PostgresML
@postgresml.bsky.social
Postgres with GPUs for ML/AI apps | Sign up for $100 in free usage credits
🦉 https://postgresml.org
⭐ https://github.com/postgresml
💬 https://discord.com/invite/DmyJP3qJ7U
🦉 https://postgresml.org
⭐ https://github.com/postgresml
💬 https://discord.com/invite/DmyJP3qJ7U
🚀 Implement semantic search in #Postgres in 15 minutes.
🐘 Use pgml and pgvector extensions
🔢 Convert text to embeddings
⚖️ Measure vector similarity
📈 Optimize with HNSW indexes
http://dlvr.it/TFZyW0
🐘 Use pgml and pgvector extensions
🔢 Convert text to embeddings
⚖️ Measure vector similarity
📈 Optimize with HNSW indexes
http://dlvr.it/TFZyW0
Implementing Semantic Search in Postgres in 15 Minutes – PostgresML
How to implement semantic search in Postgres with nothing but SQL.
dlvr.it
October 21, 2024 at 10:06 PM
🚀 Implement semantic search in #Postgres in 15 minutes.
🐘 Use pgml and pgvector extensions
🔢 Convert text to embeddings
⚖️ Measure vector similarity
📈 Optimize with HNSW indexes
http://dlvr.it/TFZyW0
🐘 Use pgml and pgvector extensions
🔢 Convert text to embeddings
⚖️ Measure vector similarity
📈 Optimize with HNSW indexes
http://dlvr.it/TFZyW0
How to build a better search engine for @ycombinator job listings 🧠 💻
Our guide shows you how to:
Powered by @runtrellis & the @postgresml SDK, Korvus
👇 Tutorial: http://dlvr.it/TF9Dx3 💻 💻 💻
Our guide shows you how to:
Powered by @runtrellis & the @postgresml SDK, Korvus
👇 Tutorial: http://dlvr.it/TF9Dx3 💻 💻 💻
Korvus x Trellis: Semantic search over YC jobs – PostgresML
A detailed guide to creating a semantic search system using Trellis AI and the PostgresML SDK, Korvus
dlvr.it
October 9, 2024 at 4:25 PM
How to build a better search engine for @ycombinator job listings 🧠 💻
Our guide shows you how to:
Powered by @runtrellis & the @postgresml SDK, Korvus
👇 Tutorial: http://dlvr.it/TF9Dx3 💻 💻 💻
Our guide shows you how to:
Powered by @runtrellis & the @postgresml SDK, Korvus
👇 Tutorial: http://dlvr.it/TF9Dx3 💻 💻 💻
PostgresML now supports Llama 3.2 🦙
🦉 Free for all Serverless Database users
🐘 Bring models to your data, not vice versa
✨ Smaller models, bigger capabilities
Read on in the blog: [http://dlvr.it/TDlpqs
🦉 Free for all Serverless Database users
🐘 Bring models to your data, not vice versa
✨ Smaller models, bigger capabilities
Read on in the blog: [http://dlvr.it/TDlpqs
Llama 3.2 now available in PostgresML serverless – PostgresML
Bringing smaller, smarter models to your data.
dlvr.it
September 27, 2024 at 6:53 PM
PostgresML now supports Llama 3.2 🦙
🦉 Free for all Serverless Database users
🐘 Bring models to your data, not vice versa
✨ Smaller models, bigger capabilities
Read on in the blog: [http://dlvr.it/TDlpqs
🦉 Free for all Serverless Database users
🐘 Bring models to your data, not vice versa
✨ Smaller models, bigger capabilities
Read on in the blog: [http://dlvr.it/TDlpqs
Ever wondered how RAG works inside a database?
Check out our latest chatbot ➡️
It performs RAG over all of Wikipedia, using open-source models directly in Postgres.
✨Full RAG workflow in one SQL query
🐘In-database processing
🌎100% open-source
Try it: http://dlvr.it/TDgLwF
Check out our latest chatbot ➡️
It performs RAG over all of Wikipedia, using open-source models directly in Postgres.
✨Full RAG workflow in one SQL query
🐘In-database processing
🌎100% open-source
Try it: http://dlvr.it/TDgLwF
PostgresML | Chatbots – PostgresML
The simplest (and fastest) chatbot builder. Use the latest large language and machine learning models right in Postgres
dlvr.it
September 25, 2024 at 3:15 PM
Ever wondered how RAG works inside a database?
Check out our latest chatbot ➡️
It performs RAG over all of Wikipedia, using open-source models directly in Postgres.
✨Full RAG workflow in one SQL query
🐘In-database processing
🌎100% open-source
Try it: http://dlvr.it/TDgLwF
Check out our latest chatbot ➡️
It performs RAG over all of Wikipedia, using open-source models directly in Postgres.
