colpali-engine

import torch from colpali_engine.models import ColPaliModel, ColPaliProcessor from colpali_engine.retrieval import ColPaliRetriever model_name = "vidore/colpali-v1.2" model = ColPaliModel.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="cuda" if torch.cuda.is_available() else "cpu") processor = ColPaliProcessor.from_pretrained(model_name) # Example documents (can be images or text) docs = [ "A diagram of the ColPali architecture", "Another document with text" ] query = "ColPali architecture" # Process and index documents doc_embeddings = [] for doc in docs: with torch.no_grad(): processed = processor.process_images([doc]) embeddings = model(**processed.to(model.device)) doc_embeddings.append(embeddings) # Index with retriever retriever = ColPaliRetriever(model, processor) retriever.index(doc_embeddings) # Search results = retriever.search(query, k=2) print(results)