deepresearch
Gemini Deep Research Agent - Multi-step research tasks
Installation
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
View source ↗GuidesSkill instructions
Deep Research Skill
Autonomous research agent that plans, searches, and synthesizes detailed reports.
Features
- Multi-step Research: Plans and executes complex research
- Web + Your Data: Uses Google Search + File Search
- Cited Reports: Sources for every claim
- Streaming: Real-time progress updates
Usage
from rhea_noir.skills.deepresearch.actions import skill as dr
# Start research (async, can take minutes)
result = dr.research(
query="Compare the top 5 AI frameworks in 2026",
format_instructions="Include comparison table"
)
print(result["report"])
print(result["sources"])
With Your Data (File Search)
result = dr.research_with_files(
query="Compare our Q4 report against industry trends",
file_store="fileSearchStores/my-store"
)
Pricing
~$2-5 per research task depending on complexity.
[!NOTE] Uses Interactions API. Tasks can take 1-20 minutes.
Examples
Read the usage examples in the source repository.
View source ↗Source history
- Indexed on
- 2026-01-20
- Index updated
- 2026-01-26
- Branch
- main
Index and sync dates describe this directory. View the source repository for code history.
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!