What do our Vectara corpora say about refunds, and which documents match best?
Vectara connects Memtro to your retrieval platform. It runs semantic search across one or more corpora, returning the best-matching passages with scores, document ids and metadata. It reads corpora with their size and encoder, document lists and the text of a document's first parts, background jobs and agents. When asked and granted, it can add a document, merge or replace a document's metadata, delete documents, create, rename, disable or enable a corpus, empty a corpus and delete one. Search generates no answer and spends no LLM credits, and a Query key can read but not change anything.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Vectara tool, reads what it needs, and answers with the source cited.
These tools change something in Vectara. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Once Vectara is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Vectara + MemtroWhat does the policies corpus say about refunds?
Which corpora are closest to their storage maximum?
Which documents in the contracts corpus have the status archived?
Has the bulk delete from last night finished?
Disable the old support corpus.
Maya Okafor, support manager at Acme Ltd, asked what the help centre corpus said about returns after 30 days. Memtro searched it and gave her the best-matching passages with their scores and document ids. She opened the top document and quoted it to the customer.
Tom Reilly, platform lead at BigCo, asked Memtro to disable the old product docs corpus once the new one was live. With the action granted, Memtro disabled it, taking it offline for search and indexing without deleting it. It can be enabled again if anyone needs it.
The teams that lean on Vectara most, a question each of them asks, and what they connect beside it.
A record in Vectara is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
Grist
NocoDB
Typesense
Weaviate
Tinybird
Hightouch
Census
kintone
Monte Carlo
OpenMetadata
Secoda
Softr
TeableIn the Vectara Console, open Authorization, then Index and Query API Keys, and create a key for the corpora Memtro may use. A Query key only searches and reads, and an Index key also changes documents.
In Memtro, open Connections → Vectara and paste the API key.
An administrator grants the document and corpus actions by name to the teams that may use them. A personal key carries every permission its owner has, so prefer a scoped one.
Ask what the policies corpus says about refunds.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Vectara tools are the same everywhere.
Only when you ask, and only what it has been granted: add a text document to a corpus; merge new metadata into a document; replace a document's metadata; delete a document (permanent); delete up to 100 named documents (permanent, runs as a background job); create a corpus; rename, describe, disable or enable a corpus; empty a corpus of every document (permanent); delete a corpus and all its data (permanent). Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
API key. In the Vectara Console, open Authorization, then Index and Query API Keys, and create a key for the corpora Memtro may use. A Query key only searches and reads, and an Index key also changes documents.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time
