# pgvector

Published articles for pgvector.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Three principles for building a vector platform at Thumbtack

DevFeed: [Three principles for building a vector platform at Thumbtack](<https://devfeed.tech/articles/three-principles-for-building-a-vector-platform-at-thumbtack-24729.md>)

Original publisher: [Read original article](<https://medium.com/thumbtack-engineering/three-principles-for-building-a-vector-platform-at-thumbtack-bca5a33dca16?source=rss----1199c607a13f---4>)

Author: John Zhu

Published: 2026-09-10T15:45:00Z

Content type: article

Language: en

Sources: [Thumbtack Engineering - Medium](<https://devfeed.tech/sources/thumbtack-engineering-medium.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Database](<https://devfeed.tech/topics/database.md>), [data](<https://devfeed.tech/topics/data.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [API](<https://devfeed.tech/topics/api.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [data](<https://devfeed.tech/tags/data.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [etl](<https://devfeed.tech/tags/etl.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml-platform](<https://devfeed.tech/tags/ml-platform.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article explains how Thumbtack built a vector platform that lets ML engineers deploy production vector search without managing database access, custom ETL, or query services. It describes three guiding principles: reuse existing infrastructure, treat embeddings as data, and reduce adoption costs for future teams.

### Source excerpt

Reusing what we already had, treating embeddings as data, and lowering the next team's cost Today, an ML engineer at Thumbtack can stand up production vector search without negotiating database access, building a custom ETL, or writing a query service. The team brings their choice of embedding model, the data, and the query; the platform handles what connects them. It took several iterations to get to this point. In this post we'll walk through how we got there and the three principles that shaped what we built. A vector database stores high-dimensional numeric arrays (embeddings) and serves nearest-neighbor queries against them. It's how an ML system asks "what's most similar to this?" instead of "what matches this exact key?" The shift from exact lookup to semantic retrieval is what makes vectors useful: a search can return results that mean the same thing, not just results that spell the same. At Thumbtack, embeddings sit between the models that produce them and the services that consume them: language models for text, multimodal models for images, retrieval models for ranking. The platform we describe here is where those embeddings live and how teams reach for them when they need to. Three principles shaped what we built. Reuse what we have: extend the infrastructure we already run rather than stand up a new system. Treat embeddings as data: flow them through the same pipelines that move every other dataset at the company. Lower the next team's cost: make the platform easier to adopt than to work around. Each principle shaped one layer of the system, and together they took vector search from a one-off project to a platform that any team can build on. Architecture at a glance The platform has four moving parts: where embeddings come from, how they reach the database, where they live, and how consumers query them. Each is a layer, and together they form a pipeline that produces vectors and serves similarity searches as a typed API call. The diagram below traces a

## Deploying a RAG Chatbot with Shared State and Storage Across Replicas

DevFeed: [Deploying a RAG Chatbot with Shared State and Storage Across Replicas](<https://devfeed.tech/articles/static-vs-dynamic-vs-continuous-batching-in-llms-clearly-explained-18242.md>)

Original publisher: [Read original article](<https://blog.dailydoseofds.com/p/static-vs-dynamic-vs-continuous-batching>)

Author: Avi Chawla

Published: 2026-09-01T21:11:23Z

Content type: tutorial

Language: en

Sources: [Daily Dose of Data Science](<https://devfeed.tech/sources/daily-dose-of-data-science.md>)

Topics: [Retrieval-Augmented Generation](<https://devfeed.tech/topics/retrieval-augmented-generation.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [Terraform](<https://devfeed.tech/topics/terraform.md>), [FastAPI](<https://devfeed.tech/topics/fastapi.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [fastapi](<https://devfeed.tech/tags/fastapi.md>), [github](<https://devfeed.tech/tags/github.md>), [persistence](<https://devfeed.tech/tags/persistence.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [terraform](<https://devfeed.tech/tags/terraform.md>)

### AI overview

The article explains why a RAG chatbot that works locally can lose vector indexes, conversation history, and documents when deployed across multiple replicas. It recommends shared persistence for embeddings, checkpointed conversation state, and shared object storage, with examples using Postgres, pgvector, LangGraph, and object storage.

