github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-02 03:15:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Ollama multi-modal template README.md (#14994)

Browse Source
This commit is contained in:
Lance Martin 2023-12-20 20:07:27 -08:00 committed by GitHub
parent 1db7450bc2
commit 94586ec242
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
templates/rag-multi-modal-local/README.md
View File

@ -1,13 +1,17 @@
# rag-multi-modal-local
Visual search is a famililar application to many with iPhones or Android devices: use natural language to search across your photo collection.
Visual search is a famililar application to many with iPhones or Android devices. It allows user to serch photos using natural language.
With the release of open source, multi-modal LLMs it's possible to build this kind of application for yourself and have it run on your personal laptop.
With the release of open source, multi-modal LLMs it's possible to build this kind of application for yourself for your own private photo collection.
This template demonstrates how to perform visual search and question-answering over a collection of photos.
This template demonstrates how to perform private visual search and question-answering over a collection of your photos.
It uses OpenCLIP embeddings to embed all of the photos and stores them in Chroma.
Given a set of photos, it will use OpenCLIP embeddings to index them, retrieve photos relevant to user question, and use Ollama to run a local, open-source multi-modal LLM to answer questions about the retrieved photos.
Given a question, relevat photos are retrieved and passed to an open source multi-modal LLM of your choice for answer synthesis.
![mm-local](https://github.com/langchain-ai/langchain/assets/122662504/da543b21-052c-4c43-939e-d4f882a45d75)
## Input
@ -119,4 +123,4 @@ We can access the template from code with:
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/rag-chroma-multi-modal")
```
```