-
Notifications
You must be signed in to change notification settings - Fork 317
Add deep research agent #2117
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
Add deep research agent #2117
Conversation
Dependency Review✅ No vulnerabilities or license issues found.Scanned FilesNone |
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
Adds a new Deep Research Agent microservice using Langchain, its configuration, Docker setup for Intel® Gaudi®, and a placeholder for accuracy benchmarks.
- Introduces
utils.py
with config loading and agent creation logic. - Implements
research_agent.py
as the microservice entrypoint. - Provides Dockerfiles, compose files, and environment scripts for deployment on Gaudi.
Reviewed Changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated 6 comments.
Show a summary per file
File | Description |
---|---|
DeepResearchAgent/utils.py | Load YAML config and create a Langchain agent |
DeepResearchAgent/research_agent.py | Define microservice endpoint and request handling |
DeepResearchAgent/requirements.txt | Add open_deep_research dependency |
DeepResearchAgent/docker_compose/intel/set_env.sh | Set and validate environment variables |
DeepResearchAgent/docker_compose/intel/hpu/gaudi/compose.yaml | Add full Docker Compose for Gaudi deployment |
DeepResearchAgent/docker_compose/intel/hpu/gaudi/README.md | Usage instructions and prerequisites |
DeepResearchAgent/deep_researcher.yaml | Default agent configuration |
DeepResearchAgent/Dockerfile | Build container for the research agent |
Comments suppressed due to low confidence (2)
DeepResearchAgent/docker_compose/intel/hpu/gaudi/compose.yaml:178
- Environment variable key uses
DocSum_
but elsewhere it’sDOCSUM_
. Standardize casing to avoid confusion or misconfiguration.
DocSum_COMPONENT_NAME: ${DOCSUM_COMPONENT_NAME:-OpeaDocSumvLLM}
DeepResearchAgent/utils.py:4
- New utility functions (
load_config
andcreate_agent
) and the research agent logic lack automated tests. Consider adding unit or integration tests to cover config loading and agent execution.
def load_config(config_path: str):
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.
Should we make the agent microservice an openai compatible chat-completion api? so that it can work with the OPEA agent-ui microservice?
the benchmark and ui will be added later |
for more information, see https://pre-commit.ci
Co-authored-by: kaokao <[email protected]>
Co-authored-by: kaokao <[email protected]> Signed-off-by: alexsin368 <[email protected]>
Description