vyokky

Hi @James4Ever0, thanks for getting in touch. We are defenitely interested in training a local model to enable faster inference. Would you minding sharing more context and perhaps a snippet...

> i guess i can work on it a small fix to handle self.plan as a list should be > > ``` > s="" > if isinstance(response_json["Plan"],list): > for i...

> At [string formatting in flows.py for self.plan](https://github.com/microsoft/UFO/blob/8be10dc4c73963c6c7b316668647b0dea4b661e3/ufo/module/flow.py#L115C22-L115C104) there is a .replace() operation called. Sometimes the model returns self.plan as a list. In such cases an error is thrown because...

Hi, This is a small bug and now has been fixed. Please try again.

> The dataset "Telecommunications - SMS, Call, Internet - MI " only provides the telecommunication activity ,i dont know how to obtain the traffic consumption.Is it related to the other...

Hi, To generate the npy file, you will need to construct grids (100×100) and cast the traffic values to their corresponding coordinates according to their cell id. You may need...

> sorry to bother you again. > I'm using python=3.6, cuda=9.0 tensorflow=1.12.0. > I've tired multiple version of tensorlayer. 1.1.1, 1.3.10, 1.7.1, 1.9.1 > all reports bug. > such as...

> Created a config.yaml and populated with API key and "gpt-4-vision-preview" as the model as per the instructions, but am getting the following error: Step 0: Selecting an application. Error...

> Trying to use openai, here's my config: API_TYPE: "openai" OPENAI_API_BASE: "https://api.openai.com/v1/chat/completions" # The base URL for the OpenAI API OPENAI_API_KEY: "###" # Set the value to the openai key...

> I'm not sure I follow, in my config above, it is 'https://', no? With the above config, does it still report 'Error making API request: Invalid URL 'YOUR_ENDPOINT': No...