github/node-DeepResearch
1
0
Fork 0
mirror of https://github.com/jina-ai/node-DeepResearch.git synced 2026-03-22 07:29:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: update readme

Browse Source
This commit is contained in:
Han Xiao
2025-02-06 23:33:38 +08:00
parent c76ab3415c
commit d6811fc2eb
4 changed files with 147 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -217,3 +217,13 @@ flowchart TD
BeastMode --> FinalAnswer[Generate final answer] --> End
```
## Evaluation
I kept the evaluation simple, LLM-as-a-judge and collect some ego questions (i.e. questions about Jina AI that I know 100% the answer) for evaluation.
I mainly look at 3 things: total steps, total tokens, and the correctness of the final answer.
```bash
npm run eval ./src/evals/ego-questions.json
```