### Source excerpt

+ a popular LLM interview question.

## From Project Description to Funding Opportunity

DevFeed: [From Project Description to Funding Opportunity](<https://devfeed.tech/articles/from-project-description-to-funding-opportunity-22853.md>)

Original publisher: [Read original article](<https://medium.com/google-developer-experts/from-project-description-to-funding-opportunity-16c2b3b8ffb5?source=rss----a67bd6fa7d58---4>)

Author: Gabriel Preda

Published: 2026-08-31T05:03:07Z

Content type: tutorial

Language: en

Sources: [Google Developer Experts - Medium](<https://devfeed.tech/sources/google-developer-experts-medium.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Google AI](<https://devfeed.tech/topics/google-ai.md>), [Streamlit](<https://devfeed.tech/topics/streamlit.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [postgresql clusters](<https://devfeed.tech/topics/postgresql-clusters.md>)

Tags: [adk](<https://devfeed.tech/tags/adk.md>), [ai](<https://devfeed.tech/tags/ai.md>), [building](<https://devfeed.tech/tags/building.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [developer](<https://devfeed.tech/tags/developer.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [google](<https://devfeed.tech/tags/google.md>), [google-adk](<https://devfeed.tech/tags/google-adk.md>), [google-cloud-sql](<https://devfeed.tech/tags/google-cloud-sql.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [search](<https://devfeed.tech/tags/search.md>), [streamlit](<https://devfeed.tech/tags/streamlit.md>)

### AI overview

This article describes GrantMatch AI, a Streamlit application that matches project descriptions with potentially relevant grant and funding opportunities. It explains how hybrid keyword and embedding search, Gemini, ADK, Cloud SQL, PostgreSQL, pgvector, and Streamlit are used to connect related concepts despite different wording.

### Source excerpt

Building GrantMatch AI with hybrid keyword and embedding search using Gemini, ADK, Cloud SQL, PostgreSQL, pgvector, and Streamlit Continue reading on Google Developer Experts "

## Hybrid Search Patterns with Postgres and pgvector

DevFeed: [Hybrid Search Patterns with Postgres and pgvector](<https://devfeed.tech/articles/hybrid-search-patterns-with-postgres-and-pgvector-14480.md>)

Original publisher: [Read original article](<https://www.crunchydata.com/blog/hybrid-vector-search>)

Author: Christopher Winslett

Published: 2026-07-30T15:00:00Z

Content type: article

Language: en

Sources: [CrunchyData Blog](<https://devfeed.tech/sources/crunchydata-blog.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Query (disambiguation)](<https://devfeed.tech/topics/query.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [caching](<https://devfeed.tech/tags/caching.md>), [hybrid-search](<https://devfeed.tech/tags/hybrid-search.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vectors-llms](<https://devfeed.tech/tags/vectors-llms.md>)

### AI overview

This article explains why filtered vector search in Postgres creates a tradeoff between recall and performance. It discusses how ANN indexes such as HNSW and IVFFlat differ from B-tree indexes, and introduces approaches including pgvector iterative scans, partial indexes, oversampling, and caching.

### Source excerpt

Filtered vector search in Postgres forces a tradeoff between recall and speed because ANN indexes and WHERE clauses do not intersect like B-trees. Read about pgvector iterative scans, partial HNSW indexes, oversampling with pg_stats, caching, and more.

## How PostgreSQL and pgvector Support Vector Search and RAG

DevFeed: [How PostgreSQL and pgvector Support Vector Search and RAG](<https://devfeed.tech/articles/you-probably-don-t-need-a-vector-database-17865.md>)

Original publisher: [Read original article](<https://encore.dev/blog/you-probably-dont-need-a-vector-database>)

Author: Ivan Cernja

Published: 2026-03-09T00:00:00Z

Content type: tutorial

Language: en

Sources: [Encore Updates](<https://devfeed.tech/sources/encore-updates.md>)

Topics: [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Database](<https://devfeed.tech/topics/database.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [rag](<https://devfeed.tech/tags/rag.md>), [search](<https://devfeed.tech/tags/search.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This tutorial explains embeddings, vector similarity search, and retrieval-augmented generation, then shows how to implement them with PostgreSQL and the pgvector extension instead of a separate vector database. It describes how embeddings represent semantic meaning and how vector search can find related content beyond exact keyword matches.

