fault tolerant, and scalable.
				</p>
			</div>
			<div class="image">
				<img src="{{ site.baseurl }}/images/langstream-screen-shot.png" alt="Screenshot of the LangStream pipeline in the UI" class="screenshot editable" />
			</div>
		</div>
	</section>


	<section class="bottom-cta">
		<h2 class="editable">Start <strong>building</strong> a powerful Gen AI app today</h2>
		<div class="button alt"><a href="/quick-start">Get Started</a></div>
	</section>
</div>