### Get System Information (Bash)

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves current system information, including version, vector database, LLM provider, and embedding provider details. Requires an API key for authentication.

```bash
curl -X GET http://localhost:3001/v1/system \
  -H "Authorization: Bearer <api-key>"
```

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

### Setup AnythingLLM Project Dependencies

Source: https://github.com/mintplex-labs/anything-llm/blob/master/BARE_METAL.md

Installs all necessary dependencies for running AnythingLLM in production and for debugging. This command should be run after cloning the repository.

```bash
cd anything-llm
yarn setup
```

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

### Get System Information

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves current system information, including version, providers, and models.

```APIDOC
## GET /v1/system

### Description
Fetches general information about the running AnythingLLM instance.

### Method
GET

### Endpoint
/v1/system

### Response
#### Success Response (200)
- **version** (string) - The current version of AnythingLLM.
- **vectorDB** (string) - The configured vector database.
- **llmProvider** (string) - The configured LLM provider.
- **embeddingProvider** (string) - The configured embedding provider.
- **embeddingModel** (string) - The configured embedding model.

#### Response Example
```json
{
  "version": "1.9.0",
  "vectorDB": "lancedb",
  "llmProvider": "openai",
  "embeddingProvider": "openai",
  "embeddingModel": "text-embedding-3-small"
}
```
```

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

### Example Script to Update AnythingLLM

Source: https://github.com/mintplex-labs/anything-llm/blob/master/BARE_METAL.md

An example bash script to automate the process of updating AnythingLLM. It pulls the latest code, rebuilds the frontend, restarts services, and installs dependencies.

```bash
#!/bin/bash

cd $HOME/anything-llm &&\
git checkout . &&\
git pull origin master &&\
echo "HEAD pulled to commit $(git log -1 --pretty=format:"%h" | tail -n 1)"

echo "Freezing current ENVs"
curl -I "http://localhost:3001/api/env-dump" | head -n 1|cut -d$' ' -f2

echo "Rebuilding Frontend"
cd $HOME/anything-llm/frontend && yarn && yarn build && cd $HOME/anything-llm

echo "Copying to Server Public"
rm -rf server/public
cp -r frontend/dist server/public

echo "Killing node processes"
pkill node

echo "Installing collector dependencies"
cd $HOME/anything-llm/collector && yarn

echo "Installing server dependencies & running migrations"
cd $HOME/anything-llm/server && yarn
cd $HOME/anything-llm/server && npx prisma migrate deploy --schema=./prisma/schema.prisma
cd $HOME/anything-llm/server && npx prisma generate

echo "Booting up services."
truncate -s 0 /logs/server.log # Or any other log file location.
truncate -s 0 /logs/collector.log

cd $HOME/anything-llm/server
(NODE_ENV=production node index.js) &> /logs/server.log &

cd $HOME/anything-llm/collector
(NODE_ENV=production node index.js) &> /logs/collector.log &

```

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

### Run Dockerized AnythingLLM on Windows

Source: https://github.com/mintplex-labs/anything-llm/blob/master/docker/HOW_TO_USE_DOCKER.md

Starts the AnythingLLM Docker container on Windows using PowerShell. This script ensures the storage directory and .env file exist, mounts them to the container for persistent storage, and maps the necessary ports. It's designed to handle Windows-specific path conventions.

```powershell
# Run this in powershell terminal
$env:STORAGE_LOCATION="$HOME\Documents\anythingllm"; `
If(!(Test-Path $env:STORAGE_LOCATION)) {New-Item $env:STORAGE_LOCATION -ItemType Directory}; `
If(!(Test-Path "$env:STORAGE_LOCATION\.env")) {New-Item "$env:STORAGE_LOCATION\.env" -ItemType File}; `
docker run -d -p 3001:3001 `
--cap-add SYS_ADMIN `
-v "$env:STORAGE_LOCATION`:/app/server/storage" `
-v "$env:STORAGE_LOCATION\.env:/app/server/.env" `
-e STORAGE_DIR="/app/server/storage" `
mintplexlabs/anythingllm;
```

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

### Server Environment Variables Configuration (.env.development)

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Example `.env.development` file for configuring AnythingLLM server settings. It includes variables for server port, JWT secret, LLM and embedding provider configurations (OpenAI, Ollama), vector database options (lancedb, pinecone), and authentication settings.

```bash
# Server
SERVER_PORT=3001
JWT_SECRET=your-secret-key-min-32-chars

# LLM Provider
LLM_PROVIDER=openai
OPEN_AI_KEY=sk-...
OPEN_MODEL_PREF=gpt-4
OPEN_AI_TEMPERATURE=0.7

# Embedding Provider
EMBEDDING_ENGINE=openai
EMBEDDING_MODEL_PREF=text-embedding-3-small

# Vector Database
VECTOR_DB=lancedb

# Document Processor
COLLECTOR_API=http://localhost:8888

# Optional: Use local models
# LLM_PROVIDER=ollama
# OLLAMA_BASE_PATH=http://localhost:11434
# OLLAMA_MODEL_PREF=llama2

# Optional: External Vector DB
# VECTOR_DB=pinecone
# PINECONE_API_KEY=...
# PINECONE_INDEX=anythingllm

# Privacy
DISABLE_TELEMETRY=true

# Authentication (single-user)
AUTH_TOKEN=my-secure-password

# Multi-user mode

