HTTP vs. WebSockets: Which one is the fastest for Postgres queries at the edge? (neon.tech)

Screenshot of neon.tech: HTTP vs. WebSockets: Which one is the fastest for Postgres queries at the edge?

First screen, captured 3 years ago.

Looks similar

Screenshot of neon.tech: 20x faster than pgvector: HNSW index in Postgres with pg_embedding

20x faster than pgvector: HNSW index in Postgres with pg_embedding (neon.tech)

79 points by nikita 3 years ago | 33 comments

Screenshot of neon.tech: On-disk HNSW index for Postgres with pg_embedding

On-disk HNSW index for Postgres with pg_embedding (neon.tech)

38 points by nikita 3 years ago | 19 comments

$Screenshot of neon.tech: Bringing psql’s \d to your web browser$

Bringing psql’s \d to your web browser (neon.tech)

71 points by gmac 2 years ago | 25 comments

Screenshot of neon.com: Elephantshark, a tool to monitor Postgres network traffic

Elephantshark, a tool to monitor Postgres network traffic (neon.com)

20 points by gmac 1 year ago | 0 comments

Screenshot of neon.com: Implementing a Kalman Filter in Postgres

Implementing a Kalman Filter in Postgres (neon.com)

58 points by carlotasoto 1 year ago | 9 comments

Screenshot of neon.com: Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

Beating GPT-5.6 Sol on retrieval with 100x cheaper open models (neon.com)

415 points by moonikakiss 2 months ago | 114 comments

Neon blog post describing how a 4B open-source model post-trained with Castform matches GPT-5.6 Sol on search-result retrieval accuracy at about 100x lower cost.

neon castform post-training retrieval

Looks similar

20x faster than pgvector: HNSW index in Postgres with pg_embedding(neon.tech)

On-disk HNSW index for Postgres with pg_embedding(neon.tech)

Bringing psql’s \d to your web browser(neon.tech)

Elephantshark, a tool to monitor Postgres network traffic(neon.com)

Implementing a Kalman Filter in Postgres(neon.com)

Beating GPT-5.6 Sol on retrieval with 100x cheaper open models(neon.com)