Sage: A conversational AI assistant simplifying data interactions with intuitive ease
Sage is a versatile AI assistant designed to enhance your data interaction experience within a container environment. It provides a user-friendly conversational interface for accessing and manipulating data from various sources, all through a simple configuration file.
...
[source]
top_k = 20
refresh_schedule = "1 0 * * SUN"
[source.confluence]
username = "your_confluence_username"
server = "https://yourcompany.atlassian.net/wiki"
spaces = ["SPACE1", "SPACE2"]
...
[source.web]
links = ["https://example.com", "https://anotherexample.com"]
nested = true
[llm]
model = "gpt-4-turbo"
[embedding]
type = "litellm"
model = "text-embedding-3-large"
[reranker]
type = "huggingface"
top_n = 5
[reranker.huggingface]
name = "BAAI/bge-reranker-large"
revision = "708e6d1fff4ba9c97540a97c23dba46b26d87764"
...Sage Chat is the user-friendly interface that connects you to the vast capabilities of Sage. It's where conversations turn into actions, allowing you to seamlessly interact with your entire digital ecosystem.
Sage enables you to communicate with your data in a natural and intuitive way. Whether you're looking up information, summarizing content, or integrating with external tools, Sage is your personal data assistant, ready to help.
Sage currently offers the following functionalities:
- Data Source Queries: Interact with multiple data sources directly through conversational prompts.
- Integrated Tools: Access tools like calculators, search engines, and Jira issue summarizers within the chat.
- Agent Mode: Activate Sage as an AI agent to handle complex queries and perform autonomous actions.
- Configuration Simplicity: Set up Sage quickly by specifying your desired tools and sources in a configuration file.
- Agent Capabilities: Utilize Sage in agent mode for advanced tasks.
- Continuous Source update: Continuously update the sage data sources via sage's data loader process whenever your data get updated
- Filter-out Data Source: Choose to interact with a specific source or all your configured data sources
Starters are predefined prompts designed to provide a seamless initiation into Sage's capabilities. They create a more intuitive experience by offering common queries and source-specific interactions. The following samples showcase examples of starters you can implement:
starters:
- label: "Casual Wedding Invite"
message: "Draft a casual message to invite a friend as my guest to a wedding next month, ensuring it feels light-hearted and stress-free."
icon: "https://picsum.photos/200"
- label: "Superconductors Simplified"
message: "Describe superconductors in a way that a five-year-old could understand."
icon: "https://picsum.photos/300"
source: "Confluence: SF Space Details"
- label: "Python Email Automation Script"
message: "Generate a Python script for automating daily email reports, and provide instructions for deployment."
icon: "https://picsum.photos/400"
source: "Confluence: Development Docs"
Configuring starters is straightforward and requires editing a YAML configuration file. Each starter consists of a user-friendly label, a pre-defined message that sets the context or action for the AI, an optional icon to visually represent the action, and an optional source identifier that specifies the context for the message.
Learn more about starters configuration
Begin your journey with Sage in just a few steps:
- Installation: Install Sage following our straightforward installation guide.
- Configuration: Define your tools and sources in the configuration file to tailor Sage to your needs.
- Interaction: Start using Sage Chat to explore the full range of its data interaction capabilities.
For complete guidance, refer to our Installation Guide and Configuration Guide
For more detailed information about Sage's capabilities and how to use it, please refer to the following resources:
- Tools Overview - Learn about the tools available in Sage and how to use them.
- LLMs Overview - Understand the Large Language Models supported by Sage.
- Data Sources - Discover the data sources Sage can interact with and how to configure them.
- Quick Start Guide - Get started with Sage quickly with this simple guide.
For an in-depth look at Sage Chat, including its architecture, how it leverages Large Language Models, and tips for getting the best results, please refer to our Sage Chat Documentation.
Sage is a collaborative project that welcomes contributions from developers and enthusiasts alike. Your input can help us refine and expand Sage's functionality.
Ready to contribute? Please see our Contributing Guidelines for more information.
Your feedback is crucial to Sage's development. For assistance, to suggest new features, or to report bugs, please visit our GitHub Issues page.