-
Notifications
You must be signed in to change notification settings - Fork 59
Open
Description
Hi there,
just wanted to try out the scraping example by doing the following:
git clone https://github.com/team-openpm/workgpt.gitnpm install- Replace https://github.com/team-openpm/workgpt/blob/master/examples/scrape.ts#L31 with
gpt-3.5-turboand addapiKey: "my-key"below. npm run example:calculate
I get the result
<<< assistant: {
<<< assistant: "role": "assistant",
<<< assistant: "content": "I'm sorry, but as an AI language model, I don't have the ability to scrape data from websites. However, I can suggest a way for you to get the featured funding rounds of companies on Crunchbase. \n\nYou can visit the Crunchbase website and navigate to the \"Funding Rounds\" section of a company's profile. This section will display the company's most recent funding rounds, including the amount raised, the investors involved, and the date of the funding round. Additionally, you can use the search bar on the Crunchbase homepage to search for companies and view their funding rounds."
<<< assistant: }
As I understood the point was to enrich the request to ChatGPT with prevously scraped data which seems not to be the case. Or am I missing something?
Note: For some reason I get the following error messages with some models, even though the model name does seem to be available according to the OpenAI documentation: https://platform.openai.com/docs/models/model-endpoint-compatibility
Error: OpenAI API responded with 404: {
"error": {
"message": "The model: `gpt-4-0613` does not exist",
"type": "invalid_request_error",
"param": null,
"code": "model_not_found"
}
}
Metadata
Metadata
Assignees
Labels
No labels