---
title: "Discussion on \"Multimodal RAG using Langchain Expression Language And GPT4-Vision\" | Hashnode"
description: "Discussion on \"Multimodal RAG using Langchain Expression Language And GPT4-Vision\". Many documents contain a mixture of content types including images an texts. Yet information captured in images is lost in most RAG applications. With the emergence of multimodal LLMs like (GPT4-V, LLaVA, or FUYU-8b) it is worth considering how to ut..."
url: "https://hashnode.com/posts/multimodal-rag-using-langchain-expression-language-and-gpt4-vision/658e9dae4f637bfb175ecaeb"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Multimodal RAG using Langchain Expression Language And GPT4-Vision](https://plaban.hashnode.dev/multimodal-rag-using-langchain-expression-language-and-gpt4-vision?utm_source=hashnode&utm_medium=feed)

Many documents contain a mixture of content types including images an texts. Yet information captured in images is lost in most RAG applications. With the emergence of multimodal LLMs like (GPT4-V, LLaVA, or FUYU-8b) it is worth considering how to ut...

Dec 29, 2023 · 15 min read · plaban.hashnode.dev  
Read the article

-   [#clip-transformers](https://hashnode.com/tag/clip-transformers)
-   [#multimodal](https://hashnode.com/tag/multimodal)
-   [#gpt4-v](https://hashnode.com/tag/gpt4-v)
-   [#langchain](https://hashnode.com/tag/langchain)
-   [#rag](https://hashnode.com/tag/rag)

## Written by

[Plaban Nayak](https://hashnode.com/@Plaban81)

@Plaban81

  
[View profile](https://hashnode.com/@Plaban81)

AI enthusiast

## Responses

Markdown supported · ⌘↵ to post

No responses yet.