No application file
Agents
1
RAG Evaluation Toolkit (RAGET)
π
Quickly generate test sets and evaluate any RAG pipeline!
Giskard
company
Verified
AI & ML interests
LLM, Agents, Evaluation, Evals, AI Quality, AI Security, Red-teaming
Recent Activity
View all activity
Organization Card
Giskard: The testing platform for LLM Agents
Control risks of performance, bias and security issues of LLM Agents
Get started π’
Install the latest version of Giskard from PyPi using pip. We support Python 3.9, 3.10 and 3.11.
pip install "giskard[llm]" -U
Finally, join our Discord community to drive the future of AI standards towards Quality, Security & Compliance!
models 0
None public yet
datasets 7
giskardai/harmbench-scenarios
Viewer β’ Updated β’ 400 β’ 73
giskardai/do-not-answer-scenarios
Viewer β’ Updated β’ 939 β’ 105
giskardai/giskard-scan-data
Updated β’ 26
giskardai/StereoTales
Viewer β’ Updated β’ 1.04M β’ 39 β’ 2
giskardai/phare
Viewer β’ Updated β’ 4.05k β’ 297 β’ 13
giskardai/realperformance
Viewer β’ Updated β’ 1.27k β’ 24 β’ 4
giskardai/realharm
Viewer β’ Updated β’ 136 β’ 34 β’ 12