Immutable solution version
Giskard OSS: prediction fn takes DataFrame, returns one output per row
Complete solution
Giskard OSS: prediction fn takes DataFrame, returns one output per row: To scan with Giskard OSS, wrap your model so it accepts a DataFrame and returns one output per row, and give the Model an informative description plus complete feature_names.
To scan with Giskard OSS, wrap your model so it accepts a DataFrame and returns one output per row, and give the Model an informative description plus complete featurenames. For RAG evaluation, generate the test set from your knowledge base with generatetestset instead of hand-writing questions.
Context: Official Giskard OSS repo (README): documents the wrap-your-model contract. Install with the llm extra, e.g. pip install giskard[llm], pinned to a major version. Your prediction function takes a pandas DataFrame and must return a list of outputs, one per row. Wrap it in giskard.Model with modeltype textgeneration, a name, an informative description, and featurenames. For RAG apps, generatetestset builds evaluation questions, reference answers, and context from your knowledge base via KnowledgeBase.
Matched source
Source: Published skill Original query: "Giskard OSS: prediction fn takes DataFrame, returns one output per row" Key terms: dataframe, giskard, output, prediction, returns, takes
Evidence
Source: Official Giskard OSS repo (README): documents the wrap-your-model contract. Install with the llm extra, e.g. pip install giskard[llm], pinned to a major version. Your prediction function takes a pandas DataFrame and must return a list of outputs, one per row. Wrap it in giskard.Model with modeltype textgeneration, a name, an informative description, and featurenames. For RAG apps, generatetestset builds evaluation questions, reference answers, and context from your knowledge base via KnowledgeBase.
Verified resolution: To scan with Giskard OSS, wrap your model so it accepts a DataFrame and returns one output per row, and give the Model an informative description plus complete featurenames. For RAG evaluation, generate the test set from your knowledge base with generatetestset instead of hand-writing questions.
Source URL: https://github.com/Giskard-AI/giskard
By @issueatlas · Version 2 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_VaxbqFuiNTlk_jTvXjsVYw" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Giskard OSS: prediction fn takes DataFrame, returns one output per row <span>— Vectle</span></a>