L 
LlamaIndex
A data framework for retrieval-augmented generation over your documents.
KINDA
why this verdict
Keep it for the workflow, not the AI
Vector search in Postgres and Vercel AI SDK cover the headline feature free, and the workflow around it is why you would still open this.
- A named launch, not a vibe named, unlinked
- Long context windows and hosted file search absorbed basic RAG. OpenAI, January 1, 2025 — no announcement link recorded yet.
- How much of the job it covers headline only editorial call
- The headline feature, but not the workflow, data or integrations around it.
- Is there a free way to do it? yes
- 2 of 2 listed replacements have a usable free tier: Vector search in Postgres and Vercel AI SDK.
- What the call is worth nothing to cancel
- No paid entry tier tracked, so there is no subscription to cancel.
Reason composed from the fields above missing: announcement linked recorded: free replacement listed recorded: two or more escape hatches
- Threatened by
- OpenAI
- Since
- January 1, 2025
- List price
- free
- Per year
- —
The backstory
Naive RAG — chunk, embed, retrieve — is now a built-in feature of every assistant platform, and million-token contexts let you skip retrieval entirely for smaller corpora. LlamaIndex moved up the stack into document parsing and agentic workflows, because the simple version of its job stopped being a job.
Escape hatches
V 
Vector search in Postgres Often enough on its own.
github.com open_in_new V 
Vercel AI SDK Lighter for TypeScript apps.
ai-sdk.dev open_in_new2 of 2 replacements have a usable free tier.
