klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-02 13:18:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Only evaluate non-empty responses to reduce eval script latency, cost

Browse Source 
Empty responses by Khoj will always be an incorrect response, so no
need to make call to an evaluator agent to check that
This commit is contained in:
Debanjum
2024-11-07 15:23:30 -08:00
parent ceb29eae74
commit 84a8088c2b
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/eval_frames.py
View File

@@ -113,7 +113,11 @@ def process_batch(batch, counter, results, dataset_length):
agent_response = get_agent_response(prompt)
# Evaluate response
evaluation = evaluate_response(prompt, agent_response, answer)
if agent_response is None or agent_response.strip() == "":
evaluation["decision"] = False
evaluation["explanation"] = "Agent response is empty. This maybe due to a service error."
else:
evaluation = evaluate_response(prompt, agent_response, answer)
# Store results
results.append(