mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-15 16:22:27 +00:00
Jack Ye
734eb39dc3
Six groups were verbs -- Manage, Ingest, Train, Operate, Secure, Deploy -- and now name the thing rather than the action. Four more were sentence case. The page labels that were verb phrases follow: Add Computed Column becomes Computed Columns, Refresh Column becomes Column Refresh, Configuring Storage becomes Configuration, and Explain becomes Query Plans, which is also more accurate now that the page covers analyze as well. SQL statement pages take the keyword -- SELECT, DDL, DML, REFRESH, SHOW, EXPLAIN -- because a statement name is a noun and lowercase Select and Show read as instructions. Concept pages there keep noun phrases: Joins, Window Functions, Subqueries, Operators. Two duplicate labels are resolved on the way. Reranking sat in Semantic Search labelled Overview despite being the only page on its subject, and the Enterprise client page sat in SQL Reference labelled SQL next to the reference Overview; it is Client Connection now. Title case leaves prepositions and articles lowercase, so Needle in a Haystack and Hybrid Search on BEIR are already correct and unchanged.
72 lines
3.4 KiB
Plaintext
72 lines
3.4 KiB
Plaintext
---
|
|
title: "Multimodal Agent"
|
|
sidebarTitle: "Multimodal Agent"
|
|
description: "Build an AI agent that understands both text and images to help users find recipes using LanceDB and PydanticAI"
|
|
---
|
|
|
|
|
|
[](https://colab.research.google.com/drive/1pxavAGoXa-KSh_4HxNpvP2AjHPcIRpbq?usp=sharing)
|
|
|
|
Ever wanted to combine the power of text and images in a single AI agent? In this tutorial,
|
|
you'll build an agent that can understand both text and images to help users discover recipes that are relevant to them. The approach shown combines LanceDB's multimodal capabilities with [Pydantic AI](https://ai.pydantic.dev/) for the agentic workflow.
|
|
|
|
## Key Technologies {#key-technologies}
|
|
|
|
- **LanceDB**: Embedded retrieval library and multimodal lakehouse for efficient storage and retrieval
|
|
- **PydanticAI**: Modern AI agent framework with type safety
|
|
- **Sentence Transformers**: Text embeddings for semantic search
|
|
- **CLIP**: Vision-language model for image understanding
|
|
- **Streamlit**: Interactive web application framework
|
|
|
|
## Tutorial Overview {#tutorial-overview}
|
|
|
|
### Option 1: Notebook {#option-1-notebook}
|
|
The notebook shows how to work through the steps and prepare a small sample recipe dataset, generate both text and image
|
|
embeddings, store everything efficiently in LanceDB, and then build a PydanticAI agent with custom tools to
|
|
query it. You'll finish by testing the agent against a few example questions to see the full multimodal flow
|
|
end to end.
|
|
|
|
<Card title="Notebook" href="https://colab.research.google.com/drive/1pxavAGoXa-KSh_4HxNpvP2AjHPcIRpbq?usp=sharing">
|
|
This simple tutorial provides a step-by-step workflow with a small demo dataset of 4 examples.
|
|
No local setup required - just click and start learning about multimodal agents.
|
|
[](https://colab.research.google.com/drive/1pxavAGoXa-KSh_4HxNpvP2AjHPcIRpbq?usp=sharing)
|
|
</Card>
|
|
|
|
### Option 2: Demo Application (Local Setup) {#option-2-demo-application-local-setup}
|
|
The demo application is the full codebase: you'll download and process a real recipe dataset with thousands
|
|
of items, run a Streamlit chat interface that supports image upload, and follow a structure that includes
|
|
production-minded touches like error handling, logging, and monitoring. Everything you need to deploy is
|
|
included.
|
|
|
|
<Card icon="download" title="Download Tutorial Files" href="https://github.com/lancedb/vectordb-recipes/tree/main/applications/multimodal-recipe-agent">
|
|
Download the files for the full demo application here.
|
|
</Card>
|
|
|
|
### Dataset Information {#dataset-information}
|
|
- **Source**: [Kaggle Recipe Dataset](https://www.kaggle.com/datasets/pes12017000148/food-ingredients-and-recipe-dataset-with-images)
|
|
- **Size**: Thousands of recipes with images
|
|
- **Format**: CSV file with recipe data and image references
|
|
|
|
### Setup {#setup}
|
|
|
|
<CodeGroup>
|
|
```bash bash icon="code"
|
|
# 1. Extract the downloaded files to a folder
|
|
# 2. Navigate to the folder in terminal
|
|
cd multimodal-recipe-agent
|
|
|
|
# 3. Install dependencies with uv
|
|
uv sync
|
|
|
|
# 4. Download the Kaggle dataset
|
|
# Visit: https://www.kaggle.com/datasets/pes12017000148/food-ingredients-and-recipe-dataset-with-images
|
|
# Extract recipes.csv to the data/ folder
|
|
|
|
# 5. Import the dataset
|
|
uv run python import.py
|
|
|
|
# 6. Run the complete Streamlit chat application
|
|
uv run streamlit run app.py
|
|
```
|
|
</CodeGroup>
|