✨Full RAG workflow in one SQL query
🐘In-database processing
🌎100% open-source
Try it: http://dlvr.it/TDgLwF
🚀 postgresml-django
Seamlessly integrate ML/AI with #django ORM
✨ Automatic in-database embeddings
🔍 Vector similarity search
🧠 ML-powered Django projects
Try it now, let us know what you think.
http://dlvr.it/TD4N31
Seamlessly integrate ML/AI with #django ORM
✨ Automatic in-database embeddings
🔍 Vector similarity search
🧠 ML-powered Django projects
Try it now, let us know what you think.
http://dlvr.it/TD4N31
GitHub - postgresml/postgresml-django: postgresml-django is a Python module that integrates PostgresML with Django ORM, enabling automatic in-database embedding of Django models.
postgresml-django is a Python module that integrates PostgresML with Django ORM, enabling automatic in-database embedding of Django models. - postgresml/postgresml-django
dlvr.it
September 10, 2024 at 7:04 PM
🚀 postgresml-django
Seamlessly integrate ML/AI with #django ORM
✨ Automatic in-database embeddings
🔍 Vector similarity search
🧠 ML-powered Django projects
Try it now, let us know what you think.
http://dlvr.it/TD4N31
Seamlessly integrate ML/AI with #django ORM
✨ Automatic in-database embeddings
🔍 Vector similarity search
🧠 ML-powered Django projects
Try it now, let us know what you think.
http://dlvr.it/TD4N31
Check out what @sudowrite pulled off with their RAG stack:
⚡️ Whipped up a prototype in just 3 hours
📈Now crunching 1M+ calls/hour like it's nothing
🐘 Doing all this fancy AI stuff inside their Postgres DB
Get the details here 👉 [http://dlvr.it/TCRY5B
⚡️ Whipped up a prototype in just 3 hours
📈Now crunching 1M+ calls/hour like it's nothing
🐘 Doing all this fancy AI stuff inside their Postgres DB
Get the details here 👉 [http://dlvr.it/TCRY5B
Sudowrite + PostgresML – PostgresML
How the best AI-powered app for fiction writers built their winning RAG stack
dlvr.it
August 27, 2024 at 4:14 PM
Check out what @sudowrite pulled off with their RAG stack:
⚡️ Whipped up a prototype in just 3 hours
📈Now crunching 1M+ calls/hour like it's nothing
🐘 Doing all this fancy AI stuff inside their Postgres DB
Get the details here 👉 [http://dlvr.it/TCRY5B
⚡️ Whipped up a prototype in just 3 hours
📈Now crunching 1M+ calls/hour like it's nothing
🐘 Doing all this fancy AI stuff inside their Postgres DB
Get the details here 👉 [http://dlvr.it/TCRY5B
Too many enterprise AI/ML apps are out of date before they launch, and unmaintainable long term. 🙃
Why?
Complex data pipelines. Isn't there a better way?
⬇️
http://dlvr.it/TBd1Ps
Why?
Complex data pipelines. Isn't there a better way?
⬇️
http://dlvr.it/TBd1Ps
LLMs are Commoditized; Data is the Differentiator – PostgresML
Last year, OpenAI’s GPT-4 launched to great fanfare and was widely hailed as the arrival of AI. Last week, Meta’s Llama 3 surpassed the launch performance of GPT-4, making AI truly available to all with an open-weight model.
dlvr.it
August 7, 2024 at 5:15 PM
Too many enterprise AI/ML apps are out of date before they launch, and unmaintainable long term. 🙃
Why?
Complex data pipelines. Isn't there a better way?
⬇️
http://dlvr.it/TBd1Ps
Why?
Complex data pipelines. Isn't there a better way?
⬇️
http://dlvr.it/TBd1Ps
Want to see how devs are using PostgresML? 🦉
Check out this great rundown from @Krishnaik06 ⬇️
http://dlvr.it/TBX8JF
Check out this great rundown from @Krishnaik06 ⬇️
http://dlvr.it/TBX8JF
Complete MLOPS Platform To Build LLMs Application In PostgresML-Bring ML code to your Database
PostgresML is a complete MLOps platform in a PostgreSQL extension. Build simpler, faster and more scalable models right inside your database.Try PostgreML: h...
dlvr.it
August 5, 2024 at 6:00 PM
Want to see how devs are using PostgresML? 🦉
Check out this great rundown from @Krishnaik06 ⬇️
http://dlvr.it/TBX8JF
Check out this great rundown from @Krishnaik06 ⬇️
http://dlvr.it/TBX8JF
RAG Retrieval Speed Showdown 🏁
We conducted a hands-on speed comparison of the most popular RAG retrieval systems.
