### First-run Setup

Source: https://rag.computer/docs/api-reference/authentication

Endpoints for initial setup, including checking setup status and creating the first admin account. The setup endpoint works only once.

```APIDOC
## Check setup status
### Description
Checks if the initial setup is still required.
### Method
GET
### Endpoint
/v1/auth/setup-status

## Create first admin
### Description
Creates the first administrator account. This endpoint can only be successfully called once.
### Method
POST
### Endpoint
/v1/auth/setup
### Request Body
- **email** (string) - Required - The email address for the admin account.
- **password** (string) - Required - The password for the admin account.
- **display_name** (string) - Required - The display name for the admin account.

### Request Example
```json
{
  "email": "admin@example.com",
  "password": "a-strong-password",
  "display_name": "Admin"
}
```
```

--------------------------------

### Initial Setup and Login

Source: https://rag.computer/docs/api-reference/authentication

Endpoints for the initial setup of the API and user login. These are accessible without authentication.

```APIDOC
## GET /v1/auth/setup-status

### Description
Checks the setup status of the API to determine if initial configuration is needed.

### Method
GET

### Endpoint
/v1/auth/setup-status

### Parameters
None

### Request Example
None

### Response
#### Success Response (200)
- **is_setup** (boolean) - True if the initial setup has been completed, false otherwise.

#### Response Example
{
  "is_setup": false
}

## POST /v1/auth/setup

### Description
Performs the initial setup for the API. This endpoint should only be called once.

### Method
POST

### Endpoint
/v1/auth/setup

### Parameters
#### Request Body
- **password** (string) - Required - The password for the initial administrator account.
- **password_confirmation** (string) - Required - Confirmation of the administrator password.

### Request Example
{
  "password": "yourStrongPassword",
  "password_confirmation": "yourStrongPassword"
}

### Response
#### Success Response (200)
- **message** (string) - Indicates successful setup.

#### Response Example
{
  "message": "Setup complete."
}

## POST /v1/auth/login

### Description
Logs in a user to the API.

### Method
POST

### Endpoint
/v1/auth/login

### Parameters
#### Request Body
- **username** (string) - Required - The user's username.
- **password** (string) - Required - The user's password.

### Request Example
{
  "username": "user@example.com",
  "password": "userPassword"
}

### Response
#### Success Response (200)
- **session_token** (string) - The session token for authenticated requests.

#### Response Example
{
  "session_token": "yourSessionToken"
}
```

--------------------------------

### Check Setup Status and Create First Admin

Source: https://rag.computer/docs/api-reference/authentication

Use this endpoint to check if the initial admin setup is required. If it is, use the POST request to create the first admin account with email, password, and display name.

```bash
# Check whether setup is still required
curl http://localhost:4000/v1/auth/setup-status
# → {"needs_setup": true}

# Create the first admin (works exactly once)
curl -X POST http://localhost:4000/v1/auth/setup \
  -H "Content-Type: application/json" \
  -d '{
    "email": "admin@example.com",
    "password": "a-strong-password",
    "display_name": "Admin"
  }'
```

--------------------------------

### Install and Run bigRAG Backend from Source (uv)

Source: https://rag.computer/docs/getting-started/installation

Navigate to the API directory, install dependencies using uv, and run the backend. This method is for running from source.

```bash
cd api
uv sync
uv run python -m bigrag.main
```

--------------------------------

### client.auth.setupStatus

Source: https://rag.computer/docs/sdks/typescript

Checks the authentication setup status.

```APIDOC
## client.auth.setupStatus

### Description
Checks whether the authentication system has been initialized or requires setup.

### Method Signature
```typescript
setupStatus(): Promise<any>;
```
```

--------------------------------

### Install and Run bigRAG Backend from Source (venv/pip)

Source: https://rag.computer/docs/getting-started/installation

Create a virtual environment, activate it, install the backend in editable mode using pip, and then run the main module.

```bash
cd api
python -m venv .venv && source .venv/bin/activate
pip install -e .
python -m bigrag.main
```

--------------------------------

### Install bigrag CLI

Source: https://rag.computer/docs/sdks/mcp

Install the bigrag CLI tool for local stdio MCP server setup. This can be done using 'uv tool install' or 'pip install'.

```Shell
uv tool install bigrag
# or: pip install bigrag
```

--------------------------------

### Start Infrastructure Services with Docker Compose

Source: https://rag.computer/docs/getting-started/installation

Start only the PostgreSQL and Redis services using Docker Compose, useful for running the backend from source.

```bash
docker compose up postgres redis -d
```

--------------------------------

### Multi-Collection Query Example

Source: https://rag.computer/docs/concepts/search

Example of querying multiple collections simultaneously to get a unified answer from distributed content.

```curl
curl -X POST http://localhost:4000/v1/query \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"machine learning","collections":["docs","papers"],"top_k":20}'
```

