canonical: https://jentic.com/apis/vectara.io/vectara

# Vectara REST API

Vectara provides an end-to-end platform for creating GenAI products using a simple to use API. You can [sign up for an account](https://console.vectara.com/signup) and then view several [API Recipes](https://docs.vectara.com/docs/api-recipes) with example queries and parameter values. The Vectara API Playground lets you experiment with REST endpoints from your browser. Select an endpoint to view i. The API exposes 29 endpoints secured with apiKey, oauth2 authentication.

## For AI agents

Programmatically computeaccountsize, computecorpussize. Covers 29 operations with apiKey, oauth2 authentication.

## Scope

Does not handle payments, communications, or crm - use for e-commerce only.

## Capabilities

- ComputeAccountSize
- ComputeCorpusSize
- CreateApiKey
- CreateCorpus
- DeleteApiKey
- DeleteConversations
- DeleteCorpus

## Use cases

### E-Commerce Operations

Use the Vectara REST API to perform e commerce operations programmatically. The API provides 29 endpoints covering core functionality including computeaccountsize, computecorpussize, createapikey.

Example prompt: Call POST /v1/compute-account-size to computeaccountsize

### Automated AdminService Management

Automate adminservice operations by combining multiple Vectara REST API endpoints. Agents can computecorpussize and then createapikey in a single workflow.

Example prompt: Call POST /v1/compute-corpus-size to computecorpussize, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Vectara REST API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey, oauth2 tokens manually.

Example prompt: Search Jentic for 'computeaccountsize', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /v1/compute-account-size | ComputeAccountSize |
| POST | /v1/compute-corpus-size | ComputeCorpusSize |
| POST | /v1/create-api-key | CreateApiKey |
| POST | /v1/create-corpus | CreateCorpus |
| POST | /v1/delete-api-key | DeleteApiKey |
| POST | /v1/delete-conversations | DeleteConversations |
| POST | /v1/delete-corpus | DeleteCorpus |
| POST | /v1/delete-doc | Delete |

## Key resources

- **AdminService** — Administrative operations, such as creating or deleting corpora
- **IndexService** — Indexing operations, such as creating and deleting documents
- **QueryService** — Query operations, such as performing a search and retrieval augmented generation
- **DocumentService** — Document operations, listing documents in a corpus
- **ChatService** — Chat operations, such as listing and reading conversations

## Why Jentic

- **Setup:** Wiring the Vectara REST API by hand means choosing between its x-api-key header and the OAuth2 client-credentials flow through Cognito, then coding each corpus and account operation as a POST call yourself. Through Jentic you install once, import the Vectara REST API from the API Directory, store the credential once, and your agent calls it.
- **Permission scoping:** The Vectara REST operations carry the corpus and account targets in the request body rather than the path, so limit the agent to the operations it needs, such as creating a corpus or computing account size. You choose that allowed set, so destructive ones like deleting a corpus or a document are excluded unless you add them.
- **Credential handling:** Your Vectara API key or OAuth credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'create a corpus' or 'compute account size', and Jentic returns the matching Vectara REST API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Shopify** — Alternative e commerce API
- **Stripe** — Alternative e commerce API

## FAQ

### What authentication does the Vectara REST API use?

The Vectara REST API uses apiKey, oauth2 authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I computeaccountsize with the Vectara REST API?

Yes. Use the POST /v1/compute-account-size endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Vectara REST API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I computeaccountsize through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'computeaccountsize'. Jentic returns the matching Vectara REST API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Vectara REST API have?

The Vectara REST API exposes 29 endpoints covering adminservice, indexservice, queryservice operations.

### Can I limit what my agent is allowed to do with the Vectara REST API?

Yes. Because you self-host Jentic One, your own rules decide which Vectara operations and credentials the agent may use, so you can grant only what it needs, such as creating a corpus or computing account and corpus size. Destructive operations like deleting a corpus, a document, or an API key stay excluded unless you explicitly add them. Since each Vectara operation carries its corpus and account target in the request body, scoping the allowed set of operations controls exactly what the agent can call.