It takes a long time to deploy and can't be stopped deploying for a whole dayy

[Jane1702]

I deployed the application on Streamlit, but it took more than 1 day and couldn’t finish.

support client

This is my file requirements.txt:
langchain
langchain-community
pysqlite3-binary
#streamlit==1.28.0
streamlit
requests
#llama_index
openai
#docx2txt
unstructured
unstructured[docx]
unstructured[pdf]
opencv-python-headless
chromadb
tiktoken
tesseract
pytesseract==0.3.8

This is my file packages.txt:
libgl1
poppler-utils
tesseract-ocr
tesseract-ocr-por

[08:07:11] Python dependencies were installed from /mount/src/support-client/requirements.txt using pip.
Check if streamlit is installed
Streamlit is already installed
[08:07:13] Processed dependencies!

/home/adminuser/venv/lib/python3.9/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class langchain_community.embeddings.openai.OpenAIEmbeddings was deprecated in langchain-community 0.0.9 and will be removed in 0.2.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run pip install -U langchain-openai and import as from langchain_openai import OpenAIEmbeddings.
warn_deprecated(
[nltk_data] Downloading package punkt to /home/appuser/nltk_data…
[nltk_data] Unzipping tokenizers/punkt.zip.
[nltk_data] Downloading package averaged_perceptron_tagger to
[nltk_data] /home/appuser/nltk_data…
[nltk_data] Unzipping taggers/averaged_perceptron_tagger.zip.
This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
Some weights of the model checkpoint at microsoft/table-transformer-structure-recognition were not used when initializing TableTransformerForObjectDetection: [‘model.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked’, ‘model.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked’, ‘model.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked’]

• This IS expected if you are initializing TableTransformerForObjectDetection from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing TableTransformerForObjectDetection from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  2024-04-16 08:09:12.059 503 GET /script-health-check (10.12.122.60) 60058.59ms
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  2024-04-16 08:10:12.378 503 GET /script-health-check (10.12.122.60) 60050.45ms
  2024-04-16 08:11:12.838 503 GET /script-health-check (10.12.122.60) 60076.18ms
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name
  This function will be deprecated in a future release and unstructured will simply use the DEFAULT_MODEL from unstructured_inference.model.base to set default model name

[tonykip]

Hi @Jane1702,

Thanks for sharing this question!

The app seems to be up and running now.

[Jane1702]

But it’s like a lottery; it may break at any time and start working again after a few days.

[Jane1702]

Similar to the issue with this application, it worked yesterday, but today it broke.

test app 2nov