gustavz/datachad

Ask questions about any data source by leveraging langchains

datachad's Issues

Can't able to open site

Import error

Hi Gustav,

I built your project with Docker Desktop and ran it. However, it gives the following error:

ImportError: cannot import name 'get_openai_token_cost_for_model' from 'langchain.callbacks.openai_info' (/usr/local/lib/python3.10/site-packages/langchain/callbacks/openai_info.py)

Traceback:

File "/usr/local/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script
    exec(code, module.__dict__)
File "/app/app.py", line 1, in <module>
    from datachad.streamlit.helper import init_session_state
File "/app/datachad/streamlit/helper.py", line 8, in <module>
    from langchain.callbacks.openai_info import get_openai_token_cost_for_model

I tried the solution here, but it still gives the same error.

I was wondering if you have any thought on this error. Many thanks in advance!

knowledge base

Hello Gustav.

I would like to understand if it's possible to put several source of different nature inside the same knowledge base.

For what i read in the doc, this is doable only for multiple pdf loading but it would be great to combine different source types as well.

Thanks

ERROR: "Dataset does not exist at the specified path..."

I am getting the following error anytime I start the app locally, or once it is running locally and I try to upload my own documents.

Failed to build chain for data source 'https://github.com/gustavz/DataChad.git' with error: A dataset does not exist at the specified path, or you do not have sufficient permissions to load or create one. Please check the dataset path and make sure that you have sufficient permissions to the path.

I am guessing this has to do with my activeloop account, but I am unable to figure out where to enable permissions for datasets to be created in activeloop. Am I missing something obvious?

Question: Is this project easily adjustable to use different model sources?

I really like the look of this project and want to use it but I am using it for a company project and we don't have a corporate account with OpenAI but rather I have a gpt-3.5-turbo model deployed to our azure AI portal can I use that with your project?

How would you describe this project ?

I have created a similar chatbot using your repo as base repo

how would you describe your project in terms of 3 points :

• Action
• Numbers
• Result

Is there conversational memory, or just document retrieval? (Question)

Since ConversationBufferMemory is not used, wondering if/how there is conversational memory. Sorry if dumb question. Appreciate this work. Thanks

Issue with Local Deployment (Ignore - I am the issue. It is me.)

Running with .env set locally, with python 3.10.9. Requirements installed. Not sure what the issue is. I'm probably just doing something stupid.

streamlit run app.py [ARGUMENTS]
2023-05-26 15:38:22.241 Session state does not function when running a script without streamlit run
Error in sys.excepthook:
Traceback (most recent call last):
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/humbug/report.py", line 540, in _hook
self.error_report(error=exception_instance, tags=tags, publish=publish)
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/humbug/report.py", line 274, in error_report
traceback.format_exception(
TypeError: format_exception() got an unexpected keyword argument 'etype'

Original exception was:
Traceback (most recent call last):
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/streamlit/runtime/state/session_state.py", line 376, in getitem
return self._getitem(widget_id, key)
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/streamlit/runtime/state/session_state.py", line 421, in _getitem
raise KeyError
KeyError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/home/pytorch-test/DataChad/app.py", line 205, in
authentication_form()
File "/Users/home/pytorch-test/DataChad/app.py", line 92, in authentication_form
f"{st.session_state['mode']} API Key",
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/streamlit/runtime/state/session_state_proxy.py", line 90, in getitem
return get_session_state()[key]
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/streamlit/runtime/state/safe_session_state.py", line 113, in getitem
return self._state[key]
File "/Users/home/.pyenv/versions/DataChad/lib/python3.10/site-packages/streamlit/runtime/state/session_state.py", line 378, in getitem
raise KeyError(_missing_key_error_message(key))
KeyError: 'st.session_state has no key "mode". Did you forget to initialize it? More info: https://docs.streamlit.io/library/advanced-features/session-state#initialization'

Using LocalMode - error getting - Failed to build chain for data source **data\data.txt** with model **GPT4All**

Hi,

I am trying to run this in LocalMode and error getting - Failed to build chain for data source data\data.txt with model GPT4All. Please help me.

hkunlp/instructor-xl Integrations Error

Solved