Closed jeffmercury closed 1 year ago
Yeah I'm also a little confused about how to feed it API keys. It doesn't seem to recognize them whether I set them as environment variables, put them in a text file, or use data_ingestion.py to preseed them
I would like some kind of folder labeled "API Keys" or something that AutoGPT always reads on startup
Or add a custom section to the .env file for user defined API keys
Ideally we shouldn’t even need a folder to house our API creds. The AI should be able to utilize what’s provided in the prompt the user submits. I see there’s a plug-in for sending emails, but this limits the AI, we should be able to use whatever third party API we have access to. Im running my instance through docker as well.
This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.
This issue was closed automatically because it has been stale for 10 days with no activity.
⚠️ Search for existing issues first ⚠️
Which Operating System are you using?
Windows
Which version of Auto-GPT are you using?
Stable (branch)
GPT-3 or GPT-4?
GPT-3.5
Steps to reproduce 🕹
Provide credentials for the API’s you want the AI to use (continuous mode)
Current behavior 😯
I’m attempting to have it send emails via Postmarks email Api. I give it the credentials it needs to call the api. The bot calls the api, but never uses the credentials I provide. It just puts a generic “your_token” when creating the scripts. I even gave it and email to use and it left that out as well.
Expected behavior 🤔
Provide the credentials the AI needs to call your desired API’s, the AI uses the credentials and executes the code correctly.
Your prompt 📝
Your Logs 📒