* Failed to start LlamaEdge API Server after 3 retries.

[wuqing3]

mac m1 16g ram macos14.5 [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:132: server_version: 0.7.3 [2024-07-16 14:29:04.884] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:140: model_name: Phi-3-mini-4k-instruct,Nomic-embed-text-v1.5 [2024-07-16 14:29:04.884] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:148: model_alias: default,embedding [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:162: ctx_size: 4096,512 [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:176: batch_size: 4096,512 [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:190: prompt_template: phi-3-chat,embedding [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:199: rag_prompt: You are a tour guide in Paris, France. Use information in the following context to directly answer the question from a Paris visitor.\n----------------\n [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:220: qdrant_url: http://127.0.0.1:6333 [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:223: qdrant_collection_name: default [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:226: qdrant_limit: 1 [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:229: qdrant_score_threshold: 0.5 [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:240: chunk_capacity: 100 [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] server_config: rag_api_server in src/main.rs:243: rag_policy: system-message [2024-07-16 14:29:04.885] [wasi_logging_stdout] [info] llama-core: llama_core in /home/runner/.cargo/registry/src/index.crates.io-6f17d22bba15001f/llama-core-0.12.1/src/lib.rs:496: Initializing the core context for RAG scenarios [2024-07-16 14:29:04.885] [info] [WASI-NN] GGML backend: LLAMA_COMMIT a59f8fdc [2024-07-16 14:29:04.885] [info] [WASI-NN] GGML backend: LLAMA_BUILD_NUMBER 3358