AutoGPT
AutoGPT copied to clipboard
Significant-Gravitas
AutoGPT still runs on local memory after Having set up Pinecone?
Duplicates
- [X] I have searched the existing issues
Summary 💡
it should run on Pinecone instead of local memory.
Examples 🌈
MEMORY_BACKEND - Memory backend type
local - Default
pinecone - Pinecone (if configured)
redis - Redis (if configured)
milvus - Milvus (if configured)
MEMORY_INDEX - Name of index created in Memory backend (Default: auto-gpt)
MEMORY_BACKEND=pinecone
MEMORY_INDEX=auto-gpt
PINECONE
PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key)
PINECONE_ENV - Pinecone environment (region) (Example: us-west-2)
PINECONE_API_KEY=2ab9e0a1-fