Repository Issue Activity (beta)

#2983 LLM cache keys can return cross-model responses

#2856 Your project is on StackMap — a curated map of the AI stack

#2995 ModuleNotFoundError: langchain_community.chat_models.vertexai (breaks import ragas)

#2624 [Bug]: evaluate() throws TypeError when using the recommended ragas.metrics.collections and llm_factory

#2992 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

#2989 CI: check-docs fails on every fork PR — pull_request_target checkout blocked by actions/checkout fork guard

#2986 使用 context manager 修复文件资源泄漏

#2981 [Bug]: Faithfulness metric (and PydanticPrompt) fails to parse JSON when LangChain LLM response contains markdown code fences

#2980 Should the reported metric mean disclose how many samples it was computed over?

#2966 A working EvalPort adapter for ragas.evaluate() results

#2978 OpenAI client base_url /v1 plus Instructor adapter for a Chat Completions host

#2690 Update `HaystackLLMWrapper` to support New Chat Generator Components

#2975 Question: per-sample scores in original form from an EvaluationResult

#2871 default_transforms() raises unhandled ZeroDivisionError on an empty documents list

#2748 Incorrect class name in deprecation warning for LLMContextPrecisionWithoutReference

#1981 Misleading documentation for "LLM Based Context Precision without reference"

#2964 ChrfScore returns 0.0 for a missing reference, scoring a dataset gap as a model failure

#2888 BleuScore evaluates only the first sentence (corpus_bleu reference structure bug)

#2101 The output answer is the same as the reference answer, and the blue score has always been 0

#2035 Context Precision Documentation

#2741 No module named 'langchain_community.chat_models.vertexai'

#2921 json_schema missing - Faithfulness - openai/gpt-oss-120b

#2925 Pre-commit hook fails on clean main: 88 docs/*.md files fail 'ruff format --check'

#2885 optimizers/dspy_llm_wrapper.py: inspect_history(n=0) returns full history (Python [-0:] bug)

#2860 LocalCSVBackend.save_dataset crashes with ValueError on rows with different keys