--------------------------------

### Start bigRAG with Docker Compose

Source: https://rag.computer/docs/getting-started/installation

Use this command to quickly start the full bigRAG stack using Docker Compose. This includes the API, Admin UI, PostgreSQL, and Redis.

```bash
docker compose up -d
```

--------------------------------

### Usage Response Example

Source: https://rag.computer/docs/api-reference/usage

Example of the JSON response structure for the Usage API. It includes overall statistics and a breakdown by collection.

```json
{
  "window_days": 30,
  "queries_total": 9122,
  "queries_per_day_avg": 304.07,
  "documents_total": 482,
  "chunks_total": 18420,
  "storage_bytes_total": 52428800,
  "embedding_tokens_total": 1820432,
  "embedding_cost_usd_estimate": 0.36,
  "avg_latency_ms": 142.31,
  "timeline": [
    {
      "date": "2026-05-16T00:00:00Z",
      "queries": 230,
      "avg_latency_ms": 138.44
    }
  ],
  "by_collection": [
    {
      "collection": "knowledge_base",
      "documents": 15,
      "chunks": 482,
      "storage_bytes": 52428800,
      "embedding_tokens": 125000,
      "embedding_cost_usd_estimate": 0.0250,
      "queries": 1203,
      "avg_latency_ms": 142.31
    }
  ]
}
```

--------------------------------

### Worker Command Example

Source: https://rag.computer/docs/deployment/production

This is the command used to start a bigRAG worker process, specifying the number of processes and threads.

```bash
bigrag-worker --processes 1 --threads 8
```

--------------------------------

### Run Admin UI

Source: https://rag.computer/docs/admin-ui

Use this command to start the admin UI development server. It runs on http://localhost:3000.

```bash
pnpm dev:app        # admin UI on http://localhost:3000
```

--------------------------------

### Install TypeScript SDK

Source: https://rag.computer/docs/sdks/typescript

Install the BigRAG TypeScript client using npm. This package is compatible with Node.js 18+, browsers, Deno, Bun, and edge runtimes.

```bash
npm install @bigrag/client
```

--------------------------------

### Create Collection with Default Query Settings

Source: https://rag.computer/docs/concepts/collections

This example shows how to create a collection and set default query parameters like top_k, min_score, and search_mode. These defaults are used if not specified during a query.

```bash
curl -X POST http://localhost:4000/v1/collections \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "docs",
    "default_top_k": 20,
    "default_min_score": 0.3,
    "default_search_mode": "hybrid"
  }'
```

--------------------------------

### Get Vector Storage Overview

Source: https://rag.computer/docs/sdks/python

Retrieve an overview of the vector storage.

```APIDOC
## Get Vector Storage Overview

### Description
Retrieve an overview of the vector storage.

### Method
`client.admin.vector_storage.overview()`
```

--------------------------------

### Install bigRAG Python SDK

Source: https://rag.computer/docs/sdks/python

Install the bigRAG Python SDK using pip. Ensure you are using Python 3.11 or newer. The SDK has httpx as its only runtime dependency.

```bash
pip install bigrag==2026.5.23
```

--------------------------------

### Create First Admin User

Source: https://rag.computer/docs/getting-started/quickstart

Creates the initial administrator account. This endpoint is only available during the initial setup phase when `needs_setup` is true. It also saves session cookies for subsequent requests.

```bash
export BASE="http://localhost:4000"

curl -X POST $BASE/v1/auth/setup \
  -H "Content-Type: application/json" \
  -d '{
    "email": "admin@example.com",
    "password": "a-strong-password",
    "display_name": "Admin"
  }' \
  -c cookies.txt
```

--------------------------------

### Check Authentication Setup Status

Source: https://rag.computer/docs/sdks/typescript

Determine if the authentication system has been set up using `client.auth.setupStatus`. This is typically the first step before other auth operations.

```typescript
client.auth.setupStatus()
```

--------------------------------

### Quick Start: Initialize and Use bigRAG Client

Source: https://rag.computer/docs/sdks/python

Initialize the async bigRAG client, create a collection, upload a document, and query the collection. The client requires an API key and is used within an async context manager.

```python
import asyncio
from bigrag import BigRAG

async def main():
    async with BigRAG(api_key="bigrag_sk_…") as client:  # minted at /v1/admin/api-keys
        # Create a collection
        collection = await client.collections.create({
            "name": "knowledge_base",
            "description": "Company docs",
        })

        # Upload a document
        doc = await client.documents.upload(
            "knowledge_base",
            "/path/to/report.pdf",
        )

        # Query the collection
        results = await client.queries.query("knowledge_base", {
            "query": "What is our revenue?",
            "top_k": 5,
        })

        for r in results["results"]:
            print(f"[{r['score']:.3f}] {r['text'][:100]}")

asyncio.run(main())
```