### Source excerpt

What vectors, similarity search, and RAG actually do under the hood, and why PostgreSQL handles most of it.

## Agent Development with CockroachDB using the LangChain Framework

DevFeed: [Agent Development with CockroachDB using the LangChain Framework](<https://devfeed.tech/articles/agent-development-with-cockroachdb-using-the-langchain-framework-23731.md>)

Original publisher: [Read original article](<https://cockroachlabs.com/blog/agent-development-cockroachdb-langchain>)

Author: David Bressler

Published: 2026-02-26T00:00:00Z

Content type: release

Language: en

Sources: [Cockroach Labs](<https://devfeed.tech/sources/cockroach-labs.md>)

Topics: [CockroachDB](<https://devfeed.tech/topics/cockroachdb.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [agentic AI applications](<https://devfeed.tech/topics/agentic-ai-applications.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Python](<https://devfeed.tech/topics/python.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [Retrieval-Augmented Generation](<https://devfeed.tech/topics/retrieval-augmented-generation.md>)

Tags: [agentic-ai-applications](<https://devfeed.tech/tags/agentic-ai-applications.md>), [cockroachdb](<https://devfeed.tech/tags/cockroachdb.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [python](<https://devfeed.tech/tags/python.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>)

### AI overview

CockroachDB describes its integration with LangChain for building production-oriented agentic AI applications in Python. The integration supports CockroachDB as a vector source and helps connect language models with CockroachDB data for retrieval and other multi-step application workflows.

### Source excerpt

Recently we launched an integration with LangChain, the most popular orchestration framework for developing applications with large language models, to simplify development of production-ready agentic AI applications with CockroachDB. This integration provides out-of-the-box support for CockroachDB as a vector source for any LangChain user using LangChain Python.

## Building AI Search on Heroku

DevFeed: [Building AI Search on Heroku](<https://devfeed.tech/articles/building-ai-search-on-heroku-26382.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/building-ai-search-on-heroku/>)

Author: Anush DSouza

Published: 2026-01-29T17:50:08Z

Content type: tutorial

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku](<https://devfeed.tech/topics/heroku.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Retrieval-Augmented Generation](<https://devfeed.tech/topics/retrieval-augmented-generation.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-search](<https://devfeed.tech/tags/ai-search.md>), [building](<https://devfeed.tech/tags/building.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-ai](<https://devfeed.tech/tags/heroku-ai.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [news](<https://devfeed.tech/tags/news.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [search](<https://devfeed.tech/tags/search.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article presents a Heroku reference architecture for production-grade enterprise AI search using two-stage retrieval. It combines vector search with semantic reranking so documents are scored for whether they answer the query, then uses Claude to generate an answer.

### Source excerpt

If you've built a RAG (Retrieval Augmented Generation) system, you've probably hit this wall: your vector search returns 20 documents that are semantically similar to the query, but half of them don't actually answer it. A user asks "how do I handle authentication errors?" and gets back documentation about authentication, errors, and error handling in [...] The post Building AI Search on Heroku appeared first on Heroku.

## Heroku AI: Claude 4 Sonnet is now available

DevFeed: [Heroku AI: Claude 4 Sonnet is now available](<https://devfeed.tech/articles/heroku-ai-claude-4-sonnet-is-now-available-26413.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/heroku-ai-claude-4-sonnet-now-available/>)

Author: Anush DSouza

Published: 2025-05-29T14:28:22Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku](<https://devfeed.tech/topics/heroku.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Python](<https://devfeed.tech/topics/python.md>), [Ruby](<https://devfeed.tech/topics/ruby.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-machine-learning](<https://devfeed.tech/tags/ai-machine-learning.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cli](<https://devfeed.tech/tags/cli.md>), [environment-variables](<https://devfeed.tech/tags/environment-variables.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-ai](<https://devfeed.tech/tags/heroku-ai.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [llm](<https://devfeed.tech/tags/llm.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [news](<https://devfeed.tech/tags/news.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [ruby](<https://devfeed.tech/tags/ruby.md>), [services](<https://devfeed.tech/tags/services.md>)

### AI overview

Heroku announces that Anthropic's Claude 4 Sonnet is available through Heroku Managed Inference and Agents. The article describes support for coding, advanced reasoning, AI agents, MCP integrations, and API access from Heroku applications.

