examples/llama-3.3-70b-instruct-turbo
Public

Prompt: System Instructions

Fork the Pipe — to testit in the playground here

About

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Variables

⌘ Langbase helps developers ship composable hyper-personalized AI apps and features.

Start by building AI assistants Pipes
Then create managed semantic memory (RAG) so your AI can talk to your data
⌘ Langbase is the composable infrastructure and developer experience to build, collaborate, and deploy secure, composable AI apps/features. Our mission is to make AI accessible to everyone, any developer not just AI/ML experts. We are the only composable AI infrastructure. That's all we do.

Join today
Langbase is free for anyone to get started. We're already processing billions of AI messages tokens monthly, used by thousands of developers. Tweet us — what will you ship with Langbase?

It all started with a developer thinking …

GPT is amazing, I want it everywhere, that's what ⌘ Langbase does for me. — AA

⌘ Langbase Pipes: Build custom AI assistants and agents with the LLM Computing primitive called Pipe. Pipe is the fastest way to ship your AI apps/features in production. It's like having a composable GPT anywhere.

⌘ Langbase Memory (RAG): Build a managed semantic RAG based AI assistants with Memory. Extend LLM Memory by 10M+ tokens to build assistants with which uses your data to personalize the AI experience.

⌘ Langbase AI Studio: Our dashboard is your playground to build, collaborate, and deploy AI. It allows you to experiment with your pipes in real-time, with real data, store messages, version your prompts, and truly helps you take your idea from building prototypes to deployed in production (with predictions on usage, cost, and effectiveness). Langbase is a complete developers platform for AI.

⌘ Collaborate: Invite all team members to collaborate on the pipe. Build AI together.
⌘ Developers & Stakeholders All your R&D team, engineering, product, GTM (marketing, sales), and even stakeholders can collaborate on the same pipe. It's like a Google Doc x GitHub for AI. That's what makes it so powerful.
API Reference
Generate
Learn about the generate API and how to use it to generate completions from a generate.

Chat
Learn about the chat API and how to use it to generate chat completions from a chat pipe.

Guides
Quickstart Guide
Get started with pipes through an AI example.

RAG Quickstart Guide
Begin creating your own RAG applications.

Integration: Next.js
Integrate a Pipe into your Next.js application.

Features
Generate
A Pipe tailored for LLM completions, with all standard Pipe features.

Chat
A Pipe crafted for chat-like completions. Ideal for building chat-bots, ChatGPT, and similar apps.

Prompt
A prompt sets the context for the LLM and the user, shaping the conversation and responses.

Variables
Add variables to a prompts in Pipes to make them dynamic.

Few-shot
Few-shot messages enable LLMs to learn from simple system and AI prompt examples.

Safety
Define a safety prompt for any LLM.

Logs
Detailed logs of each Pipe request with information like LLM request cost etc.

Stream
Stream LLM responses for all supported models on both the API and Langbase dashboard inside a Pipe.

Moderation
Set custom moderation settings for OpenAI models in a Pipe.

JSON mode
JSON mode of Pipe instructs the LLM to give output in JSON.

Store messages
Store user prompts and LLM completions in a Pipe to review in Usage.

Versions
Versions in Pipe lets you see how its config has changed over time.

Experiments
Experiments test latest Pipe config with the last five "generate" requests to see its impact on LLM responses.

Readme
Add a README to a Pipe to provide additional information.

Pipe API
Pipe offers two APIs, i.e., Generate and Chat, to interact with LLMs and integrate them into an applications.

Keysets
Add all LLM API keys once to seamless switch between models in a Pipe.

Usage
View insights of each Pipe request.

Fork
Make a copy of any Pipe either in your account or within any of your organizations.

Examples
Multiple ready to use examples to quickly setup the Pipe.

Model Presets
Configure response parameters of LLMs in a Pipe using model presets.

Organizations
Foster collaboration among users within a shared workspace via organizations.

Open Pipes
Open Pipes on Langbase allows users to create and share pipes with the public.