--------------------------------

### Realtime Token Generation

Source: https://rag.computer/docs/api-reference/realtime

Example of how to obtain a short-lived realtime token for authentication.

```APIDOC
## Realtime Token Generation

### Description
This section shows how to generate a short-lived realtime token, which can be used for authentication when a browser cannot send bearer headers during the WebSocket handshake.

### Request Example
```bash
TOKEN=$(curl -s -X POST http://localhost:4000/v1/collections/docs/realtime-token \
  -H "Authorization: Bearer $BIGRAG_API_KEY" | jq -r .token)
```

### Usage
- The `POST /v1/collections/{name}/realtime-token` endpoint is used to request a token.
- An `Authorization: Bearer $BIGRAG_API_KEY` header is required.
- The response contains a `token` field which is the generated realtime token.
- Tokens are short-lived (5 minutes) and collection-scoped.
```

--------------------------------

### Configure vLLM Collection (OpenAI-Compatible)

Source: https://rag.computer/docs/concepts/embeddings

Example cURL command to create a new collection using a vLLM endpoint, which is OpenAI-compatible. Specify the base URL and model.

```shell
curl -X POST http://localhost:4000/v1/collections \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "vllm_collection",
    "embedding_provider": "openai_compatible",
    "embedding_model": "BAAI/bge-large-en-v1.5",
    "embedding_base_url": "http://vllm.internal:8000/v1",
    "embedding_api_key": "dummy",
    "dimension": 1024
  }'
```

--------------------------------

### Get Vector Storage Overview

Source: https://rag.computer/docs/sdks/python

Retrieve an overview of the platform's vector storage utilization and status.

```python
overview = await client.admin.vector_storage.overview()
```

--------------------------------

### Get Question Suggestions

Source: https://rag.computer/docs/sdks/typescript

Retrieve suggested questions for a given collection.

```typescript
const suggestions = await client.chat.getQuestionSuggestions("docs");
```

--------------------------------

### Quick Start: BigRAG TypeScript SDK

Source: https://rag.computer/docs/sdks/typescript

Initialize the BigRAG client, create a collection, upload a document, poll its processing status, and perform a query. Ensure your API key is set as an environment variable or passed directly.

```typescript
import { BigRAG } from "@bigrag/client";

const client = new BigRAG({
  apiKey: process.env.BIGRAG_API_KEY!, // bigrag_sk_... minted via /v1/admin/api-keys
  baseUrl: "http://localhost:4000",
});

// Create a collection
const collection = await client.collections.create({
  name: "knowledge_base",
  description: "Company docs",
  chunk_size: 512,
});

// Upload a document
const doc = await client.documents.upload("knowledge_base", file);

// Poll processing status
let current = doc;
while (current.status === "pending" || current.status === "processing") {
  await new Promise((resolve) => setTimeout(resolve, 2000));
  current = await client.documents.get("knowledge_base", doc.id);
  console.log(current.progress?.message ?? current.status);
}

// Query
const { results } = await client.queries.query("knowledge_base", {
  query: "What is the PTO policy?",
  top_k: 5,
});
```

--------------------------------

### Get Platform Statistics

Source: https://rag.computer/docs/sdks/python

Retrieve overall statistics and metrics for the platform.

```python
stats = await client.get_stats()
```

--------------------------------

### Metadata Filtering Example

Source: https://rag.computer/docs/concepts/search

Demonstrates how to apply metadata filters for exact matches on fields like 'author' and 'year'.

```json
{
  "filters": { "author": "Smith", "year": 2026 }
}
```

--------------------------------

### Configure Local OpenAI-Compatible Collection (Ollama)

Source: https://rag.computer/docs/concepts/embeddings

Example cURL command to create a new collection using an OpenAI-compatible endpoint, such as Ollama. Provide the base URL and model name.

```shell
curl -X POST http://localhost:4000/v1/collections \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "local_collection",
    "embedding_provider": "openai_compatible",
    "embedding_model": "nomic-embed-text",
    "embedding_base_url": "http://ollama.internal:11434/v1",
    "embedding_api_key": "ollama",
    "dimension": 768
  }'
```

--------------------------------

### Get Vector Storage Overview

Source: https://rag.computer/docs/sdks/typescript

Retrieve an overview of the system's vector storage utilization using `client.admin.vectorStorage.overview`.

```typescript
client.admin.vectorStorage.overview()
```

--------------------------------

### Run bigRAG in Development Mode

Source: https://rag.computer/docs/getting-started/installation

Execute the dev.sh script to start all services and the backend with auto-reloading for development purposes.

```bash
./dev.sh
```

--------------------------------

### API Key Scopes Example

Source: https://rag.computer/docs/concepts/security

Defines the available scopes for API keys, which restrict access to specific resources and actions. A wildcard '*' can be used. Missing scopes result in a 403 error.

```text
collection:read          # GET /v1/collections, GET /v1/collections/{name}, stats
collection:write         # POST, PUT collections
collection:delete        # DELETE collections, truncate
document:upload          # POST /v1/collections/{name}/documents, batch upload, upload sessions
document:read            # GET documents, chunks, elements, batch get/status, /v1/documents/{id}
document:delete          # DELETE documents, batch delete
query:read               # POST /query, /batch/query, /collections/{name}/query
chat:read                # GET /v1/chat/question-suggestions
chat:write               # POST /v1/chat, POST /v1/chat/question-suggestions
vector:write             # POST /v1/collections/{name}/vectors/upsert
vector:delete            # POST /v1/collections/{name}/vectors/delete
audit:read               # GET /v1/usage
*:*                      # equivalent to no scopes
```

