mirror of
https://github.com/supabase/supabase.git
synced 2026-10-09 19:35:06 +03:00
Danny White
ba107edbda
## What kind of change does this PR introduce? Frontmatter name change. ## What is the current behavior? We repeatedly mistake `thumb` for `image` and visa versa, meaning the wrong images are used for Open Graph and in-site thumbnails on blog posts. Events and case studies use the same naming convention too. ## What is the new behavior? These two bits of frontmatter are renamed for clarity: - Blog posts: `imgThumb` + `imgSocial` That mapping for blog posts: - `thumb` is now `imgThumb` - `image` is now `imgSocial` These related bits remain as-is: - Events - Case studies The [www/README.md](https://github.com/supabase/supabase/blob/dnywh/chore/blog-image-frontmatter/apps/www/README.md#best-practices) file has been expanded to clarify all of the above. It now also provides instructions on image optimisation. ## To test A lot of files were touched here. Please help make sure: - [ ] The CMS works as intended. This is the **biggest unknown**. - [x] All blog posts render the correct image as their on-site thumbnail and Open Graph image. You can test the latter by firing up a draft iMessage. Online Open Graph services like Facebook cache images, so aren’t reliable. - [x] All events render their correct images - [x] All case studies render their correct images - [x] All customer stories render their correct images ([known issue](https://supabase.slack.com/archives/C072FL5KKKP/p1768888063209359?thread_ts=1768885681.502169&cid=C072FL5KKKP), predates this work)
78 lines
4.9 KiB
Plaintext
78 lines
4.9 KiB
Plaintext
---
|
|
name: Firecrawl
|
|
title: Firecrawl switches from Pinecone to Supabase Vector for PostgreSQL vector embeddings.
|
|
# Use meta_title to add a custom meta title. Otherwise it defaults to '{name} | Supabase Customer Stories':
|
|
meta_title: Firecrawl switches from Pinecone to Supabase Vector for PostgreSQL vector embeddings.
|
|
description: How Firecrawl boosts efficiency and accuracy of chat powered search for documentation using Supabase Vector.
|
|
# Use meta_description to add a custom meta description. Otherwise it defaults to {description}:
|
|
meta_description: How Firecrawl boosts efficiency and accuracy of chat powered search for documentation using Supabase Vector.
|
|
author: paul_copplestone
|
|
author_title: Supabase
|
|
author_url: https://github.com/kiwicopple
|
|
author_image_url: https://avatars2.githubusercontent.com/u/10214025?s=400&u=c6775be2ae667e2acae3ccd347fed62bb3f5b3e7&v=4
|
|
logo: /images/customers/logos/firecrawl.png
|
|
logo_inverse: /images/customers/logos/light/firecrawl.png
|
|
tags:
|
|
- supabase
|
|
date: '2023-05-05'
|
|
company_url: 'https://firecrawl.dev/'
|
|
stats:
|
|
[
|
|
{ stat: '00,000', label: Example stat },
|
|
{ stat: '00,000', label: Example stat },
|
|
{ stat: '00,000', label: Example stat },
|
|
]
|
|
misc: [{ label: 'Backed by', text: 'Y Combinator' }]
|
|
about: Firecrawl is Chat Powered Search for Documentation.
|
|
# "healthcare" | "fintech" | "ecommerce" | "education" | "gaming" | "media" | "real-estate" | "saas" | "social" | "analytics" | "ai" | "developer-tools"
|
|
industry: ['ai', 'saas', 'developer-tools']
|
|
# "startup" | "enterprise" | "indie_dev"
|
|
company_size: 'startup'
|
|
# "Asia" | "Europe" | "North America" | "South America" | "Africa" | "Oceania"
|
|
region: 'North America'
|
|
# "database" | "auth" | "storage" | "realtime" | "functions" | "vector"
|
|
supabase_products: ['database', 'vector']
|
|
---
|
|
|
|
[Firecrawl](http://firecrawl.dev/) provides a chat-powered search engine for technical documentation. Their AI-powered search tool makes it easier for developers and other technical users to find relevant information in complex documentation. Users can simply ask questions in natural language, and the tool returns the most relevant answers. Firecrawl's search engine also provides detailed analytics, which helps teams identify knowledge gaps and areas for improvement in their documentation. Firecrawl has integrated with some of the largest open source projects in the space such as LangChain and LlamaIndex.
|
|
|
|
## The Challenge
|
|
|
|
Firecrawl was experiencing tremendous success, growing Weekly Active Users by nearly 300% since March. They needed a tool to store and search through large amounts of vector data to improve the efficiency and accuracy of their similarity search operations. They tried Faiss, Weaviate, and Pinecone, but found them to be expensive and not very intuitive, especially when it came to storing metadata along with the vectors.
|
|
|
|
## Why they chose Supabase
|
|
|
|
Firecrawl lear that Supabase supports [pgvector](https://supabase.com/docs/guides/database/extensions/pgvector) and found it to be a simple and cost-effective solution. They were impressed with the open source nature of Supabase, as well as its ability to store metadata alongside the vectors. They also appreciated the intuitive interface and ease of use.
|
|
|
|
<Quote img="caleb-peffer.jpg" caption="Caleb Peffer - CEO, Firecrawl">
|
|
We tried other vector databases - we tried Faiss, we tried Weaviate, we tried Pinecone. We found
|
|
them to be incredibly expensive and not very intuitive. If you're just doing vector search they're
|
|
great, but if you need to store a bunch of metadata that becomes a huge pain.
|
|
</Quote>
|
|
|
|
## What They Built
|
|
|
|
Using [Supabase Vector](https://supabase.com/modules/vector), Firecrawl was able to build a more efficient and accurate search function for their AI chatbot. By storing vector data alongside metadata in Supabase, Firecrawl was able to quickly and easily search through their customers documentation to find the most relevant responses to queries. They found that Supabase's solution was just as performant as dedicated vector databases, but without the high cost.
|
|
|
|
|
|
|
|
## The Results
|
|
|
|
Thanks to Supabase Vector, Firecrawl was able to significantly improve the efficiency and accuracy of their Chat Powered Search for Documentation. They were able to build faster and more cost-effectively using Supabase's open source stack.
|
|
|
|
<Quote img="caleb-peffer.jpg" caption="Caleb Peffer - CEO, Firecrawl">
|
|
We looked at the alternatives and chose Supabase because it's open source, it's simpler, and, for
|
|
all the ways we need to use it, Supabase has been just as performant - if not more performant -
|
|
than the other vector databases.
|
|
</Quote>
|
|
|
|
To learn more about how Supabase Vector can help you store vector embeddings at scale and build AI apps with ease, [reach out to us](https://forms.supabase.com/enterprise).
|
|
|
|
## Tech stack
|
|
|
|
- React
|
|
- Vercel
|
|
- Next.js
|
|
- Express
|
|
- Supabase
|