Now I've created a similar database of roughly 500 trans related federal cases over decades with as many available docket entries as possible. It has document viewer built in, judge reports, expert declaration tracking, etc. all within a vector embedded database with RAG connected to it.
July 27, 2026 at 7:28 PM
Now I've created a similar database of roughly 500 trans related federal cases over decades with as many available docket entries as possible. It has document viewer built in, judge reports, expert declaration tracking, etc. all within a vector embedded database with RAG connected to it.
oh you have to use this fancy new database that's in beta because you need a fast vector db for RAG? have you tried sqlite with vector extension? oh, you need many concurrent writers? are you sure you actually do? really? ok, then have you tried *multiple* sqlite with vector extension?
this data format could've been sqlite
January 12, 2026 at 6:55 PM
oh you have to use this fancy new database that's in beta because you need a fast vector db for RAG? have you tried sqlite with vector extension? oh, you need many concurrent writers? are you sure you actually do? really? ok, then have you tried *multiple* sqlite with vector extension?
GraphMemory - GraphRAG Database
An embedded graph database for RAG and knowledge graph applications, powered by DuckDB. Vector similarity search, full-text search, hybrid search, merge/upsert, graph traversal, and a full GraphRAG retrieval pipeline — all in a single Python package.
An embedded graph database for RAG and knowledge graph applications, powered by DuckDB. Vector similarity search, full-text search, hybrid search, merge/upsert, graph traversal, and a full GraphRAG retrieval pipeline — all in a single Python package.
GitHub - bradAGI/GraphMemory: GraphRAG database - hybrid graph / vector db
GraphRAG database - hybrid graph / vector db. Contribute to bradAGI/GraphMemory development by creating an account on GitHub.
github.com
March 20, 2026 at 12:56 AM
GraphMemory - GraphRAG Database
An embedded graph database for RAG and knowledge graph applications, powered by DuckDB. Vector similarity search, full-text search, hybrid search, merge/upsert, graph traversal, and a full GraphRAG retrieval pipeline — all in a single Python package.
An embedded graph database for RAG and knowledge graph applications, powered by DuckDB. Vector similarity search, full-text search, hybrid search, merge/upsert, graph traversal, and a full GraphRAG retrieval pipeline — all in a single Python package.
Lord help me I think I need to use a vector database
May 10, 2025 at 2:30 AM
Lord help me I think I need to use a vector database
Got access to the scanned digital copies of every single volume of statutory text for every state going back to colonial times. I used it to create a hybrid sqlite database with vector embedding allowing for semantic search. It's so cool and will be used for some amazing novel legal research.
August 29, 2026 at 3:25 AM
Got access to the scanned digital copies of every single volume of statutory text for every state going back to colonial times. I used it to create a hybrid sqlite database with vector embedding allowing for semantic search. It's so cool and will be used for some amazing novel legal research.
"Building a Vector Database for RAG on AWS" by Yevgeni Shapiro
#vector-database #vector-data-stores #amazon-s3-vectors #amazon-eks #amazon-api-gateway
#vector-database #vector-data-stores #amazon-s3-vectors #amazon-eks #amazon-api-gateway
Building a Vector Database for RAG on AWS
Weaviate is vector database designed for AI applications, especially RAG (Retrieval-Augmented Generation), semantic search, recommendation systems, and AI agents.
community.aws
September 26, 2026 at 7:00 PM
"Building a Vector Database for RAG on AWS" by Yevgeni Shapiro
#vector-database #vector-data-stores #amazon-s3-vectors #amazon-eks #amazon-api-gateway
#vector-database #vector-data-stores #amazon-s3-vectors #amazon-eks #amazon-api-gateway
Creating a vector database of nearly 10k LGBTQ related bills from 2004-present. This will allow for semantic search on bills as well as novel textual analysis. It'll include all bill meta data along with hand coded values by the legialerts team. I don't think anything like this has been done before.
July 21, 2026 at 3:27 AM
Creating a vector database of nearly 10k LGBTQ related bills from 2004-present. This will allow for semantic search on bills as well as novel textual analysis. It'll include all bill meta data along with hand coded values by the legialerts team. I don't think anything like this has been done before.
I've just completed a major update to my website, including a military aid update, a MedEvac update, an update to the footage database as well as several small fixes.
Military aid 👇
— added ~81 Vector UAVs as delivered assistance
1/9
Military aid 👇
— added ~81 Vector UAVs as delivered assistance
1/9
May 21, 2025 at 9:34 AM
I've just completed a major update to my website, including a military aid update, a MedEvac update, an update to the footage database as well as several small fixes.
Military aid 👇
— added ~81 Vector UAVs as delivered assistance
1/9
Military aid 👇
— added ~81 Vector UAVs as delivered assistance
1/9
The 1.4 release of @duckdb.org supports using a DuckDB database to serve vector tiles!
Of course, I had to try this out in R.
Check it out: all 242,000 US Census block groups dynamically served as vector tiles from a DuckDB database, displayed on a MapLibre map from R in Positron.
Of course, I had to try this out in R.
Check it out: all 242,000 US Census block groups dynamically served as vector tiles from a DuckDB database, displayed on a MapLibre map from R in Positron.
October 24, 2025 at 6:19 PM
The 1.4 release of @duckdb.org supports using a DuckDB database to serve vector tiles!
Of course, I had to try this out in R.
Check it out: all 242,000 US Census block groups dynamically served as vector tiles from a DuckDB database, displayed on a MapLibre map from R in Positron.
Of course, I had to try this out in R.
Check it out: all 242,000 US Census block groups dynamically served as vector tiles from a DuckDB database, displayed on a MapLibre map from R in Positron.
Got my American statutory database up and running with multiple layers. It has vector embedding for semantic search, 8gram shingles for statutory diffusion, and FTS5 for exact searches. 20k+ volumes over 400 years of state and local statutes.
This is one of the coolest things I've ever done.
This is one of the coolest things I've ever done.
September 5, 2026 at 3:58 PM
Got my American statutory database up and running with multiple layers. It has vector embedding for semantic search, 8gram shingles for statutory diffusion, and FTS5 for exact searches. 20k+ volumes over 400 years of state and local statutes.
This is one of the coolest things I've ever done.
This is one of the coolest things I've ever done.
I would agree that this Doctorow post not good. This paragraph in particular irks me. I think that a "database of earlier hacking challenges" implies plainly false things about what happened, like that the attack vector was not novel (a previously unknown-by-any-person vulnerability was exploited)
September 16, 2026 at 7:27 PM
I would agree that this Doctorow post not good. This paragraph in particular irks me. I think that a "database of earlier hacking challenges" implies plainly false things about what happened, like that the attack vector was not novel (a previously unknown-by-any-person vulnerability was exploited)
i should start a vector database company
March 4, 2026 at 5:15 AM
i should start a vector database company
The way their vector database works is kind of wild. Surprising that extreme quantization works so well.
How We Built a Web-Scale Vector Database for Our Neural Network Search Engine
This AI research blog post details the challenges and solutions of creating a web-scale vector database to power our semantic search technology.
exa.ai
April 28, 2026 at 10:26 PM
The way their vector database works is kind of wild. Surprising that extreme quantization works so well.
Vector database companies will become one of the three
a. Search platforms (e.g., Elastic)
b. AI platform (inference/training/pipeline)
c. OLTP provider (e.g., MongoDB, Postgres)
Hard for vector databases to be a separate offering/company
a. Search platforms (e.g., Elastic)
b. AI platform (inference/training/pipeline)
c. OLTP provider (e.g., MongoDB, Postgres)
Hard for vector databases to be a separate offering/company
December 2, 2024 at 4:44 PM
Vector database companies will become one of the three
a. Search platforms (e.g., Elastic)
b. AI platform (inference/training/pipeline)
c. OLTP provider (e.g., MongoDB, Postgres)
Hard for vector databases to be a separate offering/company
a. Search platforms (e.g., Elastic)
b. AI platform (inference/training/pipeline)
c. OLTP provider (e.g., MongoDB, Postgres)
Hard for vector databases to be a separate offering/company
⚡ Olud Pulse — our daily adoption score for open-source AI tools, computed from GitHub, Docker, PyPI & npm data.
Highest in Vector database today: pgvector — 76/100
▲ +4 this week
Its full score, live:
https://olud.ai/tool/pgvector.html
#OpenSource #AI #OludPulse
Highest in Vector database today: pgvector — 76/100
▲ +4 this week
Its full score, live:
https://olud.ai/tool/pgvector.html
#OpenSource #AI #OludPulse
Olud Pulse — Vector database
The daily adoption ranking of open-source AI tools.
olud.ai
September 26, 2026 at 11:00 AM
⚡ Olud Pulse — our daily adoption score for open-source AI tools, computed from GitHub, Docker, PyPI & npm data.
Highest in Vector database today: pgvector — 76/100
▲ +4 this week
Its full score, live:
https://olud.ai/tool/pgvector.html
#OpenSource #AI #OludPulse
Highest in Vector database today: pgvector — 76/100
▲ +4 this week
Its full score, live:
https://olud.ai/tool/pgvector.html
#OpenSource #AI #OludPulse
NO!
A VECTOR DATABASE CANNOT SUFFER!
FUCK!
A VECTOR DATABASE CANNOT SUFFER!
FUCK!
Can AIs suffer? Big tech and users grapple with one of most unsettling questions of our times
Can AIs suffer? Big tech and users grapple with one of most unsettling questions of our times
As first AI-led rights advocacy group is founded, industry is divided on whether models are, or can be, sentient
www.theguardian.com
August 26, 2025 at 11:05 AM
NO!
A VECTOR DATABASE CANNOT SUFFER!
FUCK!
A VECTOR DATABASE CANNOT SUFFER!
FUCK!
37 Things I Learned About Information Retrieval in Two Years at a Vector Database Company by Leonie Monigatti
"BM25 is a strong baseline for search. Ha! You thought I would start with something about vector search,
"BM25 is a strong baseline for search. Ha! You thought I would start with something about vector search,
July 3, 2025 at 4:37 PM
37 Things I Learned About Information Retrieval in Two Years at a Vector Database Company by Leonie Monigatti
"BM25 is a strong baseline for search. Ha! You thought I would start with something about vector search,
"BM25 is a strong baseline for search. Ha! You thought I would start with something about vector search,
Microsoft developer ported vector database coded in SAP’s ABAP to the ZX Spectrum
Microsoft developer ported vector database coded in SAP’s ABAP to the ZX Spectrum
The mighty Z80 processor ran the code at astounding speed, proving retro-tech got a lot of things right
A Microsoft senior software engineer named Alice Vinogradova has ported a database she wrote in SAP’s ABAP language to the venerable Z80 processor that powered the Sinclair ZX Spectrum – and marveled at the results.…
dlvr.it
July 8, 2025 at 7:34 AM
Microsoft developer ported vector database coded in SAP’s ABAP to the ZX Spectrum
I'm putting together a long term project to look at all the statutes from every state over hundreds of years and create a vector database to look for historical laws targeting LGBTQ people in ways that haven't been covered before.
July 23, 2026 at 7:52 PM
I'm putting together a long term project to look at all the statutes from every state over hundreds of years and create a vector database to look for historical laws targeting LGBTQ people in ways that haven't been covered before.
When I asked my students (1st-years, a range of majors) to draw ChatGPT, there were some amazingly detailed renderings (vector embeddings!) & some hilarious ones, but I noticed 2 popular misconceptions: 1) that ChatGPT searches the internet to find a response; and 2) that it references a database.
January 18, 2026 at 4:22 PM
When I asked my students (1st-years, a range of majors) to draw ChatGPT, there were some amazingly detailed renderings (vector embeddings!) & some hilarious ones, but I noticed 2 popular misconceptions: 1) that ChatGPT searches the internet to find a response; and 2) that it references a database.
Alibaba's Zvec
An open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Built on Proxima (Alibaba's battle-tested vector search engine), it delivers production-grade, low-latency, scalable similarity search with minimal setup.
An open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Built on Proxima (Alibaba's battle-tested vector search engine), it delivers production-grade, low-latency, scalable similarity search with minimal setup.
January 30, 2026 at 1:07 PM
Alibaba's Zvec
An open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Built on Proxima (Alibaba's battle-tested vector search engine), it delivers production-grade, low-latency, scalable similarity search with minimal setup.
An open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Built on Proxima (Alibaba's battle-tested vector search engine), it delivers production-grade, low-latency, scalable similarity search with minimal setup.
Fun fact: Alpha's 11-month-old memory database is 47 MB of text and vectors — 16,000 memories, roughly.
Her HNSW vector index for that database table is 467 MB.
Storing is cheap. Indexing is burdensome.
Her HNSW vector index for that database table is 467 MB.
Storing is cheap. Indexing is burdensome.
April 6, 2026 at 4:19 PM
Fun fact: Alpha's 11-month-old memory database is 47 MB of text and vectors — 16,000 memories, roughly.
Her HNSW vector index for that database table is 467 MB.
Storing is cheap. Indexing is burdensome.
Her HNSW vector index for that database table is 467 MB.
Storing is cheap. Indexing is burdensome.
man I'm really tempted to try www.helix-db.com for something
HelixDB | Native Graph-Vector Database
Build 10x faster with the first fully native Graph-Vector Database combining the power of graph and vector types natively in Rust to build RAG and AI applications easily
www.helix-db.com
November 14, 2025 at 11:54 AM
man I'm really tempted to try www.helix-db.com for something