--------------------------------

### Get Platform Usage

Source: https://rag.computer/docs/sdks/python

Fetch platform usage data over a specified time window, in days.

```python
usage = await client.get_usage(window_days=30)
```

--------------------------------

### client.auth.setup

Source: https://rag.computer/docs/sdks/typescript

Sets up authentication with initial credentials.

```APIDOC
## client.auth.setup

### Description
Initializes the authentication system by setting up the first user account.

### Method Signature
```typescript
setup(options: { email: string; password: string; display_name?: string }): Promise<any>;
```

### Parameters
- **email** (string) - Required - The email address for the initial user.
- **password** (string) - Required - The password for the initial user.
- **display_name** (string) - Optional - The display name for the initial user.
```

--------------------------------

### Configure OpenAI Collection

Source: https://rag.computer/docs/concepts/embeddings

Example cURL command to create a new collection using the OpenAI embedding provider. Specify the model, API key, and dimensions.

```shell
curl -X POST http://localhost:4000/v1/collections \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "openai_collection",
    "embedding_provider": "openai",
    "embedding_model": "text-embedding-3-small",
    "embedding_api_key": "sk-...",
    "dimension": 1536
  }'
```

--------------------------------

### Set Up Authentication

Source: https://rag.computer/docs/sdks/typescript

Initialize the authentication system by providing an email and password using `client.auth.setup`. An optional display name can also be set.

```typescript
client.auth.setup({ email, password, display_name? })
```

--------------------------------

### Get Access Overview

Source: https://rag.computer/docs/sdks/typescript

Obtain a summary of access activity over a specified period using `client.admin.access.overview`. The `windowDays` parameter defines the lookback period.

```typescript
client.admin.access.overview({ windowDays? })
```

--------------------------------

### Keyword Search Query

Source: https://rag.computer/docs/concepts/search

Use keyword search for exact terms, product codes, IDs, or proper nouns. This example searches for a specific error code.

```curl
curl -X POST http://localhost:4000/v1/collections/docs/query \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "ERR-4021", "search_mode": "keyword"}'
```

--------------------------------

### Get Collection Stats

Source: https://rag.computer/docs/sdks/mcp

Get statistics for a specific collection, including document, chunk, and token counts.

```APIDOC
## Get Collection Stats

### Description
Get statistics for a specific collection, including document, chunk, and token counts.

### Method
GET

### Endpoint
/v1/collections/{name}/stats

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the collection.
```

--------------------------------

### Audit Trail Query Example

Source: https://rag.computer/docs/cookbook/multi-tenant-saas

Fetches audit log entries, filtering by resource type. This is useful for compliance and security monitoring of privileged actions. Requires authentication via cookies.

```bash
curl -b cookies.txt \
  "http://localhost:4000/v1/admin/audit?resource_type=collection"
```

--------------------------------

### Configure Cohere Collection

Source: https://rag.computer/docs/concepts/embeddings

Example cURL command to create a new collection using the Cohere embedding provider. Specify the model, API key, and dimensions.

```shell
curl -X POST http://localhost:4000/v1/collections \
  -H "Authorization: Bearer $BIGRAG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "cohere_collection",
    "embedding_provider": "cohere",
    "embedding_model": "embed-english-v3.0",
    "embedding_api_key": "co-...",
    "dimension": 1024
  }'
```

--------------------------------

### client.readiness()

Source: https://rag.computer/docs/sdks/typescript

Checks the readiness of the platform for operations.

```APIDOC
## GET /health/ready

### Description
Checks the readiness of the platform for operations.

### Method
GET

### Endpoint
/health/ready
```

--------------------------------

### Check Platform Readiness

Source: https://rag.computer/docs/sdks/python

Verify the readiness of the platform, including its dependencies like Postgres, Redis, and Turbopuffer.

```python
ready = await client.readiness()
```

--------------------------------

### client.admin.settings.list

Source: https://rag.computer/docs/sdks/typescript

Lists system settings.

```APIDOC
## client.admin.settings.list

### Description
Retrieves the current configuration settings for the system. Requires admin privileges.

### Method Signature
```typescript
list(): Promise<any>;
```
```

--------------------------------

### Create a Backup

Source: https://rag.computer/docs/sdks/typescript

Initiate a new backup of the system's data using `client.admin.backups.create`. An optional label can be provided for identification.

```typescript
client.admin.backups.create({ label? })
```

--------------------------------

### Get Collection

Source: https://rag.computer/docs/sdks/typescript

Retrieve a specific collection by its name.

```typescript
client.collections.get(name)
```

--------------------------------

### Get Document

Source: https://rag.computer/docs/sdks/typescript

Retrieve a specific document by its ID from a collection.

```typescript
client.documents.get(collection, documentId)
```

--------------------------------

### client.admin.mcpServers.create

Source: https://rag.computer/docs/sdks/typescript

Creates a new MCP server.

```APIDOC
## client.admin.mcpServers.create

### Description
Creates a new MCP server configuration. Requires admin privileges.

### Method Signature
```typescript
create(options: {
  title: string;
  server_name: string;
  collection?: string;
}): Promise<any>;
```

### Parameters
- **title** (string) - Required - A display title for the MCP server.
- **server_name** (string) - Required - The name of the MCP server.
- **collection** (string) - Optional - The collection associated with this MCP server.
```

--------------------------------

### Get Collection Stats

Source: https://rag.computer/docs/sdks/typescript

Retrieve statistics for a specific collection.

```typescript
client.collections.stats(name)
```

--------------------------------

### client.webhooks.list

Source: https://rag.computer/docs/sdks/typescript

Lists all configured webhooks.

```APIDOC
## client.webhooks.list

### Description
Retrieves a list of all currently configured webhooks.

### Method Signature
```typescript
list(options?: { limit?: number; offset?: number }): Promise<any>;
```

### Parameters
- **limit** (number) - Optional - The maximum number of webhooks to return.
- **offset** (number) - Optional - The number of webhooks to skip before returning results.
```

--------------------------------

### Get Backup

Source: https://rag.computer/docs/sdks/python

Retrieve details for a specific backup by its ID.

```APIDOC
## Get Backup

### Description
Retrieve details for a specific backup by its ID.

### Method
`client.admin.backups.get(backup_id)`

### Parameters
#### Path Parameters
- **backup_id** (string) - Required - The ID of the backup to retrieve.
```

--------------------------------

### Get Webhook

Source: https://rag.computer/docs/sdks/python

Retrieve details for a specific webhook by its ID.

```APIDOC
## Get Webhook

### Description
Retrieve details for a specific webhook by its ID.

### Method
`client.webhooks.get(webhook_id)`

### Parameters
#### Path Parameters
- **webhook_id** (string) - Required - The ID of the webhook to retrieve.
```

--------------------------------

### Build Admin UI Docker Image

Source: https://rag.computer/docs/deployment/docker

Build the Docker image for the static admin UI. Ensure you are in the repository root.

```bash
docker build -f app/Dockerfile -t bigrag-ui .
```

--------------------------------

### Get a bigRAG Collection

Source: https://rag.computer/docs/sdks/python

Retrieve a specific collection by its name.

```python
# Get
collection = await client.collections.get("docs")
```

--------------------------------

### client.admin.backups.create

Source: https://rag.computer/docs/sdks/typescript

Creates a new backup.

```APIDOC
## client.admin.backups.create

### Description
Initiates the creation of a new backup of the system's data. Requires admin privileges.

### Method Signature
```typescript
create(options?: { label?: string }): Promise<any>;
```

### Parameters
- **label** (string) - Optional - A custom label for the backup.
```

--------------------------------

### Get Collection Analytics

Source: https://rag.computer/docs/sdks/typescript

Retrieve analytical data for a specific collection.

```typescript
client.collections.analytics(name)
```

--------------------------------

### client.admin.users.create

Source: https://rag.computer/docs/sdks/typescript

Creates a new user.

```APIDOC
## client.admin.users.create

### Description
Creates a new user account in the system. Requires admin privileges.

### Method Signature
```typescript
create(options: {
  email: string;
  password: string;
  display_name?: string;
  role?: string;
}): Promise<any>;
```

### Parameters
- **email** (string) - Required - The email address for the new user.
- **password** (string) - Required - The password for the new user.
- **display_name** (string) - Optional - The display name for the new user.
- **role** (string) - Optional - The role assigned to the new user.
```

--------------------------------

### Get Document Status

Source: https://rag.computer/docs/sdks/python

Retrieve the processing status of a single document.

```APIDOC
## Get Document Status

### Description
Retrieve the processing status of a single document.

### Method
`client.documents.get(collection_name, document_id)`

### Parameters
#### Path Parameters
- **collection_name** (string) - Required - The name of the collection.
- **document_id** (string) - Required - The ID of the document.
```

--------------------------------

### Get Collection Analytics

Source: https://rag.computer/docs/sdks/python

Retrieve analytical data for a specific collection.

```python
analytics = await client.collections.analytics("docs")
```

--------------------------------

### admin.platform.readiness

Source: https://rag.computer/docs/api-reference/realtime

Checks the readiness of the platform.

```APIDOC
## GET /health/ready

### Description
Checks the readiness of the platform. This endpoint stays open to provide continuous health status.

### Method
GET

### Endpoint
/health/ready
```

--------------------------------

### Get Document Chunks

Source: https://rag.computer/docs/sdks/mcp

Retrieve all chunks associated with a specific document.

```APIDOC
## Get Document Chunks

### Description
Retrieve all chunks associated with a specific document.

### Method
GET

### Endpoint
/v1/collections/{name}/documents/{id}/chunks

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the collection.
- **id** (string) - Required - The ID of the document.
```

