Skip to main content


Visual search is a famililar application to many with iPhones or Android devices. It allows user to search photos using natural language.

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 private visual search and question-answering over a collection of your photos.

It uses nomic-embed-vision-v1 multi-modal embeddings to embed the images and Ollama for question-answering.

Given a question, relevant photos are retrieved and passed to an open source multi-modal LLM of your choice for answer synthesis.


Supply a set of photos in the /docs directory.

By default, this template has a toy collection of 3 food pictures.

Example questions to ask can be:

What kind of soft serve did I have?

In practice, a larger corpus of images can be tested.

To create an index of the images, run:

poetry install


This template will use nomic-embed-vision-v1 multi-modal embeddings to embed the images.

The first time you run the app, it will automatically download the multimodal embedding model.

You can choose alternative models in rag_chroma_multi_modal/, such as OpenCLIPEmbeddings.

langchain_experimental.open_clip import OpenCLIPEmbeddings

model_name="ViT-H-14", checkpoint="laion2b_s32b_b79k"

vectorstore_mmembd = Chroma(


This template will use Ollama.

Download the latest version of Ollama:

Pull the an open source multi-modal LLM: e.g.,

ollama pull bakllava

The app is by default configured for bakllava. But you can change this in and for different downloaded models.


To use this package, you should first have the LangChain CLI installed:

pip install -U langchain-cli

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package rag-chroma-multi-modal

If you want to add this to an existing project, you can just run:

langchain app add rag-chroma-multi-modal

And add the following code to your file:

from rag_chroma_multi_modal import chain as rag_chroma_multi_modal_chain

add_routes(app, rag_chroma_multi_modal_chain, path="/rag-chroma-multi-modal")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. You can sign up for LangSmith here. If you don't have access, you can skip this section

export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at We can access the playground at

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/rag-chroma-multi-modal")

Was this page helpful?

You can leave detailed feedback on GitHub.