```

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

### Install and Enable Nginx on Amazon Linux

Source: https://github.com/mintplex-labs/anything-llm/blob/master/cloud-deployments/aws/cloudformation/aws_https_instructions.md

Installs the Nginx web server and enables it to start automatically on boot, then starts the service. This is a prerequisite for configuring Nginx as a reverse proxy.

```bash
sudo yum install nginx -y
sudo systemctl enable nginx && sudo systemctl start nginx
```

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

### Configure AnythingLLM with Docker Compose

Source: https://github.com/mintplex-labs/anything-llm/blob/master/docker/HOW_TO_USE_DOCKER.md

Defines the AnythingLLM service using Docker Compose. This YAML file specifies the Docker image, container name, port mappings, capabilities, environment variables for LLM and embedding configurations, and volume mounts for persistent storage. It allows for a more complex and declarative setup.

```yaml
version: '3.8'
services:
  anythingllm:
    image: mintplexlabs/anythingllm
    container_name: anythingllm
    ports:
    - "3001:3001"
    cap_add:
      - SYS_ADMIN
    environment:
    # Adjust for your environment
      - STORAGE_DIR=/app/server/storage
      - JWT_SECRET="make this a large list of random numbers and letters 20+"
      - LLM_PROVIDER=ollama
      - OLLAMA_BASE_PATH=http://127.0.0.1:11434
      - OLLAMA_MODEL_PREF=llama2
      - OLLAMA_MODEL_TOKEN_LIMIT=4096
      - EMBEDDING_ENGINE=ollama
      - EMBEDDING_BASE_PATH=http://127.0.0.1:11434
      - EMBEDDING_MODEL_PREF=nomic-embed-text:latest
      - EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
      - VECTOR_DB=lancedb
      - WHISPER_PROVIDER=local
      - TTS_PROVIDER=native
      - PASSWORDMINCHAR=8
      # Add any other keys here for services or settings
      # you can find in the docker/.env.example file
    volumes:
      - anythingllm_storage:/app/server/storage
    restart: always

volumes:
  anythingllm_storage:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /path/on/local/disk
```

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

### Get Workspace Details (Bash)

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Fetches detailed information for a specific workspace, identified by its slug. Requires JWT authentication. Includes details about the workspace's documents and associated threads.

```bash
curl -X GET http://localhost:3001/api/workspace/product-docs \
  -H "Authorization: Bearer <jwt-token>"

# Response
{
  "workspace": {
    "id": 5,
    "name": "Product Documentation",
    "slug": "product-docs",
    "vectorTag": "product-docs",
    "documents": [
      {
        "id": "doc-123",
        "name": "user-guide.pdf",
        "metadata": {
          "title": "User Guide",
          "pages": 45
        },
        "pinned": false
      }
    ],
    "threads": []
  }
}
```

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

### OpenAI-Compatible Models List

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves a list of available OpenAI-compatible models.

```APIDOC
## GET /v1/openai/models

### Description
Retrieves a list of available OpenAI-compatible models that can be used with the AnythingLLM API.

### Method
GET

### Endpoint
/v1/openai/models

### Parameters
#### Query Parameters
- **Authorization** (string) - Required - Bearer token for authentication.

### Response
#### Success Response (200)
- **data** (array) - A list of model objects.
  - **id** (string) - The unique identifier for the model.
  - **object** (string) - The type of object, should be 'model'.
  - **created** (integer) - Timestamp of model creation.
  - **owned_by** (string) - The owner of the model.

#### Response Example
```json
{
  "data": [
    {
      "id": "product-docs",
      "object": "model",
      "created": 1737012345,
      "owned_by": "anythingllm"
    },
    {
      "id": "support-kb",
      "object": "model",
      "created": 1737012346,
      "owned_by": "anythingllm"
    }
  ],
  "object": "list"
}
```
```

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

### Enable Multi-User Mode

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Enables multi-user mode by setting up the initial administrator credentials.

```APIDOC
## POST /api/system/enable-multi-user

### Description
Initializes multi-user functionality by setting the administrator's username and password.

### Method
POST

### Endpoint
/api/system/enable-multi-user

### Parameters
#### Request Body
- **username** (string) - Required - The email address for the administrator account.
- **password** (string) - Required - The password for the administrator account.

### Request Example
```json
{
  "username": "admin@company.com",
  "password": "secureAdminPassword"
}
```

### Response
#### Success Response (200)
- **success** (boolean) - Indicates if the operation was successful.
- **message** (string) - A confirmation message.

#### Response Example
```json
{
  "success": true,
  "message": "Multi-user mode enabled"
}
```
```