--------------------------------

### Get Document

Source: https://rag.computer/docs/sdks/mcp

Retrieve metadata for a single document within a collection.

```APIDOC
## Get Document

### Description
Retrieve metadata for a single document within a collection.

### Method
GET

### Endpoint
/v1/collections/{name}/documents/{id}

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the collection.
- **id** (string) - Required - The ID of the document.
```

--------------------------------

### Create Backup

Source: https://rag.computer/docs/sdks/python

Create a new backup.

```APIDOC
## Create Backup

### Description
Create a new backup.

### Method
`client.admin.backups.create(backup_config)`

### Parameters
#### Request Body
- **backup_config** (object) - Required - Configuration for the backup (e.g., `{"label": "nightly export"}`).
```

--------------------------------

### Create a User

Source: https://rag.computer/docs/sdks/typescript

Add a new user to the system using `client.admin.users.create`. Requires email, password, and optionally display name and role.

```typescript
client.admin.users.create({ email, password, display_name?, role? })
```

--------------------------------

### Get Collection

Source: https://rag.computer/docs/sdks/mcp

Retrieve embedding and chunking configuration for a specific collection.

```APIDOC
## Get Collection

### Description
Retrieve the embedding and chunking configuration for a specific collection.

### Method
GET

### Endpoint
/v1/collections/{name}

### Parameters
#### Path Parameters
- **name** (string) - Required - The name of the collection.
```

--------------------------------

### Recommended Production Settings

Source: https://rag.computer/docs/deployment/production

Essential environment variables for production, focusing on security, logging, and infrastructure configuration.

```dotenv
# Mode
BIGRAG_ENV=prod                     # refuses to boot with insecure defaults

# Sessions
BIGRAG_SESSION_COOKIE_SECURE=true   # HTTPS-only
BIGRAG_SESSION_COOKIE_SAMESITE=lax      # use none when API and admin UI are cross-site
BIGRAG_CORS_ORIGINS=["https://admin.example.com"]
BIGRAG_TRUSTED_PROXIES=["10.0.0.0/8"]  # your reverse-proxy/load-balancer CIDRs

# Logs
BIGRAG_LOG_LEVEL=info
BIGRAG_LOG_FORMAT=json

# Auth is admin accounts + minted bigrag_sk_ keys.
# Bootstrap with POST /v1/auth/setup, then mint service keys at /v1/admin/api-keys.

# Infrastructure
BIGRAG_DATABASE_URL=postgres://user:pass@host:5432/bigrag?sslmode=require
REDIS_PASSWORD=<strong Redis password>
BIGRAG_REDIS_URL=redis://:<url-encoded Redis password>@redis:6379/0
BIGRAG_MASTER_KEY=<generated Fernet key>
BIGRAG_ALLOW_PUBLIC_BIND_IN_PROD=true  # required when the API image binds 0.0.0.0 in prod

```

--------------------------------

### Get Embedding Preset

Source: https://rag.computer/docs/api-reference/embedding-presets

Retrieves a specific embedding preset by its ID.

```APIDOC
## GET /v1/admin/embedding-presets/{id}

### Description
Retrieves the details of a specific embedding preset.

### Method
GET

### Endpoint
/v1/admin/embedding-presets/{id}

### Parameters
#### Path Parameters
- **id** (string) - Required - The unique identifier of the embedding preset to retrieve.

### Response
#### Success Response (200)
- **id** (string) - The unique identifier for the preset.
- **name** (string) - The name of the preset.
- **provider** (string) - The embedding provider.
- **model** (string) - The embedding model used.
- **dimension** (integer) - The dimension of the embeddings.
- **base_url** (string) - The base URL for the embedding provider.

### Response Example
{
  "id": "preset-123",
  "name": "OpenAI Ada 002",
  "provider": "openai",
  "model": "text-embedding-ada-002",
  "dimension": 1536,
  "base_url": "https://api.openai.com/v1"
}
```

--------------------------------

### client.admin.access.overview

Source: https://rag.computer/docs/sdks/typescript

Provides an overview of access events.

```APIDOC
## client.admin.access.overview

### Description
Returns a summary or overview of access-related events, potentially aggregated over a specified period. Requires admin privileges.

### Method Signature
```typescript
overview(options?: { windowDays?: number }): Promise<any>;
```

### Parameters
- **windowDays** (number) - Optional - The number of past days to include in the overview.
```

--------------------------------

### Get Usage Rollup

Source: https://rag.computer/docs/sdks/python

Retrieve usage data aggregated over a specified period.

```APIDOC
## Get Usage Rollup

### Description
Retrieve usage data aggregated over a specified period.

### Method
`client.get_usage(window_days)`

### Parameters
#### Query Parameters
- **window_days** (integer) - Required - The number of days to roll up usage data for.
```

