postgresml.org Open in urlscan Pro
2606:4700:20::681a:e3e Public Scan

Back to summary

Submitted URL:
https://postgresml.com/
Effective URL:
https://postgresml.org/
Submission: On July 17 via automatic, source certstream-suspicious (July 17th 2024, 6:28:25 am UTC) — Scanned from DE

Form analysis
1 forms found in the DOM

POST /account/cookies/consent

<form method="post" action="/account/cookies/consent">
  <button type="submit" class="btn-reset">
    <span class="material-symbols-outlined"> close </span>
  </button>
</form>

Text Content

PostgresML
search

   Product
   Open-source
    * Korvus
    * PGML
    * PgCat
   
   Deployment options
    * filter_drama PostgresML Cloud
    * vpn_key VPC

 * Product
   Solutions
   ml & ai tasks
    * manage_search RAG
    * description NLP
    * model_training Supervised Learning
    * subtitles Embeddings
    * open_with Vector Database
   
   use cases
    * feature_search Search
    * smart_toy Chatbots

 * Solutions
 * Pricing
 * Docs
 * Blog
   Company
    * smart_toy About
    * work Careers
    * alternate_email Contact

 * Company
 * search

 * 5.7K
   GitHub
   Sign In Start Your Project

   arrow_back Back
 * About
 * Careers
 * Contact

   arrow_back Back
 * RAG
 * NLP
 * Supervised Learning
 * Embeddings
 * Vector Database

   arrow_back Back
 * Search
 * Chatbots

   arrow_back Back
 * Tasks
 * Use Cases

   arrow_back Back
 * Korvus
 * PGML
 * PgCat

   arrow_back Back
 * PostgresML Cloud
 * VPC

   arrow_back Back
 * Open-Source
 * Deployment Options

search


Sign up and get $100 in free usage credits arrow_forward

close


INFRA FOR RAG
APPS THAT
WORK IN PROD

Index, filter & rank vectors
Create embeddings
Generate real-time, fact-based outputs

Try it Now Docsarrow_forward
Task:
text-generation expand_more
 * text-generation
 * embeddings
 * summarization
 * translation

Model:
meta-llama/Meta-Llama-3-8B-Instruct expand_more
 * meta-llama/Meta-Llama-3-8B-Instruct
 * meta-llama/Meta-Llama-3-70B-Instruct
 * mistralai/Mixtral-8x7B-Instruct-v0.1
 * mistralai/Mistral-7B-Instruct-v0.2
 * intfloat/e5-small-v2
 * Alibaba-NLP/gte-large-en-v1.5
 * mixedbread-ai/mxbai-embed-large-v1
 * google-t5/t5-base
 * google/pegasus-xsum

99
1
2
3
4
5
6
7
8
9
10
›
⌄
SELECT pgml.transform_stream(
task => '{
"task": "text-generation",
"model": "meta-llama/Meta-Llama-3-8B-Instruct"
}'::JSONB,
input => 'AI is going to',
args => '{
"max_new_tokens": 100
}'::JSONB
);


Run
Loading non-cached models may take a few moments

[{“translation_text”:”Bienvenue à l'avenir!”}]

AI is going to change the world!
TRUSTED BY ENGINEERS AT


"BLEEDING EDGE STUFF IN
A
MATTER OF MINUTES."


STUCK WITH AN AI STACK SO COMPLICATED YOUR APP BARELY RUNS IN PROD?🤔

handyman

MICROSERVICE MAYHEM

You're managing a multitude of microservices - a vector database, embedding
model, LLMs, and frameworks to glue them all together.

cognition

INCREASING INEFFICIENCY

Production outages that won't stop, high-latency UX, ever-increasing dev time,
and data-hungry compute with costly vendors.

mystery

EXCESSIVE EXPOSURE

Your data is sent through multiple systems. You can't be sure if it's secure,
stable, compliant or private.


ARCHITECTURE MAKES OR BREAKS YOUR APP.
POSTGRESML RADICALLY SIMPLIFIES IT



"Over the past year, the data infrastructure stack has seen substantial
stability in core systems and rapid proliferation of supporting tools and
applications" - a16z


4X FASTER

than HuggingFace + Pinecone
for a RAG chatbot




10X FASTER

than OpenAI for embedding
generation




SAVE 42%

On vector database cost
compared to Pinecone


DON'T TAKE OUR WORD FOR IT.