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

### Set Welcome Messages

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Configures the welcome messages displayed to users.

```APIDOC
## POST /api/system/set-welcome-messages

### Description
Sets a list of welcome messages that can be displayed to users upon interaction.

### Method
POST

### Endpoint
/api/system/set-welcome-messages

### Parameters
#### Request Body
- **messages** (array of strings) - Required - A list of welcome messages.

### Request Example
```json
{
  "messages": [
    "How can I help you today?",
    "What would you like to know?",
    "Ask me anything about our products!"
  ]
}
```

### Response
#### Success Response (200)
- **success** (boolean) - Indicates if the operation was successful.
- **welcomeMessages** (array of strings) - The newly set welcome messages.

#### Response Example
```json
{
  "success": true,
  "welcomeMessages": ["How can I help you today?", ...]
}
```
```

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

### Frontend React Integration

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Provides examples for integrating AnythingLLM chat functionality into a React application, including initializing chat with a workspace and streaming responses.

```APIDOC
## Frontend React Integration

### Initialize Chat with Workspace

This section demonstrates how to fetch workspace details and chat history using the `Workspace` model in React.

```javascript
import { useState, useEffect } from 'react';
import Workspace from '@/models/workspace';

function WorkspaceChat({ slug }) {
  const [workspace, setWorkspace] = useState(null);
  const [chatHistory, setChatHistory] = useState([]);
  const [loading, setLoading] = useState(true);

  useEffect(() => {
    async function fetchWorkspace() {
      try {
        const ws = await Workspace.bySlug(slug);
        const history = await Workspace.chatHistory(slug);
        setWorkspace(ws.workspace);
        setChatHistory(history);
      } catch (error) {
        console.error('Failed to load workspace:', error);
      } finally {
        setLoading(false);
      }
    }
    fetchWorkspace();
  }, [slug]);

  if (loading) return <div>Loading workspace...</div>;

  return (
    <div>
      <h1>{workspace.name}</h1>
      <ChatContainer
        workspace={workspace}
        history={chatHistory}
      />
    </div>
  );
}
```

### Stream Chat Response in React

This section shows how to send messages and receive streaming responses from the chat model in a React component.

```javascript
import { useEffect, useState } from 'react';
import Workspace from '@/models/workspace';

function ChatInterface({ workspaceSlug }) {
  const [messages, setMessages] = useState([]);
  const [streaming, setStreaming] = useState(false);
  const [currentResponse, setCurrentResponse] = useState('');

  const sendMessage = async (message) => {
    setStreaming(true);
    setCurrentResponse('');

    setMessages(prev => [...prev, { role: 'user', content: message }]);

    try {
      await Workspace.streamChat(
        workspaceSlug,
        message,
        'chat',
        (chunk) => {
          if (chunk.type === 'textResponseChunk') {
            setCurrentResponse(prev => prev + chunk.textResponse);
          }
          if (chunk.type === 'textResponse' && chunk.close) {
            setMessages(prev => [...prev, {
              role: 'assistant',
              content: currentResponse,
              sources: chunk.sources,
              chatId: chunk.chatId
            }]);
            setCurrentResponse('');
            setStreaming(false);
          }
        },
        () => {
          setStreaming(false);
        }
      );
    } catch (error) {
      console.error('Chat error:', error);
      setStreaming(false);
    }
  };

  return (
    <div className="chat-interface">
      <div className="messages">
        {messages.map((msg, idx) => (
          <div key={idx} className={`message ${msg.role}`}>
            {msg.content}
            {msg.sources && (
              <div className="sources">
                {msg.sources.map((src, i) => (
                  <span key={i}>{src.title}</span>
                ))}
              </div>
            )}
          </div>
        ))}
        {streaming && (
          <div className="message assistant streaming">
            {currentResponse}
            <span className="cursor">▊</span>
          </div>
        )}
      </div>
      <ChatInput onSend={sendMessage} disabled={streaming} />
    </div>
  );
}
```
```

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

### Create Workspace

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Creates a new workspace for organizing documents and conversations.

```APIDOC
## POST /v1/workspace/new

### Description
Creates a new workspace within the AnythingLLM application. Workspaces are used to organize documents and maintain separate contexts for different knowledge bases.

### Method
POST

### Endpoint
/v1/workspace/new

### Parameters
#### Header Parameters
- **Authorization** (string) - Required - Bearer token for authentication.
- **Content-Type** (string) - Required - Application JSON.

#### Request Body
- **name** (string) - Required - The display name for the new workspace.
- **slug** (string) - Required - A unique identifier for the workspace (URL-friendly).

### Request Example
```json
{
  "name": "Customer Support KB",
  "slug": "support-kb"
}
```

### Response
#### Success Response (200)
- **workspace** (object) - Details of the newly created workspace.
  - **id** (integer) - The unique identifier for the workspace.
  - **name** (string) - The display name of the workspace.
  - **slug** (string) - The unique slug of the workspace.

#### Response Example
```json
{
  "workspace": {
    "id": 7,
    "name": "Customer Support KB",
    "slug": "support-kb"
  }
}
```
```

