jayzeedesign / researcher-gpt Goto Github PK

AttributeError: OPENAI_FUNCTIONS
Traceback:
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script
exec(code, module.dict)
File "/Users/lev/Documents/Github/researcher-gpt/app.py", line 169, in
agent=AgentType.OPENAI_FUNCTIONS,
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/enum.py", line 786, in getattr
raise AttributeError(name) from None

import streamlit as st
otherwise

def main():
    st.set_page_config(page_title="AI research agent", page_icon=":bird:")

    st.header("AI research agent :bird:")
    query = st.text_input("Research goal")

    if query:
        st.write("Doing research for ", query)

        result = agent({"input": query})

        st.info(result['output'])

gives error

pip install -r requirements.txt , and I can see Langchain has almot 500 lines installtion .

And it says " Importing PromptTemplate from langchain root module is no longer supported." , by using pip install -r requirements.txt .

Using Langchain is really a pain in the ass .

Hi All,

Get the following error when running app.py:

2023-09-05 20:07:01.187 Uncaught app exception
Traceback (most recent call last):
File "/Users/xxxx/Desktop/GPT_RESEARCHER_PROJECT/myenv/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 552, in _run_script
exec(code, module.dict)
File "/Users/xxxx/Desktop/GPT_RESEARCHER_PROJECT/researcher-gpt/app.py", line 161, in
llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k-0613", openai_api_key=OpenAI_key)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/xxxx/Desktop/GPT_RESEARCHER_PROJECT/myenv/lib/python3.11/site-packages/langchain/load/serializable.py", line 75, in init
super().init(**kwargs)
File "/Users/xxxx/Desktop/GPT_RESEARCHER_PROJECT/myenv/lib/python3.11/site-packages/pydantic/v1/main.py", line 341, in init
raise validation_error
pydantic.v1.error_wrappers.ValidationError: 1 validation error for ChatOpenAI
root
Did not find openai_api_key, please add an environment variable OPENAI_API_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)

Have attempted to define openai_api_key="xxxx" directly as shown but to no avail.

Any help would be greatly appreciated!! Thanks

so everything seems to work (via streamlit) however - browserless isnt called at all for me - meaning the scraper isnt scraping anything. I do get serps and based on those I get outputs.

hello Jason
I tried to turn this into a chat:

`
def main():
st.set_page_config(page_title="search", page_icon=":eagle:")
st.header("search 🦅")

global agent  # Let the function know we're using the global version of agent
i = 0
continue_chat = True
while continue_chat:
    if i > 0:
        query = st.text_input("", key=f'text_input_{i}')
    else:
        query = st.text_input("What would you like to ask about ?", key=f'text_input_{i}')

    if query:
        result = agent({"input": query})
        st.info(result['output'])
        st.download_button('Download result', result['output'])

        # add another query here so we can continue to ask questions
        i += 1

    else:
        continue_chat = False

`

when I start this app, I type a question and get an answer. But when I continue the chat by typing a second question, they answer my first question again before answering the second question. So every time I type a new question, all previous get answered again.

I'm facing an issue replicating the endpoint part in make.com - getting {"detail":"Method Not Allowed"}

All of the other parts are working as expected. Airtable gets populated, but without the research part.