Explore the SDK and test open source models in our hosted database.

PYTHON JAVASCRIPT SQL
Task:
text-generation expand_more
 * text-generation
 * embeddings
 * summarization
 * translation


Model:
meta-llama/Meta-Llama-3-8B-Instruct expand_more
 * meta-llama/Meta-Llama-3-8B-Instruct
 * meta-llama/Meta-Llama-3-70B-Instruct
 * mistralai/Mixtral-8x7B-Instruct-v0.1
 * mistralai/Mistral-7B-Instruct-v0.2
 * intfloat/e5-small-v2
 * Alibaba-NLP/gte-large-en-v1.5
 * mixedbread-ai/mxbai-embed-large-v1
 * google-t5/t5-base
 * google/pegasus-xsum

content_copy
9
1
2
›

pip install pgml
python3 -m asyncio


content_copy
9
1
2
3
4
›

⌄
from pgml import TransformerPipeline
pipe = TransformerPipeline("text-generation",
"meta-llama/Meta-Llama-3-8B-Instruct", {},
"postgres://pg:ml@sql.cloud.postgresml.org:6432/pgml")
async for t in await pipe.transform_stream("AI is going to", {"max_new_tokens":
100}):
print(t)




WHAT MAKES POSTGRESML SO POWERFUL

INDEX, FILTER AND RE-RANK VECTOR EMBEDDINGS

10x faster vector operations
Perform fast KNN and ANN search
Index embeddings with HNSW or IVFFlat 

Learn More arrow_forward

GENERATE EMBEDDINGS

Choose from state-of-the-art models
Built-in data preprocessors for splitting and chunking
Convert text to vector embeddings

Learn More arrow_forward

COLOCATE DATA AND COMPUTE

Embed, serve and store all in one process
Terabytes of data on a single machine
Built-in data privacy & security 

TRAIN, TUNE AND DEPLOY

Regression, classification and clustering
Fine-tune LLMs on your own data 
Monitor model deployments over time 

Learn More arrow_forward

GET THE MOST OF LLMS

Use open-source models (Mistral, LLama, etc.)
Perform a range of NLP tasks
Serve with the same infrastructure 

Learn More arrow_forward

COMPREHENSIVE PLATFORM

Multiple deployment options
Perform several AI & machine learning tasks
Use SQL or SDKs in JS and Python



INDEX, FILTER AND RE-RANK VECTOR EMBEDDINGS

10x faster vector operations
Perform fast KNN and ANN search
Index embeddings with HNSW or IVFFlat 

Learn More arrow_forward

GENERATE EMBEDDINGS

Choose from state-of-the-art models
Built-in data preprocessors for splitting and chunking
Convert text to vector embeddings

Learn More arrow_forward

COLOCATE DATA AND COMPUTE

Embed, serve and store all in one process
Terabytes of data on a single machine
Built-in data privacy & security 

TRAIN, TUNE AND DEPLOY

Regression, classification and clustering
Fine-tune LLMs on your own data 
Monitor model deployments over time 

Learn More arrow_forward

GET THE MOST OF LLMS

Use open-source models (Mistral, LLama, etc.)
Perform a range of NLP tasks
Serve with the same infrastructure 

Learn More arrow_forward

COMPREHENSIVE PLATFORM

Multiple deployment options
Perform several AI & machine learning tasks
Use SQL or SDKs in JS and Python


BETTER PRICE FOR PERFORMANCE

Our pricing is based on the models you use. It’s designed to minimize costs and
operations. You’ll also save because you can replace many existing tools.

View pricing arrow_forward

INTEGRATED LIBRARIES

add remove

PyTourch

TensorFlow

Flax

SciKit-Learn

Hugging Face

Llama

Mistral

XGBoost

LightGBM

CatBoost

MODELS

add remove
Llama
Falcon
OpenAI
Mixtral
Mistral
dbrx-instruct

LANGUAGES

add remove
C++
C#
Elixir
Go
Haskell
Java & Scala
Julia
Lua
Node
Perl
PHP
Python
R
Ruby
Rust
Swift

OSS ECOSYSTEM

add remove

Apache Airflow

DBT

DBeaver

Dagster

Kafka

AWS

Azure

Google Cloud


WORK WITH
WHAT YOU WANT


HEAR FROM OUR COMMUNITY

This is why I’m bullish on @postgresml - devs will always prefer to do things in
data stores they already use in production

James yu



@jamesyu

Great article by PostgresML, running @huggingface models INSIDE @PostgreSQL nice
tidbit on scalability: "Our example data is based on 5 million DVD reviews from
Amazon ... that's more data than fits in a Pinecone Pod at the time of writing"

Paul Copplestone



@kiwicopple

Love the fact that @postgresml can run various algorithms to find the optimum
one for model creation

RebataurAI

@rebataur

You can look at PostgresML. Its based on Postgres, not specifically a vector
database but they've got a pleasantly full featured eco-system for the whole
training process, fetching datasets, huggingface integration, training etc. of
course they also have vector related functions

Dushyant (e/acc)



@DevDminGod

If you want to seamlessly integrate machine learning models into your
#PostgreSQL database, use PostgresML.

Khuyen Tran

@KhuyenTran16

💯 there's also PostgresML if you wanna get a little more full featured -
supports embedding in-database as well as CUBE / pgvector

Martin McFly

@martinmark

Tons of capability in that Postgres extension. It's an important part of the ML
Stack at cloud.tembo.io as well.

Adam Hendel



@adamhendel

A game-changer indeed! By integrating ML and AI directly at the database level
with @postgresml, we're not just streamlining processes but revolutionizing data
handling and insights generation in one fell swoop.

Pranay Suyash



@pranaysuyash

This is why I’m bullish on @postgresml - devs will always prefer to do things in
data stores they already use in production

James yu



@jamesyu

Great article by PostgresML, running @huggingface models INSIDE @PostgreSQL nice
tidbit on scalability: "Our example data is based on 5 million DVD reviews from
Amazon ... that's more data than fits in a Pinecone Pod at the time of writing"

Paul Copplestone



@kiwicopple

Love the fact that @postgresml can run various algorithms to find the optimum
one for model creation

RebataurAI

@rebataur

You can look at PostgresML. Its based on Postgres, not specifically a vector
database but they've got a pleasantly full featured eco-system for the whole
training process, fetching datasets, huggingface integration, training etc. of
course they also have vector related functions

Dushyant (e/acc)



@DevDminGod

If you want to seamlessly integrate machine learning models into your
#PostgreSQL database, use PostgresML.

Khuyen Tran

@KhuyenTran16

💯 there's also PostgresML if you wanna get a little more full featured -
supports embedding in-database as well as CUBE / pgvector

Martin McFly

@martinmark

Tons of capability in that Postgres extension. It's an important part of the ML
Stack at cloud.tembo.io as well.

Adam Hendel



@adamhendel

A game-changer indeed! By integrating ML and AI directly at the database level
with @postgresml, we're not just streamlining processes but revolutionizing data
handling and insights generation in one fell swoop.

Pranay Suyash



@pranaysuyash




GET STARTED
WITH $100 IN
FREE CREDITS

Sign up and and complete your profile to get $100
in free usage credits towards your first AI engine.

Get Started


DOCS

DOCS

Get started with our dev-friendly documentation.

BLOG

BLOG

Get the latest product updates and guides to help build your leading AI
application.

COMMUNITY

COMMUNITY

We’re active on our Discord. Connect with the team and fellow PostgresML
builders.

POSTGRESML

product

Korvus PGML PpCat Learning PostgresML VPC

solutions

RAG NLP Supervised Learning Embedding Vector Database Search

Resources

Documentation
Blog
Pricing

Company

About Careers Privacy Terms of Service Contact

Community

GitHub Discord Formerly Twitter YouTube LinkedIn

PostgresML 2023 Ⓒ All rights reserved.

This site uses cookies for usage analytics to improve our service. By continuing
to browse this site, you agree to this use. See our Privacy Policy

close

postgresml.org Open in urlscan Pro 2606:4700:20::681a:e3e Public Scan

Form analysis 1 forms found in the DOM

POST /account/cookies/consent

Text Content

postgresml.org Open in urlscan Pro
2606:4700:20::681a:e3e Public Scan

Form analysis
1 forms found in the DOM