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

### Process Raw Text using cURL

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

This example demonstrates processing raw text content directly. It requires the text content and optional metadata like title, description, and author. The API will create a document from the provided text and return its details, including a filename and content information.

```bash
curl -X POST http://localhost:8888/process-raw-text \
  -H "Content-Type: application/json" \
  -d '{
    "textContent": "This is my important note that I want to add to the knowledge base.",
    "metadata": {
      "title": "Quick Note",
      "description": "Important information",
      "author": "John Doe"
    }
  }'

# Response
{
  "success": true,
  "filename": "quick-note-1737012345.txt",
  "documents": [
    {
      "id": "uuid-789",
      "pageContent": "This is my important note...",
      "title": "Quick Note",
      "token_count_estimate": 15
    }
  ]
}
```

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

### Update System Settings

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Allows administrators to update environment variables and system configurations.

```APIDOC
## POST /api/system/update-env

### Description
Updates system environment variables such as LLM provider, API keys, vector database, and embedding models.

### Method
POST

### Endpoint
/api/system/update-env

### Parameters
#### Request Body
- **LLMProvider** (string) - Optional - The preferred Language Model provider.
- **OpenAiKey** (string) - Optional - Your OpenAI API key.
- **OpenAiModelPref** (string) - Optional - The preferred OpenAI model.
- **VectorDB** (string) - Optional - The preferred vector database.
- **EmbeddingEngine** (string) - Optional - The preferred embedding engine.
- **EmbeddingModelPref** (string) - Optional - The preferred embedding model.

### Request Example
```json
{
  "LLMProvider": "openai",
  "OpenAiKey": "sk-...",
  "OpenAiModelPref": "gpt-4",
  "VectorDB": "lancedb",
  "EmbeddingEngine": "openai",
  "EmbeddingModelPref": "text-embedding-3-small"
}
```

### Response
#### Success Response (200)
- **newValues** (object) - Contains the updated settings. Note: sensitive keys like API keys are returned as booleans indicating their presence.
- **error** (object | null) - Contains error information if any occurred.

#### Response Example
```json
{
  "newValues": {
    "LLMProvider": "openai",
    "OpenAiKey": true,
    "OpenAiModelPref": "gpt-4"
  },
  "error": null
}
```
```

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

### GitHub Repository Integration

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Integrates a GitHub repository by cloning its content and preparing it for embedding.

```APIDOC
## POST /ext/github-repo

### Description
Clones a specified GitHub repository and processes its files to generate embeddings. You can configure which files and directories to ignore during the process.

### Method
POST

### Endpoint
/ext/github-repo

### Parameters
#### Header Parameters
- **Content-Type** (string) - Required - Application JSON.

#### Request Body
- **repo** (string) - Required - The GitHub repository in the format 'owner/repository'.
- **branch** (string) - Optional - The specific branch to clone (defaults to 'main').
- **accessToken** (string) - Optional - A GitHub Personal Access Token for private repositories or increased rate limits.
- **ignorePaths** (array) - Optional - A list of file paths or glob patterns to ignore during processing.

### Request Example
```json
{
  "repo": "owner/repository",
  "branch": "main",
  "accessToken": "ghp_...",
  "ignorePaths": [".github/", "node_modules/", "*.test.js"]
}
```

### Response
#### Success Response (200)
- **success** (boolean) - Indicates if the repository integration was successful.
- **data** (object) - Information about the processed repository.
  - **files** (integer) - The number of files processed.
  - **destination** (string) - An identifier for the repository content.

#### Response Example
```json
{
  "success": true,
  "data": {
    "files": 156,
    "destination": "github-owner-repository-main"
  }
}
```
```

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

### User Management (Multi-User Mode)

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

APIs for managing users when multi-user mode is enabled.

```APIDOC
## POST /api/admin/users/new

### Description
Creates a new user account in the system.

### Method
POST

### Endpoint
/api/admin/users/new

### Parameters
#### Request Body
- **username** (string) - Required - The username (email) for the new user.
- **password** (string) - Required - The initial password for the new user.
- **role** (string) - Optional - The role assigned to the user (e.g., 'default', 'manager', 'admin'). Defaults to 'default'.

### Request Example
```json
{
  "username": "jane.smith@company.com",
  "password": "initialPassword123",
  "role": "default"
}
```

### Response
#### Success Response (200)
- **user** (object) - Details of the newly created user.
  - **id** (integer) - The unique identifier for the user.
  - **username** (string) - The username of the user.
  - **role** (string) - The assigned role of the user.
  - **createdAt** (string) - The timestamp when the user was created.
- **error** (object | null) - Contains error information if any occurred.

#### Response Example
```json
{
  "user": {
    "id": 5,
    "username": "jane.smith@company.com",
    "role": "default",
    "createdAt": "2025-01-15T12:00:00.000Z"
  },
  "error": null
}
```
```

```APIDOC
## GET /api/admin/users

### Description
Retrieves a list of all users in the system.

### Method
GET

### Endpoint
/api/admin/users

### Response
#### Success Response (200)
- **users** (array of objects) - A list containing details of each user.
  - **id** (integer) - The unique identifier for the user.
  - **username** (string) - The username of the user.
  - **role** (string) - The assigned role of the user.
  - **createdAt** (string) - The timestamp when the user was created.

#### Response Example
```json
{
  "users": [
    {
      "id": 1,
      "username": "admin@company.com",
      "role": "admin",
      "createdAt": "2025-01-01T00:00:00.000Z"
    },
    {
      "id": 5,
      "username": "jane.smith@company.com",
      "role": "default",
      "createdAt": "2025-01-15T12:00:00.000Z"
    }
  ]
}
```
```

```APIDOC
## POST /api/admin/user/{userId}

### Description
Updates the role of a specific user.

### Method
POST

### Endpoint
/api/admin/user/{userId}

### Parameters
#### Path Parameters
- **userId** (integer) - Required - The ID of the user to update.

#### Request Body
- **role** (string) - Required - The new role to assign to the user (e.g., 'manager', 'default').

### Request Example
```json
{
  "role": "manager"
}
```

### Response
#### Success Response (200)
- **success** (boolean) - Indicates if the operation was successful.
- **user** (object) - Details of the updated user.
  - **id** (integer) - The unique identifier for the user.
  - **username** (string) - The username of the user.
  - **role** (string) - The updated role of the user.

#### Response Example
```json
{
  "success": true,
  "user": {
    "id": 5,
    "username": "jane.smith@company.com",
    "role": "manager"
  }
}
```
```

```APIDOC
## POST /api/admin/workspace-users

### Description
Assigns or unassigns users to specific workspaces.

### Method
POST

### Endpoint
/api/admin/workspace-users

### Parameters
#### Request Body
- **workspaceId** (integer) - Required - The ID of the workspace.
- **userIds** (array of integers) - Required - A list of user IDs to assign to the workspace.

### Request Example
```json
{
  "workspaceId": 5,
  "userIds": [5]
}
```

### Response
#### Success Response (200)
- **success** (boolean) - Indicates if the operation was successful.
- **message** (string) - A confirmation message.

#### Response Example
```json
{
  "success": true,
  "message": "Workspace users updated"
}
```
```

```APIDOC
## POST /api/admin/invite/new

### Description
Creates a new invitation link for users to join specific workspaces.

### Method
POST

### Endpoint
/api/admin/invite/new

### Parameters
#### Request Body
- **workspaceIds** (array of integers) - Required - A list of workspace IDs the invited user will have access to.
- **role** (string) - Optional - The default role assigned to users who accept the invite. Defaults to 'default'.

### Request Example
```json
{
  "workspaceIds": [5, 6],
  "role": "default"
}
```

### Response
#### Success Response (200)
- **invite** (object) - Details of the created invitation.
  - **id** (integer) - The unique identifier for the invite.
  - **code** (string) - The invitation code.
  - **status** (string) - The status of the invite (e.g., 'active').
  - **createdAt** (string) - The timestamp when the invite was created.
- **error** (object | null) - Contains error information if any occurred.

#### Response Example
```json
{
  "invite": {
    "id": 3,
    "code": "abc123def456",
    "status": "active",
    "createdAt": "2025-01-15T12:30:00.000Z"
  },
  "error": null
}
```

**Note**: Share the link `http://localhost:3001/accept-invite/{invite.code}` with users.
```

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

### AI Agent Configuration

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Configure AI agent settings for a workspace, including mode, provider, and model.

```APIDOC
## POST /api/workspace/{workspace_slug}/update

### Description
Updates the AI agent configuration for a specific workspace. This allows you to define how the AI agent operates, including its interaction mode, the LLM provider, and the specific model to use.

### Method
POST

### Endpoint
/api/workspace/{workspace_slug}/update

### Parameters
#### Path Parameters
- **workspace_slug** (string) - Required - The slug of the workspace to configure.

#### Header Parameters
- **Authorization** (string) - Required - JWT token for authentication.
- **Content-Type** (string) - Required - Application JSON.

#### Request Body
- **agentMode** (string) - Optional - The interaction mode for the agent (e.g., 'chat').
- **agentProvider** (string) - Optional - The LLM provider to use (e.g., 'openai').
- **agentModel** (string) - Optional - The specific model to use (e.g., 'gpt-4').

### Request Example
```json
{
  "agentMode": "chat",
  "agentProvider": "openai",
  "agentModel": "gpt-4"
}
```
```

```APIDOC
## POST /api/workspace/{workspace_slug}/stream-chat

### Description
Initiates a chat with the AI agent in a specific workspace, streaming the response back to the client. This endpoint is suitable for real-time conversational interactions.

### Method
POST

### Endpoint
/api/workspace/{workspace_slug}/stream-chat

### Parameters
#### Path Parameters
- **workspace_slug** (string) - Required - The slug of the workspace to chat with.

#### Header Parameters
- **Authorization** (string) - Required - JWT token for authentication.
- **Content-Type** (string) - Required - Application JSON.

#### Request Body
- **message** (string) - Required - The user's message to the AI agent.
- **mode** (string) - Optional - The mode of interaction (e.g., 'chat').

### Request Example
```json
{
  "message": "Search the web for the latest version and compare with our docs",
  "mode": "chat"
}
```
```

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

### Developer API (v1) - OpenAI Compatible

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Provides an OpenAI-compatible API endpoint for chat completions.

```APIDOC
## POST /v1/openai/chat/completions

### Description
An OpenAI-compatible endpoint for generating chat completions. AnythingLLM routes requests to the configured LLM provider, with each workspace acting as a distinct 'model'.

### Method
POST

### Endpoint
/v1/openai/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The identifier for the model (often a workspace name).
- **messages** (array of objects) - Required - A list of message objects in the chat conversation.
  - **role** (string) - Role of the message sender ('user', 'assistant', 'system').
  - **content** (string) - The content of the message.
- **temperature** (number) - Optional - Controls randomness. Lower values make output more focused and deterministic.
- **stream** (boolean) - Optional - Whether to stream the response. Defaults to false.

### Request Example
```json
{
  "model": "product-docs",
  "messages": [
    {
      "role": "user",
      "content": "What are the installation requirements?"
    }
  ],
  "temperature": 0.7,
  "stream": false
}
```

### Response
(Response format follows OpenAI's Chat Completions API structure.)

#### Success Response (200)
- **choices** (array) - A list of generated completion choices.
- **usage** (object) - Information about token usage.

#### Response Example
```json
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "product-docs",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "To install AnythingLLM, you need Docker..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}
```
```

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

### Configure QDrant Environment Variables

Source: https://github.com/mintplex-labs/anything-llm/blob/master/server/utils/vectorDbProviders/qdrant/QDRANT_SETUP.md

These environment variables are used to configure the connection to a QDrant vector database. Ensure these are set in your `.env.development` file or defined at runtime for development mode.

```dotenv
VECTOR_DB="qdrant"
QDRANT_ENDPOINT="https://<YOUR_CLOUD_INSTANCE_URL>.qdrant.io:6333"
QDRANT_API_KEY="abc...123xyz"
```

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

### List OpenAI-Compatible Models

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves a list of available OpenAI-compatible models hosted by the AnythingLLM instance. This requires an API key for authorization.

```bash
curl -X GET http://localhost:3001/v1/openai/models \
  -H "Authorization: Bearer <api-key>"

# Response
{
  "data": [
    {
      "id": "product-docs",
      "object": "model",
      "created": 1737012345,
      "owned_by": "anythingllm"
    },
    {
      "id": "support-kb",
      "object": "model",
      "created": 1737012346,
      "owned_by": "anythingllm"
    }
  ],
  "object": "list"
}
```

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

### Get Chat History

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves the history of past chat conversations.

```APIDOC
## GET /api/workspace/product-docs/chats

### Description
Retrieves the history of past chat conversations.

### Method
GET

### Endpoint
`/api/workspace/product-docs/chats`

### Parameters
None

### Request Example
```bash
curl -X GET http://localhost:3001/api/workspace/product-docs/chats \
  -H "Authorization: Bearer <jwt-token>"
```

### Response
#### Success Response (200)
- **history** (array) - An array of chat history objects.
  - **id** (integer) - The unique identifier for the chat.
  - **prompt** (string) - The user's prompt.
  - **response** (string) - The AI's response.
  - **createdAt** (string) - The timestamp when the chat was created.
  - **include** (boolean) - Indicates if the chat should be included.
  - **user** (object|null) - Information about the user.

#### Response Example
```json
{
  "history": [
    {
      "id": 1,
      "prompt": "What are the key features?",
      "response": "Based on the documentation...",
      "createdAt": "2025-01-15T10:30:00.000Z",
      "include": true,
      "user": null
    },
    {
      "id": 2,
      "prompt": "Explain the installation process",
      "response": "To install the product...",
      "createdAt": "2025-01-15T10:35:00.000Z",
      "include": true,
      "user": null
    }
  ]
}
```
```

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

### Configure AnythingLLM Server Environment

Source: https://github.com/mintplex-labs/anything-llm/blob/master/BARE_METAL.md

Copies the example environment file for the server, which contains instance settings. You must ensure at least STORAGE_DIR is set.

```bash
cp server/.env.example server/.env
# Ensure STORAGE_DIR is set in server/.env
```

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

### GET /api/system/local-files - List All Documents

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves a list of all documents stored in the system, organized by folders.

```APIDOC
## GET /api/system/local-files

### Description
Retrieves a list of all documents stored in the system, organized by folders.

### Method
GET

### Endpoint
http://localhost:3001/api/system/local-files

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
```bash
curl -X GET http://localhost:3001/api/system/local-files \
  -H "Authorization: Bearer <jwt-token>"
```

### Response
#### Success Response (200)
- **localFiles** (object) - An object representing the file structure:
  - **name** (string) - The name of the root folder.
  - **type** (string) - The type of the item (e.g., 'folder', 'file').
  - **items** (array) - An array of items within the folder, which can be other folders or files.
    - Each item object may contain:
      - **name** (string) - The name of the file or folder.
      - **type** (string) - The type of the item.
      - **id** (string) - A unique identifier for the file, often its path.
      - **cached** (boolean) - Indicates if the file is cached locally.

#### Response Example
```json
{
  "localFiles": {
    "name": "documents",
    "type": "folder",
    "items": [
      {
        "name": "custom-documents",
        "type": "folder",
        "items": [
          {
            "name": "document.pdf",
            "type": "file",
            "id": "custom-documents/document-1737012345.pdf",
            "cached": false
          }
        ]
      }
    ]
  }
}
```
```

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

### Authentication API

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Endpoints for authenticating users and obtaining API keys. This includes logging in to get JWT tokens, verifying token validity, and generating API keys for developer access.

```APIDOC
## POST /api/request-token

### Description
Logs in a user and returns a JWT token for authentication. Supports both single-user (password-based) and multi-user modes.

### Method
POST

### Endpoint
`/api/request-token`

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

### Request Example
```json
{
  "username": "john.doe@company.com",
  "password": "securePassword123"
}
```

### Response
#### Success Response (200)
- **valid** (boolean) - Indicates if authentication was successful.
- **user** (object) - User details including id, username, and role.
- **token** (string) - The JWT token for subsequent authenticated requests.
- **message** (string) - Confirmation message.

#### Response Example
```json
{
  "valid": true,
  "user": {
    "id": 1,
    "username": "default",
    "role": "admin"
  },
  "token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...",
  "message": "Valid auth credentials"
}
```

## GET /api/system/check-token

### Description
Verifies the validity of a provided JWT token.

### Method
GET

### Endpoint
`/api/system/check-token`

### Parameters
#### Header Parameters
- **Authorization** (string) - Required - Bearer token for authentication (e.g., `Bearer <jwt-token>`).

### Response
#### Success Response (200)
- **valid** (boolean) - Indicates if the token is valid.

#### Response Example
```json
{
  "valid": true
}
```

## POST /api/system/generate-api-key

### Description
Generates an API key for developer access. This endpoint is intended for single-user mode.

### Method
POST

### Endpoint
`/api/system/generate-api-key`

### Parameters
#### Header Parameters
- **Authorization** (string) - Required - Bearer token for authentication (e.g., `Bearer <jwt-token>`).

### Response
#### Success Response (200)
- **apiKey** (object) - Contains the generated API key details.
  - **id** (integer) - The ID of the API key.
  - **secret** (string) - The secret API key.
  - **createdAt** (string) - The timestamp when the API key was created.
  - **createdBy** (integer) - The ID of the user who created the API key.
- **error** (null) - Placeholder for potential errors.

#### Response Example
```json
{
  "apiKey": {
    "id": 1,
    "secret": "ANLLM-a1b2c3d4e5f6...",
    "createdAt": "2025-01-15T10:30:00.000Z",
    "createdBy": 1
  },
  "error": null
}
```

## POST /api/admin/generate-api-key

### Description
Generates an API key for developer access. This endpoint is intended for multi-user admin mode.

### Method
POST

### Endpoint
`/api/admin/generate-api-key`

### Parameters
#### Header Parameters
- **Authorization** (string) - Required - Bearer token for authentication (e.g., `Bearer <admin-jwt-token>`).

### Response
#### Success Response (200)
- **apiKey** (object) - Contains the generated API key details.
  - **id** (integer) - The ID of the API key.
  - **secret** (string) - The secret API key.
  - **createdAt** (string) - The timestamp when the API key was created.
  - **createdBy** (integer) - The ID of the admin who created the API key.
- **error** (null) - Placeholder for potential errors.

#### Response Example
```json
{
  "apiKey": {
    "id": 2,
    "secret": "ANLLM-f7g8h9i0j1k2...",
    "createdAt": "2025-01-15T10:35:00.000Z",
    "createdBy": 99
  },
  "error": null
}
```
```

