New
RAG vs fine-tuning vs long context: what is working for your use case?
Share the use case, the approach you chose and the results.
Topic
RAG and vector search
21 stories in the last 90 days · 2 community threads
In short
Retrieval-augmented generation (RAG) gives a language model relevant passages from your own documents or data at question time, usually found through vector search over embeddings. It is a common way to ground AI answers in company knowledge, so buyers should look closely at retrieval quality, access controls on the source data and how answers cite their sources.
Written by Techarda editors · Updated · How we work
Latest stories
The newest RAG and vector search stories from the last 90 days. Each one opens with our summary and a link to the original source.
Databases
Graph Embeddings, One Line of Code Away
A single account on its own tells you very little. But look at who it sends money to, who those accounts send money to, and suddenly you have got a lot to work with. That’s the idea behind graph embeddings:… Read more →
Cloud Infrastructure
Vector Search Can’t Tell “Yes” From “No”
Learn why vector search can rank contradictory statements as similar, and how hybrid retrieval can help RAG systems identify conflicting information.
Containers & Kubernetes
AlloyDB: A unified database engine for hybrid search
For modern AI and RAG applications, achieving high search relevance requires that you combine at least two techniques: vector search for semantic context, and full-text search (FTS) for keyword precision. While AlloyDB for PostgreSQL supports both of these capabilities, managing them has traditionally required a more hands-on operational approach to ensure peak performance. The challenge is not…
Data & Analytics
NEAREST BY Join: Scaling Vector Search in Databricks Runtime
Vector search originated as a serving problem. The classical use case is a chatbot...
Containers & Kubernetes
From AI pilots to production: How DH2i and Red Hat help customers run resilient, security-focused AI on Red Hat OpenShift
Building an AI application is a milestone; running it reliably against business-critical enterprise data is a challenge. As organizations transition retrieval-augmented generation (RAG) and AI assistants from the lab to production, the underlying infrastructure becomes the primary differentiator. To succeed, models require continuous access to trusted data, the ability to coexist with legacy…
Cloud Infrastructure
Amazon S3 Vectors introduces metadata pre-filtering for up to 5x higher recall on filtered search
Amazon S3 Vectors now supports pre-filtering, which evaluates metadata filters before running similarity search, returning up to 5x more of the matching vectors when your filter is selective. S3 Vectors also adds a prefix match operator ($startsWith) for filtering on values like paths and URLs. Together, these improvements give your retrieval-augmented generation (RAG), agentic, and…
Databases
What is contextual retrieval? How AI agents find the right context
Most RAG systems today score how semantically similar a new query is to stored text chunks and return a list of the best matches. However, information doesn’t need to include similar words to be relevant. Data entities might be related… Read more →
Data & Analytics
Lakebase Search: State-of-the-art full text and vector search for Postgres
Traditional OLTP systems weren't built for the search demands of AI agents. They...
Earlier in the last 90 days
- Storage-optimized Z4D machine family, now GA, is designed for IO-intensive workloadsGoogle Cloud · 28 Sept 2026
- How to add hybrid search to a Postgres app with Pinecone in 2026Pinecone · 26 Sept 2026
- AI cost management: How to build a business case for executivesFlexera · 24 Sept 2026
- What Would RAG Look Like If Miranda Priestly Were the User?Akamai · 24 Sept 2026
- Rescored binary vector search in Neo4j: search more with less memoryNeo4j · 23 Sept 2026
- How to Build an SRE Agent That Actually Works (Without Blowing the Token Budget)New Relic · 22 Sept 2026
- Should you read the code, is RAG dead, and did Skills kill MCP?GitHub · 19 Sept 2026
- Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field NotesJetBrains · 17 Sept 2026
- AI Functions in ClickHouse: Upgrade your SQL to the AI ageClickHouse · 11 Sept 2026
- Qdrant Builds a 10-Billion-Document Vector Search Benchmark Dataset on VultrVultr · 2 Sept 2026
- Metadata filtering: boost search precision as data growsRedis · 17 Aug 2026
- Vector search in production: index trade-offs, failure modes & what to watchRedis · 14 Aug 2026
- Vector search database: news & 2026 guideRedis · 13 Aug 2026
What practitioners are discussing
Stories say what companies announced. These threads are where people who work with RAG and vector search compare notes.
New
Postgres everywhere vs purpose-built databases: where do you draw the line?
Vector search, time series, queues, analytics: many teams now start with Postgres extensions. Where has that worked, and where did you need a dedicated engine?
Companies in these stories
The active companies with the most RAG and vector search stories in the last 90 days. It counts news coverage, not quality, market share or fit for your needs.
Related categories
Where RAG and vector search sits among the categories Techarda covers. Each hub shows who is active, and each guide sets out how to evaluate vendors.
Terms to know
Plain definitions of terms that come up in RAG and vector search stories, from the Techarda glossary.
Frequently asked questions
When should we use RAG instead of fine-tuning?
Use RAG when answers depend on information that changes or must be traced to a source, such as policies, product documentation or tickets. Fine-tuning suits teaching a model a style, format or narrow task. Many systems use both.
Do we need a dedicated vector database?
Not always. Many relational and search databases now store and search vectors, which can be enough at moderate volumes and keeps data in one place. A dedicated vector database makes more sense at large scale or when search performance is the main concern.
How do we stop RAG exposing documents people shouldn’t see?
Carry the source system’s permissions into the index and filter results by the user’s access at query time. Test it during evaluation with users who have different rights.
Why does RAG give wrong answers when the documents are right?
Usually because retrieval found the wrong passages, documents were split badly, or the answer needed information spread across many sources. Measuring retrieval separately from answer quality shows which part to fix.
Stories are filed under topics automatically from their headline and summary, so the odd one may sit in the wrong place. Spotted one, or a topic we should add? Email engage@techarda.com. All topics.