louis-li / sqlgpt Goto Github PK

As described in the title, it would be great if you could add support for these models as well as they are becoming more widely available!

create_azure_sql.txt

Traceback (most recent call last):
application_1 | File "/usr/local/lib/python3.10/site-packages/gunicorn/workers/sync.py", line 136, in handle
application_1 | self.handle_request(listener, req, client, addr)
application_1 | File "/usr/local/lib/python3.10/site-packages/gunicorn/workers/sync.py", line 179, in handle_request
application_1 | respiter = self.wsgi(environ, resp.start_response)
application_1 | File "/usr/local/lib/python3.10/site-packages/flask/app.py", line 2551, in call
application_1 | return self.wsgi_app(environ, start_response)
application_1 | File "/usr/local/lib/python3.10/site-packages/flask/app.py", line 2531, in wsgi_app
application_1 | response = self.handle_exception(e)
application_1 | File "/usr/local/lib/python3.10/site-packages/flask/app.py", line 2528, in wsgi_app
application_1 | response = self.full_dispatch_request()
application_1 | File "/usr/local/lib/python3.10/site-packages/flask/app.py", line 1825, in full_dispatch_request
application_1 | rv = self.handle_user_exception(e)
application_1 | File "/usr/local/lib/python3.10/site-packages/flask/app.py", line 1823, in full_dispatch_request
application_1 | rv = self.dispatch_request()
application_1 | File "/usr/local/lib/python3.10/site-packages/flask/app.py", line 1799, in dispatch_request
application_1 | return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
application_1 | File "/app/app.py", line 77, in api_answer
application_1 | os.environ['OPENAI_API_BASE']= get_value(data['openai_base'], "OPENAI_API_BASE")
application_1 | File "/usr/local/lib/python3.10/os.py", line 685, in setitem
application_1 | value = self.encodevalue(value)
application_1 | File "/usr/local/lib/python3.10/os.py", line 757, in encode
application_1 | raise TypeError("str expected, not %s" % type(value).name)
application_1 | TypeError: str expected, not NoneType

Retrying langchain.llms.openai.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised APIError: HTTP code 502 from API ()

Getting the below error:
Traceback (most recent call last):
sqlgpt-main-application-1 | File "/app/app.py", line 92, in api_answer
sqlgpt-main-application-1 | answer, thought = sql_agent.run(question)
sqlgpt-main-application-1 | File "/app/AzureOpenAIUtil/SqlServer.py", line 30, in run
sqlgpt-main-application-1 | answer = self.agent_executor.run(text)
sqlgpt-main-application-1 | File "/usr/local/lib/python3.10/site-packages/langchain/chains/base.py", line 213, in run
sqlgpt-main-application-1 | return self(args[0])[self.output_keys[0]]
sqlgpt-main-application-1 | File "/usr/local/lib/python3.10/site-packages/langchain/chains/base.py", line 116, in _call

Just forked and tried to run and got this error.
Already fixed using SQLAchemy.

schema: dbo
Traceback (most recent call last):
File "/mnt/c/DEV/SqlGPT/application/app.py", line 92, in api_answer
answer, thought = sql_agent.run(question)
File "/mnt/c/DEV/SqlGPT/application/AzureOpenAIUtil/SqlServer.py", line 43, in run
answer = self.agent_executor.run(text)

Hi,
Is it possible to output the answer without the suffix (get only the database answer)? I just want to remove that from the application.

Thank you.