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

### Running AnythingLLM with Docker Commands

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

A set of bash commands for deploying and managing the AnythingLLM Docker container. It includes commands to pull the latest image, run the container with specified ports and environment variables, view logs, and access the application via localhost.

```bash
# Pull latest image
docker pull mintplexlabs/anythingllm:latest

# Run container
docker run -d \
  --name anythingllm \
  -p 3001:3001 \
  -e LLM_PROVIDER=openai \
  -e OPEN_AI_KEY=sk-... \
  -eDISABLE_TELEMETRY=true \
  -v anythingllm_storage:/app/server/storage \
  mintplexlabs/anythingllm:latest

# Check logs
docker logs -f anythingllm

# Access application
# http://localhost:3001

```

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

### Create Workspace via v1 API

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Creates a new workspace using the v1 API. This endpoint requires an authorization token and accepts workspace name and slug in the JSON body.

```bash
curl -X POST http://localhost:3001/v1/workspace/new \
  -H "Authorization: Bearer <api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Customer Support KB",
    "slug": "support-kb"
  }'

# Response
{
  "workspace": {
    "id": 7,
    "name": "Customer Support KB",
    "slug": "support-kb"
  }
}
```

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

### Verify JWT Token Validity (Bash)

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Checks the validity of a provided JWT token by sending a GET request to the system endpoint. Returns a JSON object indicating whether the token is valid.

```bash
curl -X GET http://localhost:3001/api/system/check-token \
  -H "Authorization: Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."

# Response
{
  "valid": true
}
```

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

### Configure Weaviate Environment Variables (.env.development)

Source: https://github.com/mintplex-labs/anything-llm/blob/master/server/utils/vectorDbProviders/weaviate/WEAVIATE_SETUP.md

This snippet shows the essential environment variables required to configure Anything LLM to use a Weaviate vector database. It includes the database type, the Weaviate endpoint URL, and an optional API key. These variables are typically set in a `.env.development` file or defined at runtime.

```dotenv
VECTOR_DB="weaviate"
WEAVIATE_ENDPOINT='http://localhost:8080'
WEAVIATE_API_KEY= # Optional
```

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

### Get Chat History

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Retrieves the history of past chat conversations. It returns a list of chat objects, each containing the prompt, response, and metadata like creation time. This is useful for displaying previous interactions to the user.

```bash
curl -X GET http://localhost:3001/api/workspace/product-docs/chats \
  -H "Authorization: Bearer <jwt-token>"

# Response
{
  "history": [
    {
      "id": 1,
      "prompt": "What are the key features?",
      "response": "Based on the documentation...",
      "createdAt": "2025-01-15T10:30:00.000Z",
      "include": true,
      "user": null
    },
    {
      "id": 2,
      "prompt": "Explain the installation process",
      "response": "To install the product...",
      "createdAt": "2025-01-15T10:35:00.000Z",
      "include": true,
      "user": null
    }
  ]
}
```

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

### Create New Workspace (Bash)

Source: https://context7.com/mintplex-labs/anything-llm/llms.txt

Creates a new workspace with specified settings, including name, slug, and LLM configuration parameters like temperature and history length. Requires JWT authentication. Returns the newly created workspace details.

```bash
curl -X POST http://localhost:3001/api/workspace/new \
  -H "Authorization: Bearer <jwt-token>" \
  -H "Content-Type: application/json" \
  -d '{ \
    "name": "Product Documentation", \
    "slug": "product-docs", \
    "openAiTemp": 0.7, \
    "openAiHistory": 20, \
    "similarityThreshold": 0.25, \
    "topN": 4 \
  }'

# Response
{
  "workspace": {
    "id": 5,
    "name": "Product Documentation",
    "slug": "product-docs",
    "createdAt": "2025-01-15T10:30:00.000Z"
  },
  "message": "Workspace created"
}
```

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

### Example AnythingLLM Helm values-secret.yaml

Source: https://github.com/mintplex-labs/anything-llm/blob/master/cloud-deployments/helm/charts/anythingllm/README.md

A sample `values-secret.yaml` file for `helm install`. It configures the container image, service type, port, references a Kubernetes Secret for environment variables, and sets persistent volume size and mount path.

```yaml
image:
  repository: mintplexlabs/anythingllm
  tag: "1.9.0"

service:
  type: ClusterIP
  port: 3001

# Reference secret containing API keys
envFrom:
  - secretRef:
      name: openai-secret

# Optionally override other values
persistentVolume:
  size: 16Gi
  mountPath: /storage
```