-
Notifications
You must be signed in to change notification settings - Fork 660
Adding an example of a scientific deep research #23
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: master
Are you sure you want to change the base?
Conversation
Output: |
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.
left some minor comments
one major comment though: why does this deserve to be its own example? It seems pretty similar to deep-research. is there something novel about this? a novel set of tools or prompting technique or subagents? is there a common benchmark to benchmark it on? I dont see any of those at the moment, so questioning whether this deserves to be its own thing a bit
|
||
See [examples/scientific_research/scientific_agent.py](examples/scientific_research/scientific_agent.py) for the full implementation. | ||
|
||
## Examples |
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.
i like this section, but lets remove line 69 then
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.
ok
The overall idea is to widen the audience of deepagents. |
I've also added ANTI-HALLUCINATION sections in the prompt. Quite a useful thing, when APIs don't return proper results (package not installed, api is down, too many responses, overload, etc.) the LLM starts to hallucinate. |
Input:
Design a multi-step synthesis route for the complex natural product Taxol (Paclitaxel),
including retrosynthetic analysis, literature review of key reactions, and detailed
experimental procedures. Consider the challenges of stereochemistry, protecting group
strategies, and scalability. Also analyze the current state of research on Taxol
synthesis and identify potential improvements or alternative approaches.