Agent Framework#
In the field of artificial intelligence (AI), the ability to enhance or complement the capabilities of a Large Language Model (LLM) using specialized tools and agents, plays a pivotal role. The combination of an LLM and tools is often referred to as an agent.
Squirro Chat can leverage the agent framework by routing specific tasks to dedicated tools, improving both the capability and performance of AI workflows. The generative AI service is capable of interfacing with a wide variety of tools capable of content creation, analysis, enrichment, classification, fact-checking, and transformation.
The Squirro agent framework is a structured, reusable software environment designed to facilitate the development, deployment, and management of agents. It offers standardized components and interfaces to streamline the implementation of an advanced and scalable Squirro platform.
A tool is a script or program called by the agent, designed to perform a specific function or a set of functions that assist the LLM in formulating a response. Contrary to the data connectors, the agent framework retrieves only the necessary information without requiring access to the data storage layer of the Squirro platform. After an initial analysis of the user prompt, the LLM activates one or more tools as needed.
Tools#
The Squirro platform includes a set of native tools, designed to provide users with robust data access, retrieval, and integration capabilities. These tools are tightly integrated with the platform, enabling users to efficiently interact with their data.
Squirro Retriever#
The Squirro Retriever tool extends the knowledge base using the content of a Squirro project when needed. Easily combine the power of a large language model with your corporate data indexed by Squirro. When enabled, Squirro Retriever first searches the data storage layer to find relevant information related to the user’s input. The system passes the information retrieved to the model, producing a response based on that context. That approach delivers more accurate responses.
Brave Search#
The Brave Search tool enhances the accuracy and relevance of user interactions with Squirro Chat. It uses a Retrieval Augmented Generation (RAG) approach to fetch relevant information from the web and generate informed answers by receiving user queries, sending them to Brave Search to retrieve relevant web results, ranking and filtering the results, and then using the retrieved information to generate a response.
Structured Data Retriever#
The Structured Data Retriever tool provides a unified interface for querying diverse databases and systems, leveraging a data virtualization layer to integrate multiple data sources. By abstracting the complexities of underlying systems, it enables users to execute queries and retrieve data through a single point of access, without requiring data indexing.
Example of an Agent#
Incident Support Agent#
Incident Support Agent facilitates the initial assessment of support requests. It operates in three distinct phases: classification of the request, collection of information, and resolution. The agent uses a knowledge graph to categorize the request and gather all the necessary information. It then provides user feedback, ultimately creating a support ticket or taking a customizable final action to conclude the conversation.
Get started#
The Squirro agent framework is the ideal solution for designing scalable and effective problem-solving and decision-making systems. To get started, you can configure agents and tools by visiting the Configuring Agents and Tools page. For building custom agents, refer to the Developing Custom Tools page.