-
Notifications
You must be signed in to change notification settings - Fork 7
chore: add generic agent #80
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR introduces a new generic RAG agent sample that demonstrates multi-source information retrieval combining context grounding indexes, web search, and optional MCP tool integration. The agent uses a LlamaIndex workflow with ReAct reasoning and includes human-in-the-loop feedback capabilities.
Key changes:
- Implementation of a flexible RAG agent with multi-knowledge base support using UiPath Context Grounding
- Integration of Tavily web search for real-time information and optional MCP server connectivity for dynamic tool loading
- Human-in-the-loop workflow with iterative feedback and answer refinement
Reviewed Changes
Copilot reviewed 16 out of 17 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| main.py | Core agent implementation with workflow steps for indexing, querying, formatting, and human confirmation |
| uipath.json | Agent schema definition with input/output contracts and resource bindings |
| pyproject.toml | Project dependencies including UiPath SDK, LlamaIndex, Tavily, and MCP tools |
| README.md | Comprehensive documentation covering features, setup, configuration, and usage examples |
| input.json | Sample input demonstrating multi-tool query capabilities |
| sample_data/primary_data/*.txt | Sample company policy documents for primary knowledge base |
| sample_data/secondary_data/*.txt | Sample user preference data for secondary knowledge base |
| resume.json | Workflow resume state file |
| llama_index.json | LlamaIndex workflow configuration |
| agent.mermaid | Workflow visualization diagram |
| AGENTS.md, CLAUDE.md, .agent/*.md | Agent development documentation and references |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
57d016d to
5c2f63c
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
Copilot reviewed 16 out of 17 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
5c2f63c to
9ab41ff
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
cool sample!
let s also include the action app .nupkg here + deployment steps in Readme
This PR introduces a generic agent built using UiPath Llamaindex. The agent serves as a template for building agents and is suitable for expansions.