### Source excerpt

Anthropic's Claude 4 Sonnet, part of the next generation of Claude models, is now available on Heroku Managed Inference and Agents. This gives developers immediate access to a model designed for coding, advanced reasoning, and the support of capable AI agents. Heroku Managed Inference and Agents expands your AI choices, offering the freedom to build [...] The post Heroku AI: Claude 4 Sonnet is now available appeared first on Heroku.

## Jupyter Notebooks on Heroku with Persistent Storage

DevFeed: [Jupyter Notebooks on Heroku with Persistent Storage](<https://devfeed.tech/articles/jupyter-notebooks-on-heroku-with-persistent-storage-26461.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/jupyter-notebooks-heroku-persistent-storage/>)

Author: Anush DSouza

Published: 2025-04-02T06:54:00Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku](<https://devfeed.tech/topics/heroku.md>), [jupyter](<https://devfeed.tech/topics/jupyter.md>), [Disk image](<https://devfeed.tech/topics/disk-image.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [Security](<https://devfeed.tech/topics/security.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-infrastructure](<https://devfeed.tech/tags/cloud-infrastructure.md>), [data-analytics](<https://devfeed.tech/tags/data-analytics.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [jupyter](<https://devfeed.tech/tags/jupyter.md>), [jupyter-notebooks](<https://devfeed.tech/tags/jupyter-notebooks.md>), [managed-inference-and-agents](<https://devfeed.tech/tags/managed-inference-and-agents.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [python](<https://devfeed.tech/tags/python.md>), [rag](<https://devfeed.tech/tags/rag.md>), [security](<https://devfeed.tech/tags/security.md>), [storage](<https://devfeed.tech/tags/storage.md>)

### AI overview

Heroku introduces Heroku-Jupyter, an open-source solution for running Jupyter Notebooks with persistent PostgreSQL storage, deployment support, password protection, and customizable environments. The article also describes using Heroku-Jupyter with pgvector and Heroku Managed Inference and Agents for retrieval-augmented generation applications.

### Source excerpt

We're excited to introduce Heroku-Jupyter, an open-source, production-ready solution for running Jupyter Notebooks on Heroku with persistent storage, seamless deployment, and built-in security. Whether you're a data scientist, educator, or developer, you can now spin up a cloud-based Jupyter environment in minutes. Why Jupyter on Heroku? Jupyter Notebooks provide an interactive computing environment ideal for [...] The post Jupyter Notebooks on Heroku with Persistent Storage appeared first on Heroku.

## Neon is coming to Azure

DevFeed: [Neon is coming to Azure](<https://devfeed.tech/articles/neon-is-coming-to-azure-5649.md>)

Original publisher: [Read original article](<https://neon.com/blog/neon-is-coming-to-azure>)

Author: Nikita Shamgunov

Published: 2024-08-07T13:09:53Z

Content type: news

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Azure](<https://devfeed.tech/topics/azure.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Database](<https://devfeed.tech/topics/database.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Security, Privacy and Abuse Prevention](<https://devfeed.tech/topics/security-privacy-and-abuse-prevention.md>)

Tags: [azure](<https://devfeed.tech/tags/azure.md>), [azure-marketplace](<https://devfeed.tech/tags/azure-marketplace.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [company](<https://devfeed.tech/tags/company.md>), [data-privacy](<https://devfeed.tech/tags/data-privacy.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [multi-cloud](<https://devfeed.tech/tags/multi-cloud.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [rag](<https://devfeed.tech/tags/rag.md>), [serverless](<https://devfeed.tech/tags/serverless.md>)

### AI overview

Neon announces its expansion to Azure, supported by a $25 million strategic investment led by Microsoft's M12 venture fund. The article describes Neon's serverless Postgres platform, its multi-cloud availability, integration with Azure, and use with pgvector for vector storage and RAG workloads. It also explains Azure access through the Neon Console or Azure Marketplace.

