Settings
Configure the AI chatbot behavior, appearance, and provider settings from the admin dashboard.
Global settings are managed from Admin → Settings. Settings are organized into tabs. Some tabs are only visible to super admins or when specific features are enabled.
System Prompt
The system prompt defines the chatbot's personality, behavior, and response style. It is prepended to every conversation.
Configuring the System Prompt
Go to Admin → Settings → General tab.
Edit the Inference System Prompt Personality field.
Click Save.
Writing an Effective System Prompt
A good system prompt should cover these areas:
- Knowledge boundaries — Define what the chatbot should and should not answer. For example, restrict it to only use information from the knowledge base.
- Greeting behavior — How the chatbot should start a conversation.
- Tone and style — Friendly, professional, formal, casual, etc.
- Response length — Short and concise, or detailed and thorough.
- Response format — Whether to use bullet points, paragraphs, numbered lists, etc.
- Fallback behavior — What to do when the chatbot cannot answer a question (e.g., refer users to a support email).
- Language — Whether to respond in a specific language or match the user's language.
Example System Prompt
**Personality traits:**
- Important - You are not allowed to respond with Your general LLM knowledge. You are allowed to only utilize information within knowledge base.
- Greet in the first message in the chat – "Hello!”. If you indicate that you need time to think, you do not need to greet once again when continuing to answer the question.
- You clearly explain what ... does and how it works, using only information available in the knowledge base.
- You stay friendly, encouraging, and professional at all times.
- When informing user of tool usage, do not respond with technical jargon. E.g., for semantic tool usage, simply advise that You are looking through the knowledge base.
- Keep responses warm and professional, but concise.
- Respond in one paragraph, no longer than five lines. Use simple, clear language that is easy to read and understand. Keep your tone friendly and approachable, making complex information digestible without losing accuracy.
- Bullet-proof formatting - use bullet points. Make scanning effortless.
- When presenting information that can be listed, format it as a bullet point list. Only add citations after the entire list, not after each bullet point.
- When answering a question You must start with the correct answer first and only then follow up with related information if applicable
- Do not include messages about asking the user to wait while searching a knowledge base—just provide the answer directly.
- Response length - short and concise.
- If you are unable to answer a related question, advise the user to contact ...@...Each workspace can also have a Custom System Prompt that extends or overrides the global prompt. See Workspaces for details.
Theme
Customize the chatbot's appearance with a custom CSS theme based on Tailwind CSS and ShadCN UI.
Go to Admin → Settings → General tab.
Generate a theme using the TweakCN Theme Editor or write custom CSS variables manually.
Paste the generated CSS into the CSS Theme field.
Click Save. The new theme applies immediately to all users.
Providers
Configure which AI models power your chatbot and how they behave.
Provider settings are only visible to super admins.
API Keys
Provide API keys for the providers you want to use. Keys configured here override any environment variable defaults.
| Provider | Description |
|---|---|
| OpenAI | GPT models and DALL-E image generation |
| Anthropic | Claude models |
| Google Gemini | Gemini models |
| DeepSeek | DeepSeek models |
| Mistral | Mistral models |
| OpenRouter | Access multiple providers through a single API |
| YouTube | YouTube Data API for YouTube channel/video ingestion |
| ElevenLabs | Speech-to-text transcription models |
Chat Models
| Setting | Description |
|---|---|
| Default Model | Primary model used for chat conversations. Must support streaming, function calling, and 128k+ context. |
| Reasoning Effort | Thinking level for models with extended reasoning (low, medium, high) |
| Thinking Budget | Maximum token budget for extended reasoning |
| Default Embedding Model | Model used for generating vector embeddings during document processing |
| Default Image Model | Model used for image generation |
| Default Transcription Model | Model used for speech-to-text transcription |
Processing Models
These models handle background document processing tasks:
| Setting | Description |
|---|---|
| Metadata Generation Model | Enriches documents with AI-generated title and description |
| Contextual Chunk Model | Adds surrounding context to document chunks for better retrieval |
| Translation Model | Translates documents to the configured base language |
Each processing model has its own Reasoning Effort and Thinking Budget settings.
Retry Settings
| Setting | Description |
|---|---|
| Max Retries | Number of retry attempts when an LLM API call fails (default: 3) |
| Retry Interval | Delay in seconds between retry attempts (default: 0.1) |
Observability
Monitor LLM interactions by connecting to Langfuse for trace collection and analysis. Observability settings are configured per organization under the Provider tab.
| Setting | Description |
|---|---|
| Langfuse Base URL | Langfuse server URL (defaults to https://cloud.langfuse.com if left blank) |
| Langfuse Public Key | Your Langfuse project public key |
| Langfuse Secret Key | Your Langfuse project secret key |
If organization-level keys are not configured, the platform falls back to the global environment variable defaults (LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, LANGFUSE_HOST).
Traces are exported via OpenTelemetry, giving you detailed visibility into LLM calls, tool executions, and token usage.
Rate Limiting
Limit how many messages users can send within a time window to control API costs and prevent abuse.
Go to Admin → Settings → General tab.
Enable Rate Limiting.
Set the Maximum messages and Time window (in seconds). For example, 20 messages per 3600 seconds allows 20 messages per hour.
Optionally customize the Error message shown to users when the limit is exceeded.
Click Save.
File Attachments
By default, uploaded file attachments require authentication to access. You can make all file attachments publicly accessible by enabling the Make all file attachments publicly accessible option in the General tab.
Data Retention
When the data retention feature is enabled, chat history is automatically deleted after the configured retention period.
Go to Admin → Settings → Data Retention Policy tab.
Set the Retention Period and Timeframe (weeks, months, or years).
Click Save. Chat history older than the configured period will be automatically removed.