skills/retrieval_augmented_generation/evaluation/vectordb.py [45:88]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        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

    def save_db(self):
        data = {
            "embeddings": self.embeddings,
            "metadata": self.metadata,
            "query_cache": json.dumps(self.query_cache),
        }
        os.makedirs(os.path.dirname(self.db_path), exist_ok=True)
        with open(self.db_path, "wb") as file:
            pickle.dump(data, file)

    def load_db(self):
        if not os.path.exists(self.db_path):
            raise ValueError("Vector database file not found. Use load_data to create a new database.")
        with open(self.db_path, "rb") as file:
            data = pickle.load(file)
        self.embeddings = data["embeddings"]
        self.metadata = data["metadata"]
        self.query_cache = json.loads(data["query_cache"])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -