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

# Vectara API

Vectara is a GenAI platform providing Retrieval Augmented Generation (RAG) as a service. The API enables corpus management, document indexing, and semantic search with grounded generation. The API exposes 12 endpoints secured with bearer authentication.

## For AI agents

Programmatically create a corpus, list corpora. Covers 12 operations with bearer authentication.

## Scope

Does not handle payments, communications, or crm - use for developer tools only.

## Capabilities

- Create a corpus
- List corpora
- Get a corpus
- Update a corpus
- Delete a corpus
- Add a document to a corpus

## Use cases

### Developer Tools Operations

Use the Vectara API to perform developer tools operations programmatically. The API provides 12 endpoints covering core functionality including create a corpus, list corpora, get a corpus.

Example prompt: Call POST /corpora to create a corpus

### Automated Chat Management

Automate chat operations by combining multiple Vectara API endpoints. Agents can list corpora and then get a corpus in a single workflow.

Example prompt: Call GET /corpora to list corpora, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Vectara 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 bearer tokens manually.

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

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /corpora | Create a corpus |
| GET | /corpora | List corpora |
| GET | /corpora/{corpus_key} | Get a corpus |
| PATCH | /corpora/{corpus_key} | Update a corpus |
| DELETE | /corpora/{corpus_key} | Delete a corpus |
| POST | /corpora/{corpus_key}/documents | Add a document to a corpus |
| GET | /corpora/{corpus_key}/documents | List documents in a corpus |
| GET | /corpora/{corpus_key}/documents/{document_id} | Get a document |

## Key resources

- **Chat** — Operations for chat
- **Chats** — Operations for chats
- **Corpora** — Operations for corpora
- **Query** — Operations for query

## Why Jentic

- **Setup:** Wiring the Vectara API by hand means handling its bearer JWT auth against api.vectara.io and coding each corpus and document operation yourself. Through Jentic you install once, import the Vectara API from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Vectara puts the corpus key and document id in the URL path (/corpora/{corpus_key}, /corpora/{corpus_key}/documents/{document_id}), so a rule can pin your agent to one corpus. You choose the operations it may call, so destructive ones like deleting a corpus or a document are not included unless you add them.
- **Credential handling:** Your Vectara bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'create a corpus' or 'add a document to a corpus', and Jentic returns the matching Vectara operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the Vectara API use?

The Vectara API uses a Bearer token in the Authorization header. 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 create a corpus with the Vectara API?

Yes. Use the POST /corpora endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Vectara 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 create a corpus through Jentic?

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

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

The Vectara API exposes 12 endpoints covering chat, chats, corpora operations.

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

Yes. Because you run Jentic One yourself, your own rules decide which Vectara operations and credentials the agent may use. Vectara puts the corpus key and document id in the URL path (/corpora/{corpus_key} and /corpora/{corpus_key}/documents/{document_id}), so you can pin the agent to a single corpus and grant only read operations like listing corpora and getting documents. Destructive calls such as deleting a corpus or a document stay off unless you explicitly add them.