{"record":{"id":"f37384e931243863","repo":"rohitg00/ai-engineering-from-scratch","slug":"top-k-must-be-positive","errorCode":null,"errorMessage":"top_k must be positive","messagePattern":"top_k must be positive","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"certifications/claude/lessons/24-rag-retrieval-and-data-pipelines/code/main.py","lineNumber":119,"sourceCode":"        return math.log(1.0 + (total - containing + 0.5) / (containing + 0.5))\n\n    def _score(self, query_terms: list[str], index: int, k1: float = 1.5, b: float = 0.75) -> float:\n        frequencies = self.term_frequencies[index]\n        length = self.lengths[index]\n        normalization = 1.0 - b + b * (length / self.average_length) if self.average_length else 1.0\n        score = 0.0\n        for term in query_terms:\n            frequency = frequencies.get(term, 0)\n            if frequency == 0:\n                continue\n            numerator = frequency * (k1 + 1.0)\n            denominator = frequency + k1 * normalization\n            score += self._inverse_document_frequency(term) * numerator / denominator\n        return score\n\n    def search(self, query: str, top_k: int = 3) -> list[RetrievalHit]:\n        if top_k <= 0:\n            raise ValueError(\"top_k must be positive\")\n        query_terms = tokenize(query)\n        if not query_terms:\n            return []\n        scored = []\n        for index, chunk in enumerate(self.chunks):\n            score = self._score(query_terms, index)\n            if score > 0:\n                scored.append((score, chunk))\n        scored.sort(key=lambda item: (-item[0], item[1].chunk_id))\n        return [\n            RetrievalHit(\n                chunk_id=chunk.chunk_id,\n                document_id=chunk.document_id,\n                text=chunk.text,\n                updated_at=chunk.updated_at,\n                score=round(score, 6),\n            )\n            for score, chunk in scored[:top_k]","sourceCodeStart":101,"sourceCodeEnd":137,"githubUrl":"https://github.com/rohitg00/ai-engineering-from-scratch/blob/39ea8a1c6d0b61f071226eff7ede4d4105fed820/certifications/claude/lessons/24-rag-retrieval-and-data-pipelines/code/main.py#L101-L137","documentation":"Error \"top_k must be positive\" thrown in rohitg00/ai-engineering-from-scratch.","triggerScenarios":"Thrown at certifications/claude/lessons/24-rag-retrieval-and-data-pipelines/code/main.py:119 when the library encounters an invalid state.","commonSituations":"See trigger scenarios.","solutions":[],"exampleFix":null,"handlingStrategy":null,"validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"39ea8a1c6d0b61f071226eff7ede4d4105fed820","analyzedAt":"2026-08-26T03:13:46.626Z","schemaVersion":2},"datasetVersion":"2026-08-26T07:17:17.940Z"}