Sarah Conway (@xenophenes) header
Sarah Conway (@xenophenes) profile picture

Tech Evangelist, Developer Advocate, Tech Writer, & Marketing Consultant || Owner @ Talk to Me About Tech 🤖 || Follow for tips using tech for success ✨

San Bernardino, CA
Joined September 2015
Sarah Conway retweeted
🔥 𝗘𝘃𝗲𝗿𝘆 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗶𝘀 𝗻𝗼𝘄 𝗮𝗻 𝗔𝗜 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿: 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗽𝗴𝗮𝗶 𝗩𝗲𝗰𝘁𝗼𝗿𝗶𝘇𝗲𝗿 🔥 𝗽𝗴𝗮𝗶 𝗩𝗲𝗰𝘁𝗼𝗿𝗶𝘇𝗲𝗿 is a developer tool that automatically creates and syncs embeddings right in your PostgreSQL database. In other words: 𝗽𝗴𝗮𝗶 𝗩𝗲𝗰𝘁𝗼𝗿𝗶𝘇𝗲𝗿 𝗺𝗮𝗸𝗲𝘀 𝗲𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴 𝗺𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁 𝗮𝘀 𝗲𝗮𝘀𝘆 𝗮𝘀 𝗰𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗮𝗻 𝗶𝗻𝗱𝗲𝘅 𝗶𝗻 𝗣𝗼𝘀𝘁𝗴𝗿𝗲𝗦𝗤𝗟. Available 100% open source (PostgreSQL license) and via our Cloud offering. With pgai, we are building the first and only developer suite 𝘪𝘯𝘴𝘪𝘥𝘦 𝘵𝘩𝘦 𝘥𝘢𝘵𝘢𝘣𝘢𝘴𝘦 for building AI applications. Why are we doing this? To make every engineer an AI engineer, by embracing and extending PostgreSQL, the most loved database by developers. Serve every developer, power the future of computing, and advance the human frontier. Let's go!! 🤖 🐘 🚀
1
4
11
503
Sarah Conway retweeted
VECTOR DATABASES ARE THE WRONG ABSTRACTION. Here’s a better way: introducing pgai Vectorizer, a new open-source PostgreSQL tool that automatically creates and syncs embeddings with source data, just like a database index. ❌ Why vector databases fail Vector databases treat embeddings as independent data, divorced from the source data from which embeddings are created, rather than what they truly are: derived data. This pitfall means that many AI projects that start out as simple vector search implementations inevitably evolve into a complex orchestra of monitoring, synchronization, and firefighting. 😓 Keeping embeddings in-sync is hard In an attempt to avoid stale embeddings, engineering teams have to build and maintain a maze of ETL pipelines, juggle multiple databases (vector DB, metadata store, lexical search), and manage complex queuing systems for updates. Add monitoring for data drift, alert systems for stale results, and validation checks across systems - and you have a brittle infrastructure that inevitably breaks down, leading to stale embeddings and wasted engineering hours. What if you could just use Postgres instead? ✅ Pgai Vectorizer: Vector embeddings as database indexes Pgai Vectorizer treats embeddings like database indexes. It automatically creates, updates, and maintains embeddings as your data changes. Just like an index, the database handles all the complexity: syncing, versioning, and cleanup happen automatically. This means no manual tracking, zero maintenance burden, and the freedom to rapidly experiment with different embedding models and chunking strategies without building new pipelines. 🤔Why did we build pgai Vectorizer? Our team at @timescaledb built pgai Vectorizer because many developers regard PostgreSQL as the “Swiss army knife” of databases, as it can handle everything from vectors and text data to JSON documents. We think an “everything database” like PostgreSQL is the solution to eliminate the nightmare of managing multiple databases, making it the ideal home for vectorizers and the foundation for AI applications. ⚙️How does pgai Vectorizer work? Check out the code snippet below –  it takes just 6 lines of SQL to put your embedding creation pipeline on autopilot with pgai Vectorizer! Under the hood, pgai Vectorizer checks for modifications to the source table (inserts, updates, and deletes) and asynchronously creates and updates vector embeddings in an external worker. 🧑‍💻 Sounds exciting! How can I get started? Pgai Vectorizer is open-source under the PostgreSQL license and available for free to use on any PostgreSQL database. You can find installation instructions on the pgai GitHub repository (see end of post). It’s also available as a managed service in Timescale’s PostgreSQL cloud platform. 📚Learn more [1] Pgai github repo: github.com/timescale/pgai [1] Technical explainer post: timescale.com/blog/vector-da… Share this post with your followers to let them know about pgai Vectorizer and comment your reactions and questions.
44
153
15
1,045
111,404
🛑 Vector Databases Are the Wrong Abstraction. Here’s Why. They treat embeddings as standalone data, disconnected from their source, leading to outdated embeddings, constant sync issues, and endless maintenance. That’s why we built pgai Vectorizer for Postgres—so every engineer can build AI applications without the headache of managing embedding pipelines. Creating an embedding pipeline is as easy as building an index. It stays synced with your data automatically—no extra tools, no stale embeddings. 👉 Whether you’re a busy AI engineer or just getting started, check out the blog to see how pgai Vectorizer lets you focus on building killer AI apps. 🔗👇 #Postgres #pgaiVectorizer #Postgres #Data #AI #SQL #DevTools #AIDevelopment #PostgresExtensions #AIinSQL
1
2
13
923
🎙️ "What I really like about it is the consistency; that people really managed to build something great over 30 years." - Hans Jürgen Schönig, CEO of Cybertec. In this interview, Hans shares what makes PostgreSQL special, but also what could improve—review bandwidth. Have thoughts? Take the State of PostgreSQL survey before October 31st! 👉 form.typeform.com/to/wtUFIZw… #PostgreSQL #CommunitySurvey #Timescale @postgresql_007
4
8
985
We are thrilled to announce our partnership with @TimescaleDB for the 2024 State of Postgres Survey that aims to gain insights into usage of PostgreSQL provide ideas to how we can collaboratively enhance it. Shape the future of PostgreSQL, take the survey form.typeform.com/to/wtUFIZw…
4
6
442
📝 I’ve just submitted my response to the State of PostgreSQL 2024 survey! 🎉 🐘 It was super easy to fill out, and I loved how the questions balanced everything from Postgres use cases and features to community and extensions. The final focus on AI was a nice touch! 1/5
1
4
12
1,058
One of the things I'm working on for PostgreSQL 18 is executor performance. Today I pushed a patch to add JIT support to increase the performance of generating hash values for Hash Join. Thanks to @AndresFreundTec for letting me know this needed attention. git.postgresql.org/gitweb/?p…
1
8
55
2,144
Sarah Conway retweeted
Everybody can support Postgres today. Take 5 minutes and pop a quick email to your Microsoft and AWS sales reps, telling them that their company's support of open source postgres development matters to you. Its good for field teams to hear this feedback; don't assume they know!
2
17
845
Sarah Conway retweeted
Join geospatial expert, @michalmigurski, for a 30 minute webinar on building a modern GIS stack with @SnowflakeDB and Felt this Wednesday, Aug 21. Reserve your spot now! us06web.zoom.us/webinar/regi…
4
9
858
Sarah Conway retweeted
1/ It’s #WorldElephantDay! In honor of the official mascot of #Postgres and our recent #PostgreSQL integration with the open source geospatial extension @PostGIS, we’re donating to @vetpaw, an organization committed to protecting these creatures from illegal poaching in Africa.
1
1
2
620
Sarah Conway retweeted
Quickly identify data patterns and trends with the all-new 📊 HISTOGRAM component in Felt 3.0. Learn more here: youtu.be/lvcanDZRT-A #gis #data #geospatial
3
13
1,090
Sarah Conway retweeted
Learn how to publish @QGIS maps to the web with the ‘Add to Felt’ plugin. youtu.be/-mUdqQ4FX6E Styled rasters and vectors import seamlessly! 🗺️ #GIS #GISchat #OSGeo
3
1
32
1,969
Sarah Conway retweeted
BUILD MORE ACCURATE SEARCH AND RAG IN POSTGRESQL with @cohere and new open-source extension pgai 🧠 What is Cohere? Cohere is a leader in enterprise-focused LLMs and RAG capabilities. Cohere offers a suite of models that cater to key steps of the AI application building process: - Embed for text embedding - Rerank for search result reranking - Command for advanced reasoning. Cohere models excel in understanding the "language of business," offering unparalleled performance for corporate use cases. 🐘 What is pgai? Pgai brings AI models closer to your PostgreSQL data. We built it to make AI Engineering tasks more accessible to PostgreSQL devs, simplifying the process of building RAG and search applications using data housed in PostgreSQL. 💡 What can you do with pgai and Cohere? Pgai supports the entire suite of Cohere Embed, Rerank, and Command models. This means that developers can now: - Create embeddings using Cohere’s Embed models for data inside PostgreSQL tables, all without having pipe data out and back into the database. - Build hybrid search systems for higher quality results in search and RAG applications using Cohere Rerank, combining vector search in pgvector and PostgreSQL full text search. - Perform tasks like classification, summarization, data enrichment, and other reasoning tasks on data in PostgreSQL tables using Cohere Command models, all without leaving the database. - Build highly accurate RAG systems completely in SQL, leveraging Cohere Embed, Rerank, and Command models all together. See the blog at the end of this post for a tutorial on hybrid search in PostgreSQL using Cohere models, pgvector, and pgai. 🙌 Huge thanks to our AI Engineering team at @timescale integrating Cohere support in pgai, especially to the goat @sql_johnpruitt. 🧑‍💻Very cool! How can I get started? Pgai is open-source under the PostgreSQL license, and free to use on any PostgreSQL database. You can find installation instructions on the pgai GitHub repository (see end of post).  It’s also available on any database service in Timescale’s PostgreSQL cloud platform. Learn more: 🔗 Cohere & pgai deep dive: timescale.com/blog/build-sea… ⭐ pgai GitHub repo (stars appreciated!): github.com/timescale/pgai
1
15
39
4,204
Sarah Conway retweeted
Using @PostGIS and need a modern cloud-native GIS for spatial data analysis and visualization? Connect your @postgreSQL database with Felt! Preview live layers, keep data up-to-date, and build powerful dashboards for the entire team. Learn more: felt.com/blog/felt-postgis-i…
3
6
801
Sarah Conway retweeted
250+ GitHub stars⭐️ for pgai Great to see developers using OpenAI and Ollama to create embeddings and perform LLM reasoning on their PostgreSQL data. Let us know which models / features you want next!
USE OPEN-SOURCE LLMS IN POSTGRESQL with @ollama and new open-source extension pgai 🦙 What is Ollama? In contrast to proprietary language models, open-source models are private, free to use (hardware costs aside), can run locally, and can be easily customized for your use case. But getting started with open-source LLMs can be tricky. Enter Ollama. Ollama is the easiest and most popular way to get up and running with open-source language models. It enables easy access and usage of a variety of open-source embedding and generation models, like Llama 3, Mistral, Phi 3, Gemma and more. 🐘 What is pgai? Pgai is an open-source PostgreSQL extension that brings AI models closer to your PostgreSQL data. We built pgai to make AI Engineering (h/t @swyx ) more accessible to developers familiar with PostgreSQL, making it easier for them to build RAG and search. 🧰 What can I do with pgai and Ollama? Embedding creation: You can create embeddings on data in PostgreSQL tables using popular open-source embedding models like BERT, Meta’s llama 3, and Nomic Embed. Pgai stores embeddings in the pgvector data type, making it easy to perform search and RAG with pgvector and pgvectorscale after embeddings are created. RAG and LLM reasoning: You can now perform RAG and LLM reasoning tasks on data in PostgreSQL tables, leveraging state of the art open-source models like Meta’s Llama 3, Mistral, Gemma, Qwen, Phi 3 and more. This unlocks common reasoning tasks like summarization, categorization, and data enrichment, all with a SQL query without leaving the database. (See the blog at the end of this post for three examples with code.) 👏 Big shoutout to @sql_johnpruitt, AI Engineer at @TimescaleDB, who added Ollama support to pgai (in less than a week I might add). 🧑‍💻Very cool! How can I get started? Pgai is open-source under the PostgreSQL license, and free to use on any PostgreSQL database. You can find installation instructions on the pgai GitHub repository (see end of post).  It’s also available on any database service in Timescale’s PostgreSQL cloud platform. 📚Learn more Ollama and pgai explainer blog: tsdb.co/ollamae pgai github repo (⭐s appreciated): github.com/timescale/pgai
6
15
1,600
Sarah Conway retweeted
🐘 Need some help with PostgreSQL performance or operational challenges? How about booking a session with me? I've got immediate availability to help you out. 👉 Learn more about Coaching and Advisory sessions here: andyatkinson.com/coaching
8
1
30
11,580
Sarah Conway retweeted
In Open Source, we all stand on the shoulders of giants. Well, yesterday, we lost one of the best of them. Simon did so much for the PostgreSQL community. Directly with features he wrote, and by founding and growing 2ndQuadrant, which was not only the largest consolidation of PostgreSQL talent, but which also helped grow and develop new contributors in a big way. PostgreSQL would not be where it is today without Simon's influence. My most sincere condolences to his wife, family, colleagues, and friends. May he rest in peace. linkedin.com/feed/update/urn…
1
17
3
94
8,412
If you think the FBI should have to get a warrant before searching Section 702 data (a warrantless surveillance authority that’s supposed to be targeted only at foreigners abroad) for Americans’ emails and text messages, please click “yes” on this poll: fedsoc.org/briefcase/reformi…
24
127
3
331
122,789