Introducing the New Coding Template: An app template for all your coding use cases.

Welcome to the?AI in 5?newsletter with Clarifai!

Every week we bring you new models, tools, and tips to build production-ready AI!

This week, we bring you: ??

• New Coding App template
• Build RAG using the latest GPT-4o (omni)
• New Symmetric and Asymmetric text search capabilities on the Platform
• New LLMs: WizardLM-2-8x22B, Mixtral-8x22B-instruct, Qwen1.5-110B-Chat and DeepSeek-V2-Chat.
• AI tip of the week - Importing Data with CSV and TSV Files

Introducing the Coding App template! ????

The Coding App template explores various coding scenarios and includes pre-built workflows tailored to address different coding use cases, employing diverse models specialized for each unique situation.

There are various workflows specialized for Code Completion, Code Generation, Code Summarization, Code Refactoring and Code Debugging.

Check out the template here and get started by cloning the app template.

RAG using GPT-4o (omni) ??

RAG using GPT-4o (omni) in just 4 lines of code! GPT-4o is a multimodal AI model from Open AI that offers rapid response times and improved performance across languages and tasks while incorporating advanced safety features.

Building a RAG system is simple with the Clarifai?Python SDK.

Check out the post here.?

Symmetric and Asymmetric text search capabilities??

Added new search capabilities to the platform.

Symmetric search allows you to find text inputs that closely resemble other text inputs, facilitating easy identification of similar content.

In contrast, asymmetric search empowers you to search for text inputs that effectively answer specific query questions, enhancing the precision and relevance of search results.

You can now experience these features on the platform. All you need to do is select your base workflow as Text while creating your Clarifai app!

New wrapped LLMs on the Platform??

• WizardLM-2-8x22B: A state-of-the-art open-source LLM, excelling in complex tasks like chat, reasoning, and multilingual understanding, competing closely with leading proprietary models. The model is designed to be both cost-effective and powerful, providing state-of-the-art performance for enterprise applications.
• Mixtral-8x22B-instruct: The latest and largest mixture of expert LLM from Mistral AI using a mixture of 8 experts (MoE) 22b models. The model comes with multilingual support and can handle a context of 32k tokens.
• Qwen1.5-110B-Chat: 100 billion parameter model, demonstrates competitive performance in base language tasks and significant improvements in chatbot evaluations and boasts multilingual capabilities.
• DeepSeek-V2-Chat: A high-performing, cost-effective 236 billion MoE LLM excelling in diverse tasks such as chat, code generation, and math reasoning.

AI tip of the week: ??

Importing Data with CSV and TSV Files!

You can upload your text directly to the platform from a .csv or .tsv file. This means you can work with your favourite spreadsheet software or text editor when preparing your data for upload.

This can be especially useful when you want to upload inputs and concepts at the same time. You also have the "CSV template" to get started.

Check out the guide here.

Want to learn more from Clarifai? “Subscribe” to make sure you don’t miss the latest news, tutorials, educational materials, and tips. Thanks for reading!