Hey there,
I succesfully installed Chat with RTX on my computer (i9 RTX3090Ti 32GB RAM and enough disk size). It installed correctly but when I click program I got this error below:
Any suggestion to fix this ?
Environment path found: C:\Users\mehmet\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": true,
"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",
"nodataset"
],
"selected": "directory",
"path": "dataset",
"isRelative": true
},
"strings": {
"directory": "Folder Path",
"nodataset": "AI model default"
}
}
[03/25/2024-12:33:38] You try to use a model that was created with version 2.5.1, however, your version is 2.2.2. This might cause unexpected behavior or errors. In that case, try to update to the latest version.
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ C:\Users\mehmet\AppData\Local\NVIDIA\ChatWithRTX\RAG\trt-llm-rag-windows-main\app.py:109 in │
│ <module> │
│ │
│ 106 ) │
│ 107 │
│ 108 # create embeddings model object │
│ ❱ 109 embed_model = HuggingFaceEmbeddings(model_name=embedded_model) │
│ 110 service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model, │
│ 111 │ │ │ │ │ │ │ │ │ │ │ context_window=model_config["max_input_to │
│ 112 │ │ │ │ │ │ │ │ │ │ │ chunk_overlap=200) │
│ │
│ C:\Users\mehmet\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\langchain\embeddi │
│ ngs\huggingface.py:66 in __init__ │
│ │
│ 63 │ │ │ │ "Please install it with `pip install sentence-transformers`." │
│ 64 │ │ │ ) from exc │
│ 65 │ │ │
│ ❱ 66 │ │ self.client = sentence_transformers.SentenceTransformer( │
│ 67 │ │ │ self.model_name, cache_folder=self.cache_folder, **self.model_kwargs │
│ 68 │ │ ) │
│ 69 │
│ │
│ C:\Users\mehmet\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\sentence_transfor │
│ mers\SentenceTransformer.py:95 in __init__ │
│ │
│ 92 │ │ │ │ │ │ │ │ │ │ use_auth_token=use_auth_token) │
│ 93 │ │ │ │
│ 94 │ │ │ if os.path.exists(os.path.join(model_path, 'modules.json')): #Load as Sen │
│ ❱ 95 │ │ │ │ modules = self._load_sbert_model(model_path) │
│ 96 │ │ │ else: #Load with AutoModel │
│ 97 │ │ │ │ modules = self._load_auto_model(model_path) │
│ 98 │
│ │
│ C:\Users\mehmet\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\sentence_transfor │
│ mers\SentenceTransformer.py:840 in _load_sbert_model │
│ │
│ 837 │ │ modules = OrderedDict() │
│ 838 │ │ for module_config in modules_config: │
│ 839 │ │ │ module_class = import_from_string(module_config['type']) │
│ ❱ 840 │ │ │ module = module_class.load(os.path.join(model_path, module_config['path'])) │
│ 841 │ │ │ modules[module_config['name']] = module │
│ 842 │ │ │
│ 843 │ │ return modules │
│ │
│ C:\Users\mehmet\AppData\Local\NVIDIA\ChatWithRTX\env_nvd_rag\lib\site-packages\sentence_transfor │
│ mers\models\Pooling.py:120 in load │
│ │
│ 117 │ │ with open(os.path.join(input_path, 'config.json')) as fIn: │
│ 118 │ │ │ config = json.load(fIn) │
│ 119 │ │ │
│ ❱ 120 │ │ return Pooling(**config) │
│ 121 │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: Pooling.__init__() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'
Press any key to continue . . .