Overview

The Knowledge Service retrieves information or answers from preloaded and/or cached knowledge bases for efficient query processing.

• Predefined Knowledge Bases: Support for multiple domain-specific knowledge bases hosted on BReact OS
• Additional Knowledge Input: Ability to provide custom knowledge alongside predefined bases
• Configurable Output: Control over response length and model parameters
• Flexible Integration: Easy to use with any knowledge-intensive task

Endpoints

Process Endpoint

The process endpoint performs knowledge retrieval and AI-powered text generation.

API Endpoint

Endpoint Parameters

Request

content (string, required)

The query or message to process.

context (object, required)

Knowledge base selection and additional knowledge:

• knowledgeBases (string[]): Array of knowledge base IDs to use
• knowledge (string, optional): Additional custom knowledge to include

config (object, optional)

Model and output configuration:

• modelId (string): Model to use for inference (default: "mistral-large-2411")
• maxInputTokens (integer): Maximum tokens for combined input (default: 7000)
• maxTokens (integer): Maximum tokens in response (default: 4000)
• maxOutputLength (integer): Maximum character length of response (default: 1000)
• systemPrompt (string, optional): Additional instructions to append to default prompt

Response

status (string)

Status of the processing ("success" or "error").

result (object)

For successful responses:

• response (string): Generated text response
• usedKnowledge (string): Knowledge bases used
• confidence (number): Confidence score

metadata (object)

Processing metadata:

• model (string): Model used
• created_at (string): Creation timestamp
• processed_at (string): Processing timestamp
• instance_id (string): Instance identifier
• tracking_id (string): Unique tracking ID
• knowledge_bases (string[]): Knowledge bases used
• has_additional_knowledge (boolean): Whether custom knowledge was included
• was_truncated (boolean): Whether input was truncated
• total_input_tokens (integer): Total tokens in input

Examples

Request

Basic Chart Pattern Analysis

Combined Elliott Wave and Chart Pattern Analysis

Comprehensive Technical Analysis

Advanced Technical Analysis with System Prompt

Conservative Token Usage and additional System Prompt

Token-Aware Multiple Knowledge Base Query

Response

Successful Response

Response showing token management

Error Response

Response with comprehensive analysis

Response showing token management with truncation