Python package's ImportErrors

[gmflau]

I ran into some Python package's ImportError issues when running the chat-your-pdf example. Below is the log from the chat-your-pdf-chatbot container:

Collecting usage statistics. To deactivate, set browser.gatherUsageStats to False.
You can now view your Streamlit app in your browser.

Network URL: http://172.22.0.3:8080
External URL: http://76.132.34.138:8080

2023-10-04 20:58:09.068 Uncaught app exception
Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/redisvl/vectorize/text/huggingface.py", line 11, in init
from sentence_transformers import SentenceTransformer
File "/usr/local/lib/python3.9/site-packages/sentence_transformers/init.py", line 3, in
from .datasets import SentencesDataset, ParallelSentencesDataset
File "/usr/local/lib/python3.9/site-packages/sentence_transformers/datasets/init.py", line 1, in
from .DenoisingAutoEncoderDataset import DenoisingAutoEncoderDataset
File "/usr/local/lib/python3.9/site-packages/sentence_transformers/datasets/DenoisingAutoEncoderDataset.py", line 1, in
from torch.utils.data import Dataset
File "/usr/local/lib/python3.9/site-packages/torch/init.py", line 229, in
from torch._C import * # noqa: F403
ImportError: /usr/local/lib/python3.9/site-packages/torch/lib/libtorch_cuda.so: invalid ELF header

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 552, in _run_script
exec(code, module.dict)
File "/app/main.py", line 9, in
from redisvl.llmcache.semantic import SemanticCache
File "/usr/local/lib/python3.9/site-packages/redisvl/llmcache/semantic.py", line 13, in
class SemanticCache(BaseLLMCache):
File "/usr/local/lib/python3.9/site-packages/redisvl/llmcache/semantic.py", line 32, in SemanticCache
vectorizer: Optional[BaseVectorizer] = HFTextVectorizer(
File "/usr/local/lib/python3.9/site-packages/redisvl/vectorize/text/huggingface.py", line 13, in init
raise ImportError(
ImportError: HFTextVectorizer requires sentence-transformers library. Please install with pip install sentence-transformers
2023-10-04 20:58:12.938 Uncaught app exception
Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/redisvl/vectorize/text/huggingface.py", line 11, in init
from sentence_transformers import SentenceTransformer
File "/usr/local/lib/python3.9/site-packages/sentence_transformers/init.py", line 3, in
from .datasets import SentencesDataset, ParallelSentencesDataset
File "/usr/local/lib/python3.9/site-packages/sentence_transformers/datasets/init.py", line 1, in
from .DenoisingAutoEncoderDataset import DenoisingAutoEncoderDataset
File "/usr/local/lib/python3.9/site-packages/sentence_transformers/datasets/DenoisingAutoEncoderDataset.py", line 1, in
from torch.utils.data import Dataset
File "/usr/local/lib/python3.9/site-packages/torch/init.py", line 229, in
from torch._C import * # noqa: F403
ImportError: /usr/local/lib/python3.9/site-packages/torch/lib/libtorch_cuda.so: invalid ELF header

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 552, in _run_script
exec(code, module.dict)
File "/app/main.py", line 9, in
from redisvl.llmcache.semantic import SemanticCache
File "/usr/local/lib/python3.9/site-packages/redisvl/llmcache/semantic.py", line 13, in
class SemanticCache(BaseLLMCache):
File "/usr/local/lib/python3.9/site-packages/redisvl/llmcache/semantic.py", line 32, in SemanticCache
vectorizer: Optional[BaseVectorizer] = HFTextVectorizer(
File "/usr/local/lib/python3.9/site-packages/redisvl/vectorize/text/huggingface.py", line 13, in init
raise ImportError(
ImportError: HFTextVectorizer requires sentence-transformers library. Please install with pip install sentence-transformers

[gmflau]

I fixed it by cleaning the docker build cache in my environment using "$ docker builder prune" command. Then I ran "$ docker compose up" to build and launch the app.