--------------------------------

### Get Platform Stats

Source: https://rag.computer/docs/sdks/python

Retrieve statistics about the platform's performance and usage.

```APIDOC
## Get Platform Stats

### Description
Retrieve statistics about the platform's performance and usage.

### Method
`client.get_stats()`
```

--------------------------------

### Readiness Check

Source: https://rag.computer/docs/sdks/python

Check the readiness of the platform, including its dependencies like Postgres, Redis, and embedding providers.

```APIDOC
## Readiness Check

### Description
Check the readiness of the platform, including its dependencies like Postgres, Redis, and embedding providers.

### Method
`client.readiness()`
```

--------------------------------

### client.admin.apiKeys.create

Source: https://rag.computer/docs/sdks/typescript

Creates a new API key.

```APIDOC
## client.admin.apiKeys.create

### Description
Generates a new API key with specified name, expiration, scopes, and collection access. Requires admin privileges.

### Method Signature
```typescript
create(options: {
  name: string;
  expires_at?: string;
  scopes?: string[];
  collection?: string;
}): Promise<any>;
```

### Parameters
- **name** (string) - Required - A descriptive name for the API key.
- **expires_at** (string) - Optional - The expiration date/time for the API key (ISO format).
- **scopes** (string[]) - Optional - An array of scopes to grant to the API key.
- **collection** (string) - Optional - The specific collection this API key can access.
```

--------------------------------

### Get Document Chunks

Source: https://rag.computer/docs/sdks/typescript

Retrieve the chunks associated with a specific document, with pagination support.

```typescript
client.documents.getChunks(collection, documentId, { limit?, offset? }?)
```

--------------------------------

### List Embedding Models

Source: https://rag.computer/docs/sdks/python

Get a list of available embedding models supported by the platform.

```APIDOC
## List Embedding Models

### Description
Get a list of available embedding models supported by the platform.

### Method
`client.list_embedding_models()`
```

--------------------------------

### Create an MCP Server

Source: https://rag.computer/docs/sdks/typescript

Register a new MCP server with the system using `client.admin.mcpServers.create`. Requires a title, server name, and optionally a collection.

```typescript
client.admin.mcpServers.create({ title, server_name, collection? })
```

--------------------------------

### client.admin.vectorStorage.overview

Source: https://rag.computer/docs/sdks/typescript

Provides an overview of vector storage usage.

```APIDOC
## client.admin.vectorStorage.overview

### Description
Returns statistics and information about the current state and usage of the vector storage. Requires admin privileges.

### Method Signature
```typescript
overview(): Promise<any>;
```
```

--------------------------------

### Batch Get Document Status

Source: https://rag.computer/docs/sdks/python

Retrieve the processing statuses for multiple documents in a collection.

```APIDOC
## Batch Get Document Status

### Description
Retrieve the processing statuses for multiple documents in a collection.

### Method
`client.documents.batch_get_status(collection_name, document_ids)`

### Parameters
#### Path Parameters
- **collection_name** (string) - Required - The name of the collection.

#### Request Body
- **document_ids** (list of strings) - Required - A list of document IDs.
```

--------------------------------

### Get Backup Details

Source: https://rag.computer/docs/sdks/python

Retrieve detailed information about a specific backup using its ID.

```python
backup = await client.admin.backups.get(backup["id"])
```

--------------------------------

### Get Document

Source: https://rag.computer/docs/api-reference/documents

Retrieve details of a specific document. Requires `document:read` permission.

```APIDOC
## GET /v1/collections/{collection_name}/documents/{document_id}

### Description
Retrieve details of a specific document.

### Method
GET

### Endpoint
`/v1/collections/{collection_name}/documents/{document_id}`

### Parameters
#### Path Parameters
- **collection_name** (string) - Required - The name of the collection containing the document.
- **document_id** (string) - Required - The unique identifier for the document.

### Response
#### Success Response (200)
- **document_id** (string) - The unique identifier for the document.
- **name** (string) - The name of the document.
- **status** (string) - The current status of the document.
- **metadata** (object) - Metadata associated with the document.
```

--------------------------------

### Log In

Source: https://rag.computer/docs/sdks/typescript

Authenticate a user by providing their email and password using `client.auth.login`. This establishes a user session.

```typescript
client.auth.login({ email, password })
```

--------------------------------

### Stream Realtime Platform Readiness Events

Source: https://rag.computer/docs/sdks/python

Asynchronously monitor real-time events indicating the readiness status of the platform components.

```python
async for event in client.admin.realtime.platform_readiness():
    if event["type"] == "snapshot":
        print(event["payload"])
```

--------------------------------

### Get bigRAG Collection Stats

Source: https://rag.computer/docs/sdks/python

Retrieve statistics for a specific collection, such as document count and size.

```python
# Stats
stats = await client.collections.stats("docs")
```

--------------------------------

### Create Backup

Source: https://rag.computer/docs/sdks/python

Initiate a new backup operation, optionally providing a label for identification.

```python
backup = await client.admin.backups.create({"label": "nightly export"})
```

