Several AI companies, including LangChainAI and Llama Index, have announced new integrations and tools for multi-modal RAG applications following the launch of the GPT-4V API. LangChainAI has added support for images in LangSmith tracing, while Llama Index has introduced new tools for QA over data, including multi-modal RAG. Additionally, LakeraAI has released Lakera Guard to protect LangChainAI applications. The developments aim to enhance the experience of building with LangChain and using LLM chains.
There's a new multi-modal RAG stack that's emerging, letting users do QA over complex documents and images. Here's a diagram and 🧵 of what it consists of 👇 Multi-modal RAG extends beyond RAG in the following ways: * Input: The input can be a text or image query. *… https://t.co/8ZPxhzgJ3N https://t.co/kgVz9wdLvJ
⭐️RAG with multi-modal embeddings ⭐️ The launch of the GPT-4V API has sparked a surge in interest for multi-modal RAG applications. Multi-modal embeddings will become central to these apps, mapping text and images into a common space for retrieval. This week, @trychroma rolled… https://t.co/g03iNn8LvG https://t.co/7QU7i4xfpF
📝🔎 Multi-modal Indexing, Retrieval, RAG 🔎 🖼️ With the launch of GPT-4V, we’re excited to present comprehensive, new tools for QA over your data: multi-modal RAG. Unify text/images as a data source! We’re launching some new [beta] abstractions in @llama_index, a cookbook, and… https://t.co/b8f5gfNqwo https://t.co/eLy56oc1kx
✨ Building with #LLMs? You can now protect your @langchainai applications with Lakera Guard. 📖 Check out this guide to learn more: https://t.co/MHhGeq9wpd
🦜📷Multi-modal LangSmith Tracing With OpenAI releasing GPT4-V, we've now adding support for images in LangSmith tracing! This means you can now see images as they appear in your LLM calls, making it easy to debug multi-modal RAG pipelines Example Trace:… https://t.co/YUVxQqWHCy https://t.co/N7TnNr54ty
✨ We're excited to announce our new integration with @LangChainAI, allowing you to unlock more value from your LLM chains. Check out our docs to enable detailed tracing and custom analytics. This will take your "building with LangChain" experience to the next level! 🚀 https://t.co/MPvOr99FE1