Function calling
Call functions to perform operations like fetching data from an API, etc.
Composable AI: The Developer Friendly Future of AI Infrastructure
Note
We're actively working on an interactive guide to explain this better. Bear with us!
In software engineering, composition is a powerful concept. It allows for building complex systems from simple, interchangeable parts. Think Legos, Docker containers, React components. Langbase extends this concept to AI infrastructure with our Composable AI stack using Pipes and Memory.

Example: Composable AI Email Agent
⌘ Langbase Email Agent
⌘ Langbase Email Agent reference architecture
I have built an AI email agent that can read my emails, understand the sentiment, summarize, and respond to them. Let's break it down to how it works, hint several pipes working together to make smart personalized decisions.

I created a pipe: email-sentiment — this one reads my emails to understand the sentiment
email-summarizer pipe — it summarizes my emails so I can quickly understand them
email-decision-maker pipe — should I respond? is it urgent? is it a newsletter?
If email-decision-maker pipe says yes, then I need to respond. This invokes the final pipe
email-writer pipe — writes a draft response to my emails with one of the eight formats I have
Why Composable AI is powerful?
Ah, the power of composition. I can swap out any of these pipes with a new one.

Flexibility: Swap components without rewriting everything
Reusability: Build complex systems from simple, tested parts
Scalability: Optimize at the component level for better performance
Observability: Monitor and debug each step of your AI pipeline
Control flow
Maybe I want to use a different sentiment analysis model
Or maybe I want to use a different summarizer when I'm on vacation
Or maybe I want to use a different decision maker on a busy day.
Extensibility
Add more when needed: I can also add more pipes to this pipeline. Maybe I want to add a pipe that checks my calendar or the weather before I respond to an email. You get the idea. Always bet on composition.
Eight Formats to write emails: And I have several formats. Because Pipes are composable, I have eight different versions of email-writer pipe. I have a pipe email-pick-writer that picks the correct pipe to draft a response with. Why? I talk to my friends differently than my investors, reports, managers, vendors — you name it.
Long-term memory and context awareness
By the way, I have all my emails in an emails-store memory, which any of these pipes can refer to if needed. That's managed semantic RAG over all the emails I have ever received.
And yes, my emails-smart-spam memory knows all the pesky smart spam emails that I don't want to see in my inbox.
Cost & Observability
Because each intent and action is mapped out Pipe — which is an excellent primitive for using LLMs, I can see everything related to cost, usage, and effectiveness of each pipe. I can see how many emails were processed, how many were responded to, how many were marked as spam, etc.
I can switch LLMs for any of these actions, fork a pipe, and see how it performs. I can version my pipes and see how the new version performs against the old one.
And we're just getting started …
Why Developers Love It
Modular: Build, test, and deploy pipes x memorysets independently
Extensible: API-first no dependency on a single language
Version Control Friendly: Track changes at the pipe level
Cost-Effective: Optimize resource usage for each AI task
Stackholder Friendly: Collaborate with your team on each pipe and memoryset. All your R&D team, engineering, product, GTM (marketing, sales), and even stakeholders can collaborate on the same pipe. It's like a Google Doc x GitHub for AI. That's what makes it so powerful.
Each pipe and memory are like a docker container. You can have any number of pipes and memorysets.

Can't wait to share more exciting examples of composable AI. We're cookin!!

Let's go! 👊

Tools

No tools added to the Pipe.

Safety

Readme

Llama-3.3-70B-Instruct-Turbo

Langbase

examples/llama-3.3-70b-instruct-turbo
Public

Prompt: System Instructions

About

Meta

JSON mode

Moderation

Stream mode

Store messages

Variables

{{Langbase}}

Tools

Safety

Readme

Llama-3.3-70B-Instruct-Turbo

⌘Langbase

Prompt: System Instructions

About

Meta

JSON mode

Moderation

Stream mode

Store messages

Variables

{{Langbase}}

Tools

Safety

Readme

Llama-3.3-70B-Instruct-Turbo

Langbase