Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
31.
▲
Generating LLM embeddings with open source models in PostgresML
(postgresml.org)
3 points
levkk
3 years ago
discuss
32.
▲
Scaling PostgresML to 1 Million Requests per Second
(postgresml.org)
3 points
levkk
4 years ago
discuss
33.
▲
Backwards Compatible or Bust: Python Inside Rust Inside Postgres
(postgresml.org)
3 points
levkk
4 years ago
discuss
34.
▲
Postgres Full Text Search Is Awesome
(postgresml.org)
3 points
philliphaydon
4 years ago
discuss
35.
▲
Oxidizing Machine Learning
(postgresml.org)
2 points
levkk
4 years ago
1 comment
36.
▲
Hacker News' problem with open source AI
(postgresml.org)
2 points
sorcercode
2 years ago
discuss
37.
▲
Unified RAG – a practical solution to the pitfalls of typical LLM apps
(postgresml.org)
2 points
levkk
2 years ago
discuss
38.
▲
Zero to RAG – Circumventing the Limits of Modern LLMs
(postgresml.org)
2 points
smarvin2
2 years ago
discuss
39.
▲
Show HN: PostgresML – Run open-source ML/LLM models in a Postgres extension
(postgresml.org)
2 points
montanalow
3 years ago
discuss
40.
▲
PG Stat Sysinfo, a Postgres Extension for Querying System Statistics
(postgresml.org)
2 points
levkk
3 years ago
discuss
41.
▲
PostgresML is 8-40x faster than Python HTTP microservices
(postgresml.org)
2 points
levkk
4 years ago
discuss
42.
▲
Implementing Semantic Search in Postgres in 15 Minutes
(postgresml.org)
1 point
cassandra_who
2 years ago
2 comments
43.
▲
Postgres Learns to RAG: Wikipedia Q&A using Llama 3.1 inside the database
(postgresml.org)
1 point
cassandra_who
2 years ago
1 comment
44.
▲
Personalize embedding results with application data in your database
(postgresml.org)
1 point
montanalow
3 years ago
1 comment
45.
▲
Running Semantic query over YC job posting
(postgresml.org)
1 point
macklinkachorn
2 years ago
discuss
46.
▲
Speed Comparison of the Most Popular Retrieval Systems for RAG
(postgresml.org)
1 point
cassandra_who
2 years ago
discuss
47.
▲
Serverless LLMs are dead; Long live Serverless LLMs
(postgresml.org)
1 point
montanalow
2 years ago
discuss
48.
▲
LLMs are commoditized; data is the differentiator
(postgresml.org)
1 point
montanalow
2 years ago
discuss
49.
▲
Using PostgresML with Django and embedding search
(postgresml.org)
1 point
levkk
2 years ago
discuss
50.
▲
Improving Vector Recall Speed by 5x – IVFFlat –> HNSW
(postgresml.org)
1 point
smarvin2
3 years ago
discuss
51.
▲
How-to improve search results with machine learning
(postgresml.org)
1 point
montanalow
3 years ago
discuss
52.
▲
Support for AWS us-east-1 Region
(postgresml.org)
1 point
levkk
3 years ago
discuss
53.
▲
We Generate JavaScript and Python SDKs from Our Canonical Rust SDK
(postgresml.org)
1 point
lukastyrychtr
3 years ago
discuss
54.
▲
Tuning vector recall while generating query embeddings in the database
(postgresml.org)
1 point
levkk
3 years ago
discuss
55.
▲
Scaling PostgresML to 1M requests per second
(postgresml.org)
1 point
mendigou
4 years ago
discuss
56.
▲
Which Database, That Is the Question
(postgresml.org)
1 point
levkk
4 years ago
discuss
57.
▲
Data Is Living and Relational
(postgresml.org)
1 point
levkk
4 years ago
discuss
58.
▲
Show HN: Postgresql.org suddenly gone to poor dark mode
(postgresql.org)
4 points
sgt
4 years ago
1 comment
59.
▲
Is it time for a newbie-hacker mentor for PostgreSQL.Org?
(commandprompt.com)
1 point
linuxhiker
8 years ago
discuss
60.
▲
Show HN: PostgreSQL index advisor
(github.com/supabase)
417 points
kiwicopple
2 years ago
97 comments
More