Error when starting python ingest.py

[Shelushun]

(localgpt) F:\localGPT>python ingest.py
2024-02-29 23:49:13,666 - INFO - ingest.py:147 - Loading documents from F:\localGPT/SOURCE_DOCUMENTS
Importing: METODIChKA_pechat_04_01.pdf
F:\localGPT/SOURCE_DOCUMENTS\METODIChKA_pechat_04_01.pdf loaded.

F:\localGPT/SOURCE_DOCUMENTS\METODIChKA_pechat_04_01.pdf loading error:
No module named 'torchvision'

2024-02-29 23:49:25,149 - INFO - ingest.py:156 - Loaded 1 documents from F:\localGPT/SOURCE_DOCUMENTS
2024-02-29 23:49:25,150 - INFO - ingest.py:157 - Split into 0 chunks of text
2024-02-29 23:49:26,491 - INFO - SentenceTransformer.py:66 - Load pretrained SentenceTransformer: cointegrated/rubert-tiny2
2024-02-29 23:49:28,755 - INFO - ingest.py:168 - Loaded embeddings from cointegrated/rubert-tiny2
Batches: 0it [00:00, ?it/s]
Traceback (most recent call last):
  File "F:\localGPT\ingest.py", line 182, in <module>
    main()
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\click\core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\click\core.py", line 1078, in main
    rv = self.invoke(ctx)
         ^^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\click\core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\click\core.py", line 783, in invoke
    return __callback(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "F:\localGPT\ingest.py", line 170, in main
    db = Chroma.from_documents(
         ^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\langchain\vectorstores\chroma.py", line 613, in from_documents
    return cls.from_texts(
           ^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\langchain\vectorstores\chroma.py", line 577, in from_texts
    chroma_collection.add_texts(texts=texts, metadatas=metadatas, ids=ids)
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\langchain\vectorstores\chroma.py", line 236, in add_texts
    self._collection.upsert(
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\chromadb\api\models\Collection.py", line 294, in upsert
    ids, embeddings, metadatas, documents = self._validate_embedding_set(
                                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\chromadb\api\models\Collection.py", line 342, in _validate_embedding_set
    ids = validate_ids(maybe_cast_one_to_many(ids))
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\Lib\site-packages\chromadb\api\types.py", line 99, in maybe_cast_one_to_many
    if isinstance(target[0], (int, float)):
                  ~~~~~~^^^
IndexError: list index out of range

I use the IlyaGusev/saiga_mistral_7b_guf model

cointegrated/rubert-tiny2 embedding model

[Shelushun]

We managed to get rid of this error by deleting the virtual environment and reinstalling the entire system on Python 3.10 There is no more error when embedding text. But now there is another error when launching the model itself. Although she hadn't been there before.

(localgpt) F:\localGPT>python run_localGPT.py
Traceback (most recent call last):
  File "F:\localGPT\run_localGPT.py", line 24, in <module>
    from load_models import (
  File "F:\localGPT\load_models.py", line 6, in <module>
    from auto_gptq import AutoGPTQForCausalLM
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\auto_gptq\__init__.py", line 4, in <module>
    from .utils.peft_utils import get_gptq_peft_model
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\auto_gptq\utils\peft_utils.py", line 9, in <module>
    from peft import get_peft_model, PeftConfig, PeftModel, PeftType
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\__init__.py", line 22, in <module>
    from .auto import (
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\auto.py", line 32, in <module>
    from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\mapping.py", line 22, in <module>
    from .mixed_model import PeftMixedModel
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\mixed_model.py", line 26, in <module>
    from peft.tuners.mixed import COMPATIBLE_TUNER_TYPES
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\tuners\__init__.py", line 21, in <module>
    from .lora import LoraConfig, LoraModel, LoftQConfig
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\tuners\lora\__init__.py", line 20, in <module>
    from .model import LoraModel
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\tuners\lora\model.py", line 42, in <module>
    from .awq import dispatch_awq
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\peft\tuners\lora\awq.py", line 26, in <module>
    from awq.modules.linear import WQLinear_GEMM
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\awq\__init__.py", line 2, in <module>
    from awq.models.auto import AutoAWQForCausalLM
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\awq\models\__init__.py", line 15, in <module>
    from .mixtral import MixtralAWQForCausalLM
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\awq\models\mixtral.py", line 7, in <module>
    from awq.modules.fused.moe import FusedSparseMoeBlock
  File "C:\Users\Cash\AppData\Local\NVIDIA\MiniConda\envs\localgpt\lib\site-packages\awq\modules\fused\moe.py", line 2, in <module>
    import triton
ModuleNotFoundError: No module named 'triton'