Core Concepts
Applications
Each application using the RAG framework has its own configuration, tailored
to its unique requirements. Applications can define specific system prompts,
custom tools, enabled agents, and LLM model preferences to align with their
individual workflows and data needs.
Tool Repository
The Tool Repository is a centralized collection of tools used by agents to
complete tasks. It includes general-purpose tools, which offer broad
functionality, and app-specific tools, which are custom-built to meet unique
application requirements. Each tool follows a structured input and output
schema for consistent integration.
Agents
Agents are specialized AI entities configured with profiles that determine
their behavior, workflow type, and the tools they can access. Agents process
user requests by selecting and sequencing tools.
Dynamically Generated Pipelines
Agents generate pipelines by breaking down complex tasks into subtasks, each
associated with a specific tool. These pipelines follow an
Input-Process-Output (IPO) loop with error-handling and self-correction
capabilities, allowing the agent to adapt dynamically and handle complex
workflows.
Vectorization
Vectorization is the process of transforming content into vector embeddings to
enable efficient and semantically relevant retrieval.
Capabilities
| Name | Description |
|---|---|
| Agentic Workflows | Enables autonomous workflows where AI agents make independent decisions based on task context. |
| Agent Intent Analysis | Aligns agent choices with user intent. |
| Dynamic Pipeline Generation | Constructs task pipelines from available tools, selecting the best tools for precise processing. |
| Iterative Self-Correction | Refines responses through iterative feedback, dynamically handling errors to improve accuracy. |
| Knowledge Base Retrieval | Uses a knowledge base for accurate, content-driven answers requiring information retrieval. |
| Automated Document Handling | Automates document processing and categorization. |
| Contextual Retrieval | Retrieves data based on surrounding context, ensuring highly relevant, contextually situated responses. |
| Hypothetical Document Embeddings (HyDE) | Enhances embeddings by generating hypothetical answers, improving understanding of complex queries. |
| Hybrid Search | Combines vector similarity with keyword-based search, ensuring relevance across varied query types. |
| Real-Time Re-ranking | Re-orders search results by contextual relevance, prioritizing the most pertinent information. |
| Date-Based Vector Calculation | Prefers the most recent documents during re-ranking, prioritizing up-to-date information for time-sensitive queries. |
| Multi-Source Vectorization | Ingests and vectorizes data from PDFs, RSS feeds, and structured databases, enhancing retrieval capabilities. |
| Data-Based Retrieval | Retrieves structured data from specific databases, allowing precise, data-driven responses. |
| External Data Source Integration | Supports real-time data from external sources like APIs or RSS feeds, keeping responses relevant. |
| Data Aggregation & Summarization | Summarizes large datasets, providing easy-to-interpret information at a glance. |
| Structured Output | Provides schema-based outputs aligned with templates, ideal for reports and standardized responses. |
| Visualization Capabilities | Supports charts, tables, and graphs for visual representation of complex data. |
| Proactive Query Suggestions | Suggests additional questions based on conversation flow, guiding interactions for deeper insights. |
| User-Specific Context Retention | Retains user-specific context across sessions for personalized experiences. |
| Embeddings Management | Manages vector embeddings for efficient similarity searches and relevant content retrieval. |
| Guards (Safe Input/Output) | Implements safeguards for data handling, validating inputs and outputs for security and integrity. |
| Automated AI Testing | Continuous testing of AI models to ensure consistent, secure, and reliable performance across scenarios. |
| Fine-Tuning and Optimization | Adapts pre-trained models for specific tasks, improving relevance and performance for specialized needs. |
| Memory-Driven Caching | Caches responses based on user intention, reducing redundancy and enhancing response time. |
| Tool Argument-Based Caching | Caches results based on tool arguments, optimizing responses for repeated queries. |
| SDK Integration | Provides a JavaScript and React SDK, enabling easy frontend integration and customization. |
| Adaptive NLP Models | Uses tailored NLP models to suit different conversational contexts. |