GUI wasn't rendered on 127.0.0.1:8001

[nickzherdev]

I succesfully installed all requirements, though having a slightly old NVIDIA drivers. Nether open http:////127.0.0.1:8001/ nor xdg-open http:////127.0.0.1:8001/ managed to render a GUI. It opened a new tab and that's it, infinite loading. I'm on a Linux Mint 19

python3.11 -m private_gpt
16:43:40.887 [INFO    ] private_gpt.settings.settings_loader - Starting application with profiles=['default']
16:43:43.419 [INFO    ] private_gpt.components.llm.llm_component - Initializing the LLM in mode=local
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /home/devel/Projects/privateGPT/models/mistral-7b-instruct-v0.1.Q4_K_M.gguf (version GGUF V2)

llm_load_print_meta: model ftype      = mostly Q4_K - Medium
llm_load_print_meta: model params     = 7.24 B
llm_load_print_meta: model size       = 4.07 GiB (4.83 BPW) 
llm_load_print_meta: general.name   = mistralai_mistral-7b-instruct-v0.1
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.11 MB
llm_load_tensors: mem required  = 4165.47 MB
...............................................................................................
llama_new_context_with_model: n_ctx      = 3900
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size  =  487.50 MB
llama_build_graph: non-view tensors processed: 740/740
llama_new_context_with_model: compute buffer total size = 276.93 MB
AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | 
16:43:44.478 [INFO    ] private_gpt.components.embedding.embedding_component - Initializing the embedding model in mode=local
16:43:47.708 [WARNING ]               py.warnings - /home/devel/Projects/privateGPT/.venv/lib/python3.11/site-packages/torch/cuda/__init__.py:138: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 11030). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.)
  return torch._C._cuda_getDeviceCount() > 0

[nltk_data] Downloading package punkt to /tmp/llama_index...
[nltk_data]   Unzipping tokenizers/punkt.zip.
16:43:57.259 [INFO    ] llama_index.indices.loading - Loading all indices.
16:43:57.259 [INFO    ] private_gpt.components.ingest.ingest_component - Creating a new vector store index
Parsing nodes: 0it [00:00, ?it/s]
Generating embeddings: 0it [00:00, ?it/s]
16:43:57.413 [INFO    ]         private_gpt.ui.ui - Mounting the gradio UI, at path=/
16:43:57.468 [INFO    ]             uvicorn.error - Started server process [25657]
16:43:57.468 [INFO    ]             uvicorn.error - Waiting for application startup.
16:43:57.469 [INFO    ]             uvicorn.error - Application startup complete.
16:43:57.469 [INFO    ]             uvicorn.error - Uvicorn running on http://0.0.0.0:8001 (Press CTRL+C to quit)

[github-actions[bot]]

Stale issue

[amoyosore]

I ran into the same problem on a Windows 10 machine

[github-actions[bot]]

Stale issue

[PieBru]

Same problem here in Arch Linux, using this docker-compose.yaml :

version: '3.9'

services:
  # https://hub.docker.com/r/3x3cut0r/privategpt
  privategpt:
    image: docker.io/3x3cut0r/privategpt:latest
    container_name: privategpt
    environment:
      KEEP_FILES="true"
      LOCAL_LLM_HF_REPO_ID="TheBloke/dolphin-2.6-mistral-7B-GGUF"
      LOCAL_LLM_HF_MODEL_FILE="dolphin-2.6-mistral-7b.Q4_K_M.gguf"
      EMBEDDING_INGEST_MODE="parallel"
      EMBEDDING_COUNT_WORKERS="4"
    volumes:
      - /home/piero/Piero/AI_Lab/LLM/GGUF/dolphin-2.6-mistral-7B-GGUF/dolphin-2.6-mistral-7b.Q4_K_M.gguf:/home/worker/app/models/dolphin-2.6-mistral-7b.Q4_K_M.gguf
    ports:
      - 8080:8080/tcp

The container log (uvicorn.error are INFO, not real errors):

[nltk_data]   Unzipping tokenizers/punkt.zip.
07:29:50.687 [INFO    ] llama_index.indices.loading - Loading all indices.
07:29:50.687 [INFO    ] private_gpt.components.ingest.ingest_component - Creating a new vector store index
Parsing nodes: 0it [00:00, ?it/s]
Generating embeddings: 0it [00:00, ?it/s]
07:29:50.837 [INFO    ]         private_gpt.ui.ui - Mounting the gradio UI, at path=/
07:29:50.905 [INFO    ]             uvicorn.error - Started server process [64]
07:29:50.905 [INFO    ]             uvicorn.error - Waiting for application startup.
07:29:50.906 [INFO    ]             uvicorn.error - Application startup complete.
07:29:50.907 [INFO    ]             uvicorn.error - Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)

Hints? Thank you, Piero