### Source excerpt

It's official: Neon is coming to Azure. This expansion is backed by a $25M strategic investment led by M12, Microsoft's Venture Fund. Multi-cloud has always been a part of our vision at Neon. We want to help developers ship faster with Postgres on Neon, regardless of which cloud...

## Building a RAG application with Llama 3.1 and pgvector

DevFeed: [Building a RAG application with Llama 3.1 and pgvector](<https://devfeed.tech/articles/building-a-rag-application-with-llama-3-1-and-pgvector-5093.md>)

Original publisher: [Read original article](<https://neon.com/blog/building-a-rag-application-with-llama-3-1-and-pgvector>)

Author: Andrew Tate

Published: 2024-07-30T16:58:41Z

Content type: tutorial

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [llama](<https://devfeed.tech/topics/llama.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [Meta](<https://devfeed.tech/topics/meta.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llama](<https://devfeed.tech/tags/llama.md>), [meta](<https://devfeed.tech/tags/meta.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openai](<https://devfeed.tech/tags/openai.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [product](<https://devfeed.tech/tags/product.md>), [rag](<https://devfeed.tech/tags/rag.md>)

### AI overview

A tutorial on building a Retrieval-Augmented Generation application with Meta's Llama 3.1 and pgvector. It explains how retrieval and embeddings let an LLM use relevant, up-to-date information from an external knowledge base.

### Source excerpt

The AI wars have begun. Not the one where the machines enslave us and use our body heat to power their compute-that's at least 18 months off. 🙂 No, this AI war is between the tech giants and between closed, proprietary models and open source. In one corner, we have OpenAI, suppo...

## Introducing New Heroku Postgres Essential Plans Built On Amazon Aurora

DevFeed: [Introducing New Heroku Postgres Essential Plans Built On Amazon Aurora](<https://devfeed.tech/articles/introducing-new-heroku-postgres-essential-plans-built-on-amazon-aurora-26440.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/heroku-postgres-essential-launch/>)

Author: Jonathan Brown

Published: 2024-05-21T22:05:00Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku](<https://devfeed.tech/topics/heroku.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [Amazon Aurora](<https://devfeed.tech/topics/amazon-aurora.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [migration](<https://devfeed.tech/topics/migration.md>), [Scalability](<https://devfeed.tech/topics/scalability.md>)

Tags: [amazon-aurora](<https://devfeed.tech/tags/amazon-aurora.md>), [database](<https://devfeed.tech/tags/database.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [heroku-postgres](<https://devfeed.tech/tags/heroku-postgres.md>), [launch](<https://devfeed.tech/tags/launch.md>), [migration](<https://devfeed.tech/tags/migration.md>), [news](<https://devfeed.tech/tags/news.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [product-features](<https://devfeed.tech/tags/product-features.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [sql](<https://devfeed.tech/tags/sql.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

Heroku announces new Postgres Essential plans built on Amazon Aurora. The plans include pgvector support, no row-count limits, a 32 GB option, PostgreSQL compatibility, and fully managed database service starting at $5 per month. Existing Mini and Basic plans are scheduled for automatic migration.

### Source excerpt

We're thrilled to launch our new Heroku Postgres Essential database plans. These plans have pgvector support, no row count limits, and come with a 32 GB option. We deliver exceptional transactional query performance with Amazon Aurora as the backing infrastructure. One of our beta customers said: "The difference was noticeable right from the start. Heroku [...] The post Introducing New Heroku Postgres Essential Plans Built On Amazon Aurora appeared first on Heroku.

## How to Use pgvector for Similarity Search on Heroku Postgres

DevFeed: [How to Use pgvector for Similarity Search on Heroku Postgres](<https://devfeed.tech/articles/how-to-use-pgvector-for-similarity-search-on-heroku-postgres-26483.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/pgvector-for-similarity-search-on-heroku-postgres/>)

Author: Valerie Woolard

Published: 2023-11-16T00:42:00Z

Content type: tutorial

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku Postgres](<https://devfeed.tech/topics/heroku-postgres.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [embeddings](<https://devfeed.tech/tags/embeddings.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [heroku](<https://devfeed.tech/tags/heroku.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [python](<https://devfeed.tech/tags/python.md>), [release](<https://devfeed.tech/tags/release.md>), [similarity-search](<https://devfeed.tech/tags/similarity-search.md>)

### AI overview

This tutorial explains how to use the pgvector extension on Heroku Postgres for similarity search. It describes supported databases, vector embeddings, and a Python example using Wikipedia2Vec to generate and store embeddings.

### Source excerpt

Introducing pgvector for Heroku Postgres Over the past few weeks, we worked on adding pgvector as an extension on Heroku Postgres. We're excited to release this feature, and based on the feedback on our public roadmap, many of you are too. We want to share a bit more about how you can use it and [...] The post How to Use pgvector for Similarity Search on Heroku Postgres appeared first on Heroku.

## Heroku Postgres Adds pgvector Extension for Vector Similarity Search

DevFeed: [Heroku Postgres Adds pgvector Extension for Vector Similarity Search](<https://devfeed.tech/articles/enhancing-heroku-postgres-with-pgvector-generating-ai-insights-26484.md>)

Original publisher: [Read original article](<https://www.heroku.com/blog/pgvector-launch/>)

Author: Jonathan Brown

Published: 2023-10-26T21:18:00Z

Content type: release

Language: en

Sources: [Heroku](<https://devfeed.tech/sources/heroku.md>)

Topics: [Heroku Postgres](<https://devfeed.tech/topics/heroku-postgres.md>), [Heroku](<https://devfeed.tech/topics/heroku.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [database](<https://devfeed.tech/tags/database.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [heroku-postgres](<https://devfeed.tech/tags/heroku-postgres.md>), [news](<https://devfeed.tech/tags/news.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>)

### AI overview

Heroku introduces the pgvector extension for Heroku Postgres. It supports high-dimensional vector similarity searches and is compatible with Production-tier Postgres 15 databases at no additional charge.

### Source excerpt

We're pleased to introduce the pgvector extension on Heroku Postgres. In an era where large language models (LLMs) and AI applications are paramount, pgvector provides the essential capability for performing high-dimensional vector similarity searches. This allows Heroku Postgres to quickly find similar data points in complex data, which is great for applications like recommendation systems [...] The post Enhancing Heroku Postgres with pgvector: Generating AI Insights appeared first on Heroku.

## pgvector: Fewer dimensions are better

DevFeed: [pgvector: Fewer dimensions are better](<https://devfeed.tech/articles/pgvector-fewer-dimensions-are-better-371.md>)

Original publisher: [Read original article](<https://supabase.com/blog/fewer-dimensions-are-better-pgvector>)

Author: Greg Richardson; Oliver Rice; Egor Romanov

Published: 2023-08-03T07:00:00Z

Content type: article

Language: en

Sources: [Supabase Blog](<https://devfeed.tech/sources/supabase-blog.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Supabase](<https://devfeed.tech/topics/supabase.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>)

Tags: [compute](<https://devfeed.tech/tags/compute.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [index](<https://devfeed.tech/tags/index.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [openai](<https://devfeed.tech/tags/openai.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [provisioning](<https://devfeed.tech/tags/provisioning.md>), [vectors](<https://devfeed.tech/tags/vectors.md>)

### AI overview

This article explains why using embedding vectors with fewer dimensions can improve pgvector performance. It covers vector storage in Postgres, similarity indexes, memory and compute requirements, and the scaling challenges of high-dimensional embeddings.

### Source excerpt

Increase performance in pgvector by using embedding vectors with fewer dimensions

## 20x faster than pgvector: introducing pg\_embedding extension for vector search in Postgres and LangChain

DevFeed: [20x faster than pgvector: introducing pg\_embedding extension for vector search in Postgres and LangChain](<https://devfeed.tech/articles/20x-faster-than-pgvector-introducing-pg-embedding-extension-for-vector-search-in-postgres-and-langchain-5715.md>)

Original publisher: [Read original article](<https://neon.com/blog/pg-embedding-extension-for-vector-search>)

Author: Raouf Chebri

Published: 2023-07-11T16:34:04Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Extension](<https://devfeed.tech/topics/extension.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>)

Tags: [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [compare](<https://devfeed.tech/tags/compare.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [development](<https://devfeed.tech/tags/development.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [search](<https://devfeed.tech/tags/search.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article announces pg_embedding, a Postgres and LangChain extension for graph-based approximate nearest neighbor vector search. It describes HNSW indexing, compares it with IVFFlat using the GIST-960 dataset, and reports faster search at similar recall in the stated benchmark.

