ragas · Issues· 596 open

AgentGoalAccuracyWithoutReference never sets output_type, so metric.train() instruction optimization aborts with ValueError

Inconsistency between claims and statements in context_recall

AG-UI MessagesSnapshot: convert_messages_snapshot drops tool call name and arguments (ToolCall(name='unknown_tool', args={}))

# Question: Recommended integration approach for Node.js / TypeScript full-stack applications

Metric integrity: faithfulness and context-recall divide by emitted verdicts not submitted inputs; errors become NaN and exit headline; context embedded unsanitized into judge prompts; extract_json takes first structure

Question: per-sample scores in original form from an EvaluationResult

Is this project actively maintained at this point?

Should the reported metric mean disclose how many samples it was computed over?

No module named 'langchain_community.chat_models.vertexai'

New metric: PII Leakage detection for RAG/agentic responses

LLM cache keys can return cross-model responses

Your project is on StackMap — a curated map of the AI stack

ModuleNotFoundError: langchain_community.chat_models.vertexai (breaks import ragas)

CI: check-docs fails on every fork PR — pull_request_target checkout blocked by actions/checkout fork guard

使用 context manager 修复文件资源泄漏