Sabitlenmiş Tweet
Chroma
620 posts
Chroma
@trychroma
Data infrastructure for AI Apache 2.0
Katılım Mart 2022
55 Takip Edilen25.6K Takipçiler
exploring new ways to search and view my photos
• threejs interface
• smolVLM + roboflow RF-DETR computer vision
• chromaDB semantic search
this lets me use natural language search (city, color, object) across all my photos
AA@measure_plan
i built an app to search old travel photos on my computer with natural language queries using free local AI models: - smolVLM to describe the scene and colours - roboflow RF-DETR to detect objects - chromaDB to store metadata labels and run semantic search - python + streamlit for the interface fast and free search has been achieved internally
English
Your SSD is a cache. S3 is the real database.
That sounds wrong until you see the math:
• S3: $0.023/GB/month
• EBS gp3: $0.08/GB/month
• 3x replication on EBS: $0.24/GB/month
At 10TB, that's $230 vs $2,400/month.
The trick is making S3 feel like local disk. That's what disaggregated storage engines do — hot path stays fast, cold path stays cheap.
The future of databases isn't faster disks. It's smarter caching on infinite storage.
The next challenging question is how to build a latency-sensitive OLTP database based on S3.
#CloudNative #S3 #ObjectStorage #DatabaseEngineering #DistributedSystems #TiDB #DataInfra
English
#multimodal-embeddings" target="_blank" rel="nofollow noopener">docs.trychroma.com/integrations/e…
ZXX
Gemini Embedding 2 is now available in Chroma clients.
Google AI Developers@googleaidevs
Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.
English
Chroma retweetledi
lesser known but extremely powerful feature on @trychroma is forking. Cheap copy-on-write clones of a dataset, only billed for incremental storage.
Insanely useful for dataset versioning, shadowing a git repo etc
docs.trychroma.com/cloud/features…
English
Data pipelines can be brittle and hard to maintain.
Chroma Sync makes ingesting data for search simple.
trychroma.com/products/sync
English
New:
@perplexity_ai's new pplx-embed-v1 embedding models are available directly within our clients.
Perplexity@perplexity_ai
Today we're releasing two embedding model families, pplx-embed-v1 and pplx-embed-context-v1. These SOTA embedding APIs are designed specifically for real-world, web-scale retrieval. pplx.ai/pplx-embed
English
Discover more ADK integrations:
developers.googleblog.com/supercharge-yo…
English
New:
Our agent skill can add search to your product with one prompt.
More skills coming soon.
github.com/chroma-core/ag…
English
Our Schema() and Search() APIs give you powerful and flexible configuration for collections and searches on Chroma Cloud.
@itaismith walks us through it.
English