alexwaresystems.pages.alexware.systems/homepage/#home…

My dream.

docs.tonic.ai/validate/about…

Tonic.ai lists several metrics to evaluate end-to-end LLM retrieval applications. It's indeed an intriguing resource to explore.

tensorchord / pgvecto.rs: Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database. ★1271 github.com/tensorchord/pg…

It is important to note that this is closely tied to the embedding model being used. The benchmark we conducted specifically focused on OpenAI's text-embedding-3-large model.

Maybe some binary embedding models have better performance. e.g. cohere Jina AI

TIL about binary vector search... apparently there's a trick where you can take an embedding vector like [0.0051, 0.017, -0.0186, -0.0185...] and turn that into a binary vector just reflecting if each value is > 0 - so [1, 1, -1, -1, ...] and still get useful cosine similarities!

After conducting a thorough benchmarking process using Qdrant's dataset, we have discovered fascinating insights regarding the superiority of binary vectors and shortened vectors.

blog.pgvecto.rs/my-binary-vect…

#NebulaGraph just hit 10K Github Stars❤️

github.com/vesoft-inc/neb…

Vector Search in PostgreSQL: Comparison blog.pgvecto.rs/pgvector-vs-pg…

Check out my latest blog post comparing pgvector and pgvecto.rs for vector search in PostgreSQL.

Here is the full blog post: blog.pgvecto.rs/pgvector-vs-pg…

#Database #Vectorsearch #PostgreSQL

pgvecto.rs 0.2: Unifying Relational Queries and Vector Search in PostgreSQL

Let's check out the enhanced efficiency and enabling complex queries within PostgreSQL.

#DEVCommunity #Database
dev.to/gaocegege/pgve…

Super impressed by #Immich . So long Google Photos...

Our Vector Search Extension in Postgres, TensorChord pgvecto.rs, Reaches 1 Million Docker Pulls! 🎉

#GenerativeAI #vectordatabase

Just updated Tabby's leaderboard (leaderboard.tabbyml.com) for the StarCoder2 model series from BigCode

Unfortunately, they're not performing as well as HumanEval@1 suggest. DeepSeek models remain the best OSS choice for AI x Code Completion tasks 👏

Gow Tham Nilesh They've been shipping features at a lightning speed though, so maybe give it another try? I used to face issues with Typesense search, but they've migrated to pgvecto.rs in the recent updates and things have improved a lot.

Conducted benchmarks on the TensorChord pgvecto.rs new binary vector recently and found that Canva is an excellent platform for creating charts.

The data and style components are separate, allowing for easy editing and customization in the UI

✨Introducing Devv Agent

A new mode designed to deliver more accurate and detailed responses.

Underpinning Devv Agent is a Multi-agent architecture that employs different agents and language models based on the specific requirements of the task at hand

devv.ai/en

LLMs remind me of proprietary firmware.

Check out ai-infra.fun for more products!
The landscape also encourages contributions, so if you have something to add: github.com/tensorchord/ai…

AI infra is pretty chaotic. Thus I created an AI Infrastructure Landscape (ai-infra.fun) to simplify the crowded space.

It includes frameworks like LangChain, LlamaIndex 🦙 along with platforms like Replicate . Databases like Weaviate • vector database are also featured.

There are three approaches to RAG: Naive, Advanced, and Modular. In Leonie's blog post, she shows you how to go from a naive implementation to an advanced pipeline using LlamaIndex 🦙 and Weaviate • vector database 🫡

An advanced RAG pipeline is categorized into three buckets:
•…