👉 Dive into our full blog post to get the details and analysis.
http://dlvr.it/TBJyNK
We conducted a hands-on speed comparison of the most popular RAG retrieval systems.
👉 Dive into our full blog post to get the details and analysis.
http://dlvr.it/TBJyNK
A Speed Comparison of the Most Popular Retrieval Systems for RAG – PostgresML
A hands-on test of the most popular retrieval systems for retrieval augmented generation (RAG).
dlvr.it
July 31, 2024 at 3:27 PM
RAG Retrieval Speed Showdown 🏁
We conducted a hands-on speed comparison of the most popular RAG retrieval systems.
👉 Dive into our full blog post to get the details and analysis.
http://dlvr.it/TBJyNK
We conducted a hands-on speed comparison of the most popular RAG retrieval systems.
👉 Dive into our full blog post to get the details and analysis.
http://dlvr.it/TBJyNK
"Open source AI is important, not because of some pedantic definition by some pseudo-official body like OSI — it’s important because of the power and incentive structures that pervade our society."
Read on in our blog ➡️
http://dlvr.it/TB2B9v
Read on in our blog ➡️
http://dlvr.it/TB2B9v
What’s Hacker News’ problem with open source AI – PostgresML
Open source AI is not the future. It’s here, now. Hacker News has spent the last 24 hours debating if Meta’s Llama models are really “open source” rather than talking about the ramifications of its launch.
dlvr.it
July 25, 2024 at 12:43 AM
"Open source AI is important, not because of some pedantic definition by some pseudo-official body like OSI — it’s important because of the power and incentive structures that pervade our society."
Read on in our blog ➡️
http://dlvr.it/TB2B9v
Read on in our blog ➡️
http://dlvr.it/TB2B9v
Excited to announce meta-llama-3.1 support in PostgresML Cloud! 🦉 + 🦙
Get the details on our blog ➡️
http://dlvr.it/T9zdFY
Get the details on our blog ➡️
http://dlvr.it/T9zdFY
Announcing Support for Meta Llama 3.1 – PostgresML
Today we’re taking the next steps towards open source AI becoming the industry standard. We’re adding support for Llama 3.1 405B, the first frontier-level open source AI model, as well as new and improved Llama 3.1 70B and 8B models.
dlvr.it
July 23, 2024 at 10:31 PM
Excited to announce meta-llama-3.1 support in PostgresML Cloud! 🦉 + 🦙
Get the details on our blog ➡️
http://dlvr.it/T9zdFY
Get the details on our blog ➡️
http://dlvr.it/T9zdFY
RAG in a single query. On Postgres. That's Korvus.
Our new open-source RAG pipeline combines the entire RAG workflow - from embedding to text generation - into a single DB query...one query to rule them all ☝️ No SQL necessary. Python, JS, or Rust.
➡️ http://dlvr.it/T9QlcK
Our new open-source RAG pipeline combines the entire RAG workflow - from embedding to text generation - into a single DB query...one query to rule them all ☝️ No SQL necessary. Python, JS, or Rust.
➡️ http://dlvr.it/T9QlcK
July 10, 2024 at 8:26 PM
RAG in a single query. On Postgres. That's Korvus.
Our new open-source RAG pipeline combines the entire RAG workflow - from embedding to text generation - into a single DB query...one query to rule them all ☝️ No SQL necessary. Python, JS, or Rust.
➡️ http://dlvr.it/T9QlcK
Our new open-source RAG pipeline combines the entire RAG workflow - from embedding to text generation - into a single DB query...one query to rule them all ☝️ No SQL necessary. Python, JS, or Rust.
➡️ http://dlvr.it/T9QlcK
PGML + DBT = ❤️
Are you a data engineer looking to incorporate NLP into your data workflow? Check out this tutorial on getting up and running quickly and easily using DBT and PostgresML.
http://dlvr.it/T96mg4
Are you a data engineer looking to incorporate NLP into your data workflow? Check out this tutorial on getting up and running quickly and easily using DBT and PostgresML.
http://dlvr.it/T96mg4
LLM based pipelines with PostgresML and dbt (data build tool) – PostgresML
Unlock the Power of Large Language Models (LLM) in Data Pipelines with PostgresML and dbt.
dlvr.it
July 3, 2024 at 7:32 PM
PGML + DBT = ❤️
Are you a data engineer looking to incorporate NLP into your data workflow? Check out this tutorial on getting up and running quickly and easily using DBT and PostgresML.
http://dlvr.it/T96mg4
Are you a data engineer looking to incorporate NLP into your data workflow? Check out this tutorial on getting up and running quickly and easily using DBT and PostgresML.
http://dlvr.it/T96mg4
Rather than shipping the entire vector back to an application like a normal vector database, PostgresML includes all the algorithms needed to compute results internally.
