-
Notifications
You must be signed in to change notification settings - Fork 330
Transit the implementation of DeepResearchAgent #2334
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
Signed-off-by: Joshua Yao <yi.a.yao@intel.com>
Dependency ReviewThe following issues were found:
License IssuesDeepResearchAgent/requirements.txt
Scanned Files
|
for more information, see https://pre-commit.ci
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 transitions the DeepResearchAgent from the deprecated open_deep_research implementation to the LangChain DeepAgents harness, which LangChain now positions as their primary framework for building autonomous agents.
Key changes:
- Complete replacement of
open_deep_researchdependency withdeepagentsand associated libraries - New agent factory pattern for creating research agents with configurable parameters
- Enhanced environment configuration with granular control over research behavior and model settings
Reviewed Changes
Copilot reviewed 15 out of 16 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| DeepResearchAgent/utils.py | Removed old agent creation utility that used open_deep_research |
| DeepResearchAgent/tests/test_compose_on_gaudi.sh | Added case-insensitive grep for more flexible test validation |
| DeepResearchAgent/research_agents/deepagents/utils.py | Added Rich-based utilities for formatting and displaying agent messages |
| DeepResearchAgent/research_agents/deepagents/tools.py | Implemented Tavily search and reflection tools for the research agent |
| DeepResearchAgent/research_agents/deepagents/prompts.py | Added comprehensive prompt templates for research workflow and agent instructions |
| DeepResearchAgent/research_agents/deepagents/README.md | Added README referencing DeepAgents source |
| DeepResearchAgent/research_agent.py | Refactored to use new agent factory and handle DeepAgents response format |
| DeepResearchAgent/requirements.txt | Updated dependencies from open_deep_research to deepagents ecosystem |
| DeepResearchAgent/requirements.in | Added new dependency specifications for deepagents |
| DeepResearchAgent/docker_compose/intel/hpu/gaudi/set_env.sh | Enhanced with detailed comments, validation, and new configuration options |
| DeepResearchAgent/docker_compose/intel/hpu/gaudi/compose.yaml | Updated service configuration with tool calling support and new environment variables |
| DeepResearchAgent/deep_researcher.yaml | Removed old configuration file |
| DeepResearchAgent/agent_factory.py | Added factory for creating DeepAgents research agents with configurable prompts |
| DeepResearchAgent/README.md | Updated documentation to reflect DeepAgents implementation |
| DeepResearchAgent/Dockerfile | Updated to copy new research_agents directory and agent_factory |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Description
The LangChain
open_deep_researchhas gone quite(last commit is ~ 3 months ago). LangChain has explicitly shifted strategy from building "single-purpose" agentic apps to building a "general harness" for agents. The LangChain blog explicitly published a post titled "Doubling down on DeepAgents," positioning it as the primary harness for building autonomous, long-running agents. DeepAgents also provide sample code for building deep research capability.In this PR, we will transit from open_deep_research to the Deep Research of DeepAgents for OPEA DeepResearchAgent.
Issues
#2333
Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
Tests