runtime error

Exit code: 1. Reason: █████████| 605M/605M [00:02<00:00, 242MB/s] 0_CLIPModel/model.safetensors: 100%|██████████| 605M/605M [00:02<00:00, 242MB/s] preprocessor_config.json: 0%| | 0.00/316 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 316/316 [00:00<00:00, 1.94MB/s] 0_CLIPModel/pytorch_model.bin: 0%| | 0.00/605M [00:00<?, ?B/s] 0_CLIPModel/pytorch_model.bin: 100%|██████████| 605M/605M [00:00<00:00, 762MB/s] special_tokens_map.json: 0%| | 0.00/389 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 389/389 [00:00<00:00, 2.37MB/s] tokenizer_config.json: 0%| | 0.00/604 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 604/604 [00:00<00:00, 3.93MB/s] vocab.json: 0%| | 0.00/961k [00:00<?, ?B/s] vocab.json: 100%|██████████| 961k/961k [00:00<00:00, 20.8MB/s] Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`. ✓ LlamaIndex configured to use local Embedding Model and LLM. File '/data/cellpose_db' already exists. No download needed. File '/data/sam_vit_h_4b8939.pth' already exists. No download needed. ❌ ERROR: Could not connect to Neo4j: Cannot resolve address 8d0af37b.databases.neo4j.io:7687 Please ensure Neo4j is running and accessible. Traceback (most recent call last): File "/home/user/app/app.py", line 251, in <module> main() File "/home/user/app/app.py", line 246, in main demo = create_gradio_interface() File "/home/user/app/app.py", line 144, in create_gradio_interface raise RuntimeError("Failed to initialize application. Please check logs.") RuntimeError: Failed to initialize application. Please check logs.

Container logs: