project
Open-source PostgreSQL extension adding vector data types and similarity search for embeddings in RAG and semantic search.
No evidence-backed relationships are recorded.
Turbopuffer is rewriting its serverless database as v3, moving the ANN index out of the core of storage and making it one of several secondary indexes. A dev.to explainer of the September 30 post says the vector-first layout held back GROUP BY and aggregation queries.
Reality
Databricks made Lakebase Search generally available, pairing BM25 with a Postgres vector index it says runs 4 times cheaper than pgvector at 100M vectors. The vector index lives in object storage behind a cache, so large agent corpora no longer need RAM sized to the whole index.
Reality
A dev.to walkthrough of a permission-aware Postgres project puts the ACL test in a CTE that the vector ranking reads from, so the nearest-neighbour search only ever orders rows the caller may see.
Reality
A dev.to walkthrough replaces a managed vector store and a hosted embedding API with sqlite-vec and a local model on port 11434. Its schema declares float[768], so changing model dimension means re-embedding everything.
Reality
A dev.to post argues that moving embeddings out of Postgres buys a second source of truth, a four-leg query path and 50 to 150 ms of internet latency. Its 8 ms pgvector counter-figure has no benchmark behind it.
Reality
A dev.to post lays out a four-layer recommender and a 100 millisecond p99 budget with no slot for a generative call in the hot path. The figures are its author's own allocation, not a measurement from a running system.
Reality
A September 2026 comparison pins the workload at 10 million 1536-dimension vectors and reports Qdrant between $250 and $947 a month, while Pinecone's serverless bill is set by the gigabytes each query scans.
Reality
AWS's comparison of the three customer-managed backends credits OpenSearch with in-memory speed and S3 Vectors with sub-second queries at up to 90 percent lower storage cost. The Aurora spec sets a ceiling your embedding model has to fit under.
Reality
A three-engine evaluation of filtered vector search on a purpose-built relational dataset credits Milvus's hybrid approximate/exact execution with stable recall, and puts pgvector's plan choice ahead of its index choice as the thing that loses it.
Reality
A dev.to design guide moves JSON documents and vector search into one PostgreSQL instance, and the evidence it offers is operational: deleted ETL pipelines and sync bugs, with no query timings on either side.
Reality
A dev.to walkthrough builds the whole retrieval path on pgvector and the azure_ai extension inside Azure Database for PostgreSQL. The costs land in the DDL, the extension allowlist, and a transaction that waits on an HTTP call.
Reality
A Java engineer measured his own retrieval pipeline and found that the 0.35 similarity floor had never rejected anything. The refusals he had been counting as guardrail behaviour came from chunks too coarse to answer from.
Reality
The upcoming technical preview in Red Hat OpenShift AI 3.5 runs the combinations and compiles the winner into a deployable pipeline. The test data and the metric it scores against are still yours to supply.
Reality
A tester on Nile's free tier made two tenants, then ran the same SELECT on a connection that never set nile.tenant_id and got every row back. Nile's docs describe that open read as deliberate, so the guarantee sits in application code.
Reality
Statewave's case for a separate agent memory layer rests on three defaults in a RAG stack: similarity-only ranking, append-only chunks, and no compaction. The post asserts all three failure modes and measures none of them.
Reality
pgvector ships hnsw.ef_search at 40, the size of the candidate list its graph walk keeps in flight, and a top-20 query with a tenant filter can come back with two rows and no error to explain it.
Reality
Mem0-style memory replaces embed-and-store with extraction, write-time retrieval, an ADD/UPDATE/DELETE/NOOP decision and consolidation. The similarity scores in the dev.to writeup show why no threshold can make that call for you.
Reality
The dedicated store won every unfiltered benchmark this team ran, which happened to be the one query their product never issued. What they were paying for was a copy of derived data that could disagree with its source in silence.
Reality
An independent rebuild of the SQLite side says the gap is real, but the published tables measure two different queries on two different graphs, so the depth at which SQLite's plan collapses on your data is a number you have to take yourself.
Reality
The estimate was 30,000 to 40,000 credits per simulation, the gateway needed only three read patterns, and the store already holding tenant rows could serve all three, so tenancy became an argument every query passes.
Reality
Build · August 26, 2026 · 1 publisher
Build · August 25, 2026 · 1 publisher
Build · August 22, 2026 · 1 publisher
Build · August 21, 2026 · 1 publisher
Build · August 19, 2026 · 1 publisher
Build · August 18, 2026 · 1 publisher
Build · August 15, 2026 · 1 publisher
Build · August 15, 2026 · 1 publisher
Build · August 14, 2026 · 1 publisher