github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-01 19:03:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update multi-modal multi-vector template README.md (#14992)

Browse Source
This commit is contained in:
Lance Martin 2023-12-20 20:07:12 -08:00 committed by GitHub
parent 448b4d3522
commit 8996d1a65d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
templates/rag-chroma-multi-modal-multi-vector/README.md
View File

@ -1,13 +1,15 @@
# rag-chroma-multi-modal-multi-vector
Multi-modal LLMs enable text-to-image retrieval and question-answering over images.
Multi-modal LLMs enable visual assistants that can perform question-answering about images.
You can ask questions in natural language about a collection of photos, retrieve relevant ones, and have a multi-modal LLM answer questions about the retrieved images.
This template create a visual assistant for slide decks, which often contain visuals such as graphs or figures.
This template performs text-to-image retrieval for question-answering about a slide deck, which often contains visual elements that are not captured in standard RAG.
It uses GPT-4V to create image summaries for each slide, embeds the summaries, and stores them in Chroma.
Given a question, relevat slides are retrieved and passed to GPT-4V for answer synthesis.
This will use GPT-4V for image captioning and answer synthesis.
![mm-captioning](https://github.com/langchain-ai/langchain/assets/122662504/5277ef6b-d637-43c7-8dc1-9b1567470503)
## Input
@ -124,4 +126,4 @@ We can access the template from code with:
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/rag-chroma-multi-modal-multi-vector")
```
```