<POST> configureApp API
The table below provides a detailed breakdown of all fields included in the API request body. It describes each field's purpose, type, and possible values to help you configure the API effectively with examples.
Field | Type | Description | Example |
|---|---|---|---|
config_language | String | Specifies the languages that the system supports for user interaction. Can be English (default value) or English & Korean both. by default "en", possible values "en,ko" | "en" |
config_llm | String | Defines the configured Language Model (LLM) to be used.
Note:
| "Mistral" |
image_analysis_type | String | Supported Image Analysis types like OCR or Content Moderation.
| "ocr" |
"input_config" | Dict | Details about the input configuration: | |
| |
| "JSON": { "enabled": true } |
| |
| "Block Competitor": { "value": "Airtel,Jio", "comparison":"exact_match" } |
| |
| "Block Substring": { "value": "kill,murder", "comparison":"exact_match" } |
| |
| "Ban Topic": { "value": "Compensation,War" } |
| |
| "Allowed List": { "value": "AIShield,Bosch", "comparison": "exact_match" } |
| |
| "Regex": { "value": "[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+.[a-zA-Z]{2,}$" } |
| |
| "URL Detection": { "enabled": true } |
| |
| "Code Detection": { "enabled": true } |
| |
| "Toxicity": { "enabled": true, "level": "Low" } |
| |
| "Profanity": { "enabled": true } |
| |
| "PII Detection": { "enabled": true, "redaction": false } |
| |
| "Special PII Detection": { "enabled": true } |
| |
| "Prompt Injection / Jailbreaks": { "enabled": true, "level": "Medium" } |
| |
| "Secrets": { "enabled": false } |
| |
| "Not Safe For Work": { "enabled": false } |
| |
| "Gender Sensitive": { "enabled": false } |
| |
| "Racial Sensitive": { "enabled": false } |
| |
| "Invisible Text": { "enabled": false } |
| |
| "Input Rate Limiter": { "value": 5 } |
| |
| "Token Limit": { "value": 1024 } |
| |
| "BCI Detection": { "enabled": true, "default_model_name": "BCI_MODEL_LOW", "custom_model_name": "", "mode": "dafault" } |
"output_config" | Dict | Details about the output guardrail configuration: | |
| |
| "JSON": { "enabled": true } |
| |
| "Ban Topic": { "value": "Compensation,War" } |
| |
| "Allowed List": { "value": "AIShield,Bosch", "comparison": "exact_match" } |
| |
| "Blocked List": { "value": "kill,murder,suicide", "comparison": "contains" } |
| |
| "Regex": { "value": "[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+.[a-zA-Z]{2,}$" } |
| |
| "Code Detection": { "enabled": true } |
| |
| "Toxicity": { "enabled": true, "level": "Low" } |
| |
| "Sentiment": { "enabled": true } |
| |
| "No LLM Output": { "enabled": true } |
| |
| "Special PII Detection": { "enabled": true } |
| |
| "Malicious URL Detection": { "enabled": true } |
| |
| "URL Reachability": { "enabled": true }
|
| |
| "Not Safe For Work": { "enabled": true }
|
| |
| "Gender Sensitive": { "enabled": false } |
| |
| "Racial Sensitive": { "enabled": false } |
| |
| "BCI Detection": { "enabled": true, "default_model_name": "BCI_MODEL_LOW", "custom_model_name": "", "mode": "dafault" } |
Theme | Feature | Description |
|---|---|---|
Content Access Control | Block Competitor | Blocks mentions of competitors |
Content Access Control | Block Substring | Blocks specific strings of text |
Content Access Control | Ban Topic | Blocks entire topics of discussion |
Content Access Control | Allowed List | Permits only approved content |
Content Access Control | Blocked List | Prevents output of certain block listed content |
Content Analysis | Regex | Uses patterns to match text/alphanumeric for filtering |
Content Analysis | URL Detection | Identifies URLs in prompt |
Content Safety | Toxicity | Filters toxic and harmful language in input or in prompt's response |
Content Safety | Profanity | Blocks swear words and vulgar language (supports English language) |
Content Safety | Not Safe For Work | Filters sexually explicit or inappropriate material |
Content Safety | Sentiment | Analyzes the sentiment of AI responses (positive, negative, or neutral) |
Content Safety | Gender Sensitive | Detects Gender Bias in Language |
Content Safety | Racial Sensitive | Detects Racial Bias in Language |
Privacy Protection | PII Detection | Detects personal identifiable information (e.g., Full name, email address, phone number) |
Privacy Protection | PII Redaction | Redacts sensitive information to enhance security and ensure compliance |
Privacy Protection | BII Detection | Detects Business Identified Information (e.g., Salary, Bonus) |
Privacy Protection | Special PII Detection | Detects specialized personal information |
Security Measures | Prompt Injection / Jailbreaks | Detects attempts to manipulate the AI |
Security Measures | Secrets | Detects and redacts sensitive information (AWS Secrets, Git Secrets, DB Secrets) |
Security Measures | Code Detection | Identifies programming code in text (C, C++, HTML, Bash, JAVA, JavaScript, Python, C#, JSON) |
Security Measures | Malicious URL Detection | Scans for harmful URLs in output |
Security Measures | URL Detection | Identifies harmful URLs |
Security Measures | URL Reachability | Checks if URLs in output are accessible |
Additional Checks | JSON | Ensures correctness and validates JSON format |
Additional Checks | Invisible Text | Identifies hidden text in the input |
Content Validation | No LLM Output | Underlying LLM refuses to provide an answer |
Content - Feature | Image Content Moderation | Support for OCR, Image Filtering |