### Source excerpt

We're excited to announce the release of our pg_embedding extension for Postgres and LangChain! The new pg_embedding extension brings 20x the speed for 99% accuracy to graph-based approximate nearest neighbor search to your Postgres databases. While the pgvector extension with IV...

## Optimizing vector search performance with pgvector

DevFeed: [Optimizing vector search performance with pgvector](<https://devfeed.tech/articles/optimizing-vector-search-performance-with-pgvector-5704.md>)

Original publisher: [Read original article](<https://neon.com/blog/optimizing-vector-search-performance-with-pgvector>)

Author: Raouf Chebri

Published: 2023-06-28T16:01:07Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Database](<https://devfeed.tech/topics/database.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [community](<https://devfeed.tech/tags/community.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [product](<https://devfeed.tech/tags/product.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article explains how to optimize vector similarity search with pgvector in Postgres. It compares exact sequential scans with approximate nearest neighbor search using the ivfflat index, discusses performance as datasets grow, and introduces the Lists and Probes parameters that affect search speed and recall.

### Source excerpt

According to the StackOverflow Survey 2023, nearly half of professional developers use Postgres. It's natural then that the Postgres extension for vector similarity search, pgvector, is one of the most popular options for prototyping AI-powered applications. But how to properly u...

## Introducing AI Help (Beta): Your Companion for Web Development

DevFeed: [Introducing AI Help (Beta): Your Companion for Web Development](<https://devfeed.tech/articles/introducing-ai-help-beta-your-companion-for-web-development-4071.md>)

Original publisher: [Read original article](<https://developer.mozilla.org/en-US/blog/introducing-ai-help/>)

Author: hermina-condei

Published: 2023-06-27T00:00:00Z

Content type: news

Language: en

Sources: [MDN Blog](<https://devfeed.tech/sources/mdn-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [Supabase](<https://devfeed.tech/topics/supabase.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [API](<https://devfeed.tech/topics/api.md>), [Data Science](<https://devfeed.tech/topics/data-science.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [openai](<https://devfeed.tech/tags/openai.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [search](<https://devfeed.tech/tags/search.md>), [web-development](<https://devfeed.tech/tags/web-development.md>)

### AI overview

MDN introduces AI Help in beta, a logged-in-user feature that answers web development questions using MDN documentation. It combines embeddings stored in Supabase-hosted PostgreSQL with pgvector similarity search and OpenAI's Chat API to generate answers, examples, and links to the consulted articles.

### Source excerpt

We're introducing an AI assistant powered by MDN and OpenAI GPT 3.5 to answer all your web development questions in real time.

## ChatGPT plugins now support Postgres & Supabase

DevFeed: [ChatGPT plugins now support Postgres & Supabase](<https://devfeed.tech/articles/chatgpt-plugins-now-support-postgres-supabase-337.md>)

Original publisher: [Read original article](<https://supabase.com/blog/chatgpt-plugins-support-postgres>)

Author: Egor Romanov; Paul Copplestone

Published: 2023-05-25T07:00:00Z

Content type: article

Language: en

Sources: [Supabase Blog](<https://devfeed.tech/sources/supabase-blog.md>)

Topics: [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Supabase](<https://devfeed.tech/topics/supabase.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [Database](<https://devfeed.tech/topics/database.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [openai](<https://devfeed.tech/tags/openai.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [python](<https://devfeed.tech/tags/python.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

Supabase contributed Postgres and Supabase implementations to the OpenAI Retrieval Plugin repository, enabling developers to build ChatGPT plugins that retrieve information from private data sources using pgvector. The article explains how retrieval plugins chunk documents, generate embeddings, store them in a vector database, and query relevant content.

### Source excerpt

Supabase recently contributed to the OpenAI Retrieval Plugin repo with a Postgres and a Supabase implementation to help developers build ChatGPT plugins using pgvector.