Learn more ➡️
http://dlvr.it/T91syY
Learn more ➡️
http://dlvr.it/T91syY
Tuning vector recall while generating query embeddings in the database – PostgresML
How to effectively write and tune queries against large embedding collections with significant speed and quality advantages compared to OpenAI + Pinecone.
dlvr.it
July 1, 2024 at 6:41 PM
Rather than shipping the entire vector back to an application like a normal vector database, PostgresML includes all the algorithms needed to compute results internally.
Learn more ➡️
http://dlvr.it/T91syY
Learn more ➡️
http://dlvr.it/T91syY
How to create a semantic search engine with nothing but SQL ➡️
Implementing Semantic Search in Postgres in 15 Minutes – PostgresML
How to implement semantic search in Postgres with nothing but SQL.
dlvr.it
June 20, 2024 at 4:16 PM
How to create a semantic search engine with nothing but SQL ➡️
Introducing Unified RAG — a practical solution to the pitfalls of typical LLM apps.
http://dlvr.it/T8DnHV
http://dlvr.it/T8DnHV
Unified RAG – PostgresML
Embedding generation, storage and retrieval + search reranking + text generation - all in Postgres.
dlvr.it
June 13, 2024 at 4:01 PM
Introducing Unified RAG — a practical solution to the pitfalls of typical LLM apps.
http://dlvr.it/T8DnHV
http://dlvr.it/T8DnHV
Introducing Unified RAG — a practical solution to the pitfalls of typical LLM apps.
http://dlvr.it/T8DkkX
http://dlvr.it/T8DkkX
Unified RAG – PostgresML
Embedding generation, storage and retrieval + search reranking + text generation - all in Postgres.
dlvr.it
June 13, 2024 at 3:38 PM
Introducing Unified RAG — a practical solution to the pitfalls of typical LLM apps.
http://dlvr.it/T8DkkX
http://dlvr.it/T8DkkX
How to build a Django app -- with the spicy addition 🌶️ of semantic search -- powered by embedding models running inside your PostgreSQL database.
http://dlvr.it/T8B9T6
http://dlvr.it/T8B9T6
Using PostgresML with Django and embedding search – PostgresML
An example application using PostgresML and Django to build embedding based search.
dlvr.it
June 12, 2024 at 3:32 PM
How to build a Django app -- with the spicy addition 🌶️ of semantic search -- powered by embedding models running inside your PostgreSQL database.
http://dlvr.it/T8B9T6
http://dlvr.it/T8B9T6
In-database ML represents a strategic shift to leverage data more effectively. By enabling MLOPs directly within the DB, more orgs can make AI apps that are more efficient, effective and reactive to real-time data changes.
http://dlvr.it/T851Vz
http://dlvr.it/T851Vz
LLMs are Commoditized; Data is the Differentiator – PostgresML
Last year, OpenAI’s GPT-4 launched to great fanfare and was widely hailed as the arrival of AI. Last week, Meta’s Llama 3 surpassed the launch performance of GPT-4, making AI truly available to all with an open-weight model.
dlvr.it
June 10, 2024 at 3:30 PM
In-database ML represents a strategic shift to leverage data more effectively. By enabling MLOPs directly within the DB, more orgs can make AI apps that are more efficient, effective and reactive to real-time data changes.
http://dlvr.it/T851Vz
http://dlvr.it/T851Vz
Moving from AWS ➡️ GCP with minimal downtime
4 lessons learned from our cloud migration
http://dlvr.it/T7z026
4 lessons learned from our cloud migration
http://dlvr.it/T7z026
How we migrated from AWS to GCP with minimal downtime – PostgresML
Lessons learned from moving terabytes of real time data between cloud providers.
dlvr.it
June 7, 2024 at 3:31 PM
Moving from AWS ➡️ GCP with minimal downtime
4 lessons learned from our cloud migration
http://dlvr.it/T7z026
4 lessons learned from our cloud migration
http://dlvr.it/T7z026
Serverless LLMs don't work. Bringing your models in-database is the answer.
postgresml.org/blog/serverl...
postgresml.org/blog/serverl...
Serverless LLMs are dead; Long live Serverless LLMs – PostgresML
Building LLM infrastructure presents a series of tradeoffs that aren't obvious at the outset, even for seasoned teams. This is our journey to high-performance LLMs at scale.
postgresml.org
June 6, 2024 at 8:17 PM
Serverless LLMs don't work. Bringing your models in-database is the answer.
postgresml.org/blog/serverl...
postgresml.org/blog/serverl...