def search()

in skills/retrieval_augmented_generation/evaluation/vectordb.py [0:0]

• 22 lines of code
• 6 McCabe index (conditional complexity)

    def search(self, query, k=3, similarity_threshold=0.75):
        if query in self.query_cache:
            query_embedding = self.query_cache[query]
        else:
            query_embedding = self.client.embed([query], model="voyage-2").embeddings[0]
            self.query_cache[query] = query_embedding

        if not self.embeddings:
            raise ValueError("No data loaded in the vector database.")

        similarities = np.dot(self.embeddings, query_embedding)
        top_indices = np.argsort(similarities)[::-1]
        top_examples = []
        
        for idx in top_indices:
            if similarities[idx] >= similarity_threshold:
                example = {
                    "metadata": self.metadata[idx],
                    "similarity": similarities[idx],
                }
                top_examples.append(example)
                
                if len(top_examples) >= k:
                    break
        self.save_db()
        return top_examples