Streamlit app runs fine on local Windows PC from command line but produces errors on streamlit.io

Deployment
1

Hi,

GitHub - scooter7/web runs fine locally on my windows PC from command line.

But, running on streamlit.io produces the following errors:

Traceback (most recent call last):

  File "/home/appuser/venv/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script

    exec(code, module.__dict__)

  File "/app/web/webqaapp.py", line 118, in <module>

    response = chatbot(input_text)

               ^^^^^^^^^^^^^^^^^^^

  File "/app/web/webqaapp.py", line 75, in chatbot

    response = chain(prompt)

               ^^^^^^^^^^^^^

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/chains/base.py", line 140, in __call__

    raise e

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/chains/base.py", line 134, in __call__

    self._call(inputs, run_manager=run_manager)

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/chains/qa_with_sources/base.py", line 127, in _call

    docs = self._get_docs(inputs)

           ^^^^^^^^^^^^^^^^^^^^^^

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/chains/qa_with_sources/vector_db.py", line 50, in _get_docs

    docs = self.vectorstore.similarity_search(

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/vectorstores/faiss.py", line 226, in similarity_search

    docs_and_scores = self.similarity_search_with_score(query, k)

                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/vectorstores/faiss.py", line 196, in similarity_search_with_score

    docs = self.similarity_search_with_score_by_vector(embedding, k)

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/appuser/venv/lib/python3.11/site-packages/langchain/vectorstores/faiss.py", line 170, in similarity_search_with_score_by_vector

    scores, indices = self.index.search(np.array([embedding], dtype=np.float32), k)

                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

TypeError: IndexFlat.search() missing 3 required positional arguments: 'k', 'distances', and 'labels'
2

The streamlit app can be found at https://scooter7-web-webqaapp-z4qer5.streamlit.app/

3

It is bug in langchain of FAISS. See:

Solution is to recreate your embeddings in the environment you run you code.

4

This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.