--------------------------------

### Get Document Status

Source: https://rag.computer/docs/api-reference/documents

Retrieve the processing status of a document. Requires `document:read` permission.

```APIDOC
## GET /v1/collections/{collection_name}/documents/{document_id}/status

### Description
Retrieve the processing status of a document.

### Method
GET

### Endpoint
`/v1/collections/{collection_name}/documents/{document_id}/status`

### Parameters
#### Path Parameters
- **collection_name** (string) - Required - The name of the collection containing the document.
- **document_id** (string) - Required - The unique identifier for the document.

### Response
#### Success Response (200)
- **document_id** (string) - The unique identifier for the document.
- **status** (string) - The current processing status of the document (e.g., `processing`, `completed`, `failed`).
```

--------------------------------

### Update Admin Settings

Source: https://rag.computer/docs/sdks/python

Modify administrative settings, for example, to update trusted proxy configurations.

```python
await client.admin.settings.update({"values": {"trusted_proxies": ["10.0.0.0/8"]}})
```

--------------------------------

### Get a Specific Backup

Source: https://rag.computer/docs/sdks/typescript

Retrieve details about a particular backup using `client.admin.backups.get`. Requires the backup ID.

```typescript
client.admin.backups.get(backupId)
```

--------------------------------

### List Admin Settings

Source: https://rag.computer/docs/sdks/python

Retrieve the current administrative settings for the platform.

```python
settings = await client.admin.settings.list()
```

--------------------------------

### Get Document Elements

Source: https://rag.computer/docs/sdks/typescript

Retrieve the elements (e.g., paragraphs, sentences) of a specific document, with pagination support.

```typescript
client.documents.getElements(collection, documentId, { limit?, offset? }?)
```

--------------------------------

### Get Question Suggestions

Source: https://rag.computer/docs/sdks/python

Retrieve suggested questions for a given collection. This can help users explore the data further.

```python
# Question suggestions
suggestions = await client.chat.get_question_suggestions("docs")
fresh = await client.chat.generate_question_suggestions({"collection": "docs"})
```

--------------------------------

### client.webhooks.create

Source: https://rag.computer/docs/sdks/typescript

Creates a new webhook subscription.

```APIDOC
## client.webhooks.create

### Description
Registers a new webhook to receive event notifications. You can specify which events and collections the webhook should monitor.

### Method Signature
```typescript
create(options: {
  url: string;
  events: string[];
  collections?: string[];
}): Promise<any>;
```

### Parameters
- **url** (string) - Required - The URL to send webhook events to.
- **events** (string[]) - Required - An array of event names to subscribe to (e.g., `document.ready`, `collection.truncated`).
- **collections** (string[]) - Optional - An array of collection names to filter events by.
```

--------------------------------

### Get Preferences

Source: https://rag.computer/docs/api-reference/preferences

Retrieves the current user's preferences. For new users, an empty data object is returned.

```APIDOC
## GET /v1/auth/preferences

### Description
Retrieves the current user's preferences. For new users, an empty data object is returned.

### Method
GET

### Endpoint
/v1/auth/preferences

### Response
#### Success Response (200)
- **data** (object) - The user's preferences object. Example: `{"sidebar_collapsed": false, "default_collection": "knowledge_base", "chat": { "search_mode": "hybrid", "top_k": 10 }}`

#### Response Example
```json
{
  "data": {
    "sidebar_collapsed": false,
    "default_collection": "knowledge_base",
    "chat": { "search_mode": "hybrid", "top_k": 10 }
  }
}
```
```

--------------------------------

### Connect to Realtime

Source: https://rag.computer/docs/sdks/typescript

Establish a connection to the real-time service.

```typescript
client.realtime.connect()
```

--------------------------------

### Realtime Platform Readiness

Source: https://rag.computer/docs/sdks/python

Stream real-time events indicating the platform's readiness status.

```APIDOC
## Realtime Platform Readiness

### Description
Stream real-time events indicating the platform's readiness status.

### Method
`client.admin.realtime.platform_readiness()`
```

--------------------------------

### client.admin.mcpServers.list

Source: https://rag.computer/docs/sdks/typescript

Lists MCP servers.

```APIDOC
## client.admin.mcpServers.list

### Description
Retrieves a list of all configured MCP (Multi-Collection Processing) servers. Requires admin privileges.

### Method Signature
```typescript
list(): Promise<any>;
```
```

--------------------------------

### client.auth.login

Source: https://rag.computer/docs/sdks/typescript

Logs in a user with email and password.

```APIDOC
## client.auth.login

### Description
Authenticates a user using their email and password.

### Method Signature
```typescript
login(options: { email: string; password: string }): Promise<any>;
```

### Parameters
- **email** (string) - Required - The user's email address.
- **password** (string) - Required - The user's password.
```

--------------------------------

### Get User Preferences

Source: https://rag.computer/docs/sdks/typescript

Retrieve the current user's preferences using `client.auth.preferences`. This allows inspection of user-specific settings.

```typescript
client.auth.preferences()
```