No pulic url and dashboard exported

[CodeAunt]

After running gaianet init. No pulic url and dashboard got exported.

Using Ubuntu 22 Docker container

[+] Checking the config.json file ...

[+] Downloading Phi-3-mini-4k-instruct-Q5_K_M.gguf ...

    * Using the cached Phi-3-mini-4k-instruct-Q5_K_M.gguf in /root/gaianet

[+] Downloading nomic-embed-text-v1.5.f16.gguf ...

    * Using the cached nomic-embed-text-v1.5.f16.gguf in /root/gaianet

[+] Creating 'default' collection in the Qdrant instance ...

    * Start a Qdrant instance ...

    * Remove the existed 'default' Qdrant collection ...

    * Download Qdrant collection snapshot ...

######################################################################## 100.0%

      The snapshot is downloaded in /root/gaianet

    * Import the Qdrant collection snapshot ...

      The process may take a few minutes. Please wait ...

      Recovery is done!

[+] Preparing the dashboard ...

You already have a private key.

[+] Preparing the GaiaNet domain ...

[+] COMPLETED! GaiaNet node is initialized successfully.

>>> To start the GaiaNet node, run the command: gaianet start <<<

[+] Checking the config.json file ...

You already have a private key.

[+] Starting Qdrant instance ...

    Qdrant instance started with pid: 397

[+] Starting LlamaEdge API Server ...

    Run the following command to start the LlamaEdge API Server:

wasmedge --dir .:./dashboard --env NODE_VERSION=0.2.4 --nn-preload default:GGML:AUTO:Phi-3-mini-4k-instruct-Q5_K_M.gguf --nn-preload embedding:GGML:AUTO:nomic-embed-text-v1.5.f16.gguf rag-api-server.wasm --model-name Phi-3-mini-4k-instruct,Nomic-embed-text-v1.5 --ctx-size 4096,512 --batch-size 16,512 --prompt-template phi-3-chat,embedding --rag-policy system-message --qdrant-collection-name default --qdrant-limit 1 --qdrant-score-threshold 0.5 --web-ui ./ --socket-addr 0.0.0.0:8080 --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" 

    LlamaEdge API Server started with pid: 626

[2024-07-28 08:12:55.462] [info] [WASI-NN] llama.cpp: llm_load_print_meta: model size       = 2.62 GiB (5.89 BPW) 

[2024-07-28 08:12:55.462] [info] [WASI-NN] llama.cpp: llm_load_print_meta: general.name     = Phi3

[2024-07-28 08:12:55.462] [info] [WASI-NN] llama.cpp: llm_load_print_meta: BOS token        = 1 '<s>'

[juntao]

How much RAM do you have allocated to Docker? Thanks

[CodeAunt]

How much RAM do you have allocated to Docker? Thanks

docker stats and the container uses 48.12MiB/4.818GiB

[juntao]

I believe that refers to the disk space you have available to Docker not the RAM.

[CodeAunt]

I believe that refers to the disk space you have available to Docker not the RAM.

Cause I added Memory to 5G in Docker Desktop's preference. And the disk space allocated is 59G.

CPUs: 4 Memory: 5.00 GB Swap: 1 GB Disk image size: 59.6 GB (56.9 GB used)

[juntao]

You can try a smaller model first:

https://github.com/GaiaNet-AI/node-configs/tree/main/qwen2-0.5b-instruct