Chat with RTX setup issue

AI & Data Science AI Foundation Models and Endpoints
1

Hi
I encountered the following error after launching Chat with RTX, does anyone know how to fix it?

gradio.exceptions.Error: ‘Invalid session’

System Information
RTX4080
Driver Version: 551.23

Here is the full error log for your reference:

Environment path found: C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag
App running with config
 {
    "models": {
        "supported": [
            {
                "name": "Mistral 7B int4",
                "installed": true,
                "metadata": {
                    "model_path": "model\\mistral\\mistral7b_int4_engine",
                    "engine": "llama_float16_tp1_rank0.engine",
                    "tokenizer_path": "model\\mistral\\mistral7b_hf",
                    "max_new_tokens": 1024,
                    "max_input_token": 7168,
                    "temperature": 0.1
                }
            },
            {
                "name": "Llama 2 13B int4",
                "installed": false,
                "metadata": {
                    "model_path": "model\\llama\\llama13_int4_engine",
                    "engine": "llama_float16_tp1_rank0.engine",
                    "tokenizer_path": "model\\llama\\llama13_hf",
                    "max_new_tokens": 1024,
                    "max_input_token": 3900,
                    "temperature": 0.1
                }
            }
        ],
        "selected": "Mistral 7B int4"
    },
    "sample_questions": [
        {
            "query": "How does NVIDIA ACE generate emotional responses?"
        },
        {
            "query": "What is Portal prelude RTX?"
        },
        {
            "query": "What is important about Half Life 2 RTX?"
        },
        {
            "query": "When is the launch date for Ratchet & Clank: Rift Apart on PC?"
        }
    ],
    "dataset": {
        "sources": [
            "directory",
            "youtube",
            "nodataset"
        ],
        "selected": "directory",
        "path": "dataset",
        "isRelative": true
    },
    "strings": {
        "directory": "Folder Path",
        "youtube": "YouTube URL",
        "nodataset": "AI model default"
    }
}
[02/15/2024-00:15:55] No sentence-transformers model found with name C:\Users\lzlal/.cache\torch\sentence_transformers\WhereIsAI_UAE-Large-V1. Creating a new one with MEAN pooling.
Using the persisted value form dataset_vector_embedding
The file at ./config/preferences.json does not exist.
Open http://127.0.0.1:5424?cookie=a2b7100d-4a19-4a41-b78b-8fe861f9504a&__theme=dark in browser to start Chat with RTX
Running on local URL:  http://127.0.0.1:5424

To create a public link, set `share=True` in `launch()`.
Traceback (most recent call last):
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\ui\user_interface.py", line 596, in _validate_session_and_raise
    self._validate_request(request)
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\ui\user_interface.py", line 298, in _validate_request
    key, value = cookie.split('=')
ValueError: too many values to unpack (expected 2)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\queueing.py", line 495, in call_prediction
    output = await route_utils.call_process_api(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
    output = await app.get_blocks().process_api(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\blocks.py", line 1561, in process_api
    result = await self.call_function(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\blocks.py", line 1179, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\utils.py", line 678, in wrapper
    response = f(*args, **kwargs)
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\ui\user_interface.py", line 598, in _validate_session_and_raise
    raise gr.Error('Invalid session')
gradio.exceptions.Error: 'Invalid session'
Traceback (most recent call last):
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\ui\user_interface.py", line 596, in _validate_session_and_raise
    self._validate_request(request)
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\ui\user_interface.py", line 298, in _validate_request
    key, value = cookie.split('=')
ValueError: too many values to unpack (expected 2)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\queueing.py", line 495, in call_prediction
    output = await route_utils.call_process_api(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
    output = await app.get_blocks().process_api(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\blocks.py", line 1561, in process_api
    result = await self.call_function(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\blocks.py", line 1179, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\gradio\utils.py", line 678, in wrapper
    response = f(*args, **kwargs)
  File "C:\Users\lzlal\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\ui\user_interface.py", line 598, in _validate_session_and_raise
    raise gr.Error('Invalid session')
gradio.exceptions.Error: 'Invalid session'

image
image1918×891 20.6 KB

2

Please see: Chat with RTX Installation Failure

3

same reaction on Chrome, working fine in Opera

4

I have a laptop with a RTX 3050 Mobile with 4GB memory, BUT it can access up to 20GB of RAM SHARED. Yet when I try to install Chat with RTX it complains and says I need at least 7GB NVIDIA RAM. Is there any way to BYPASS that stop and try to install the system REGARDLESS?

5

Unfortunately those LLMs aren’t able to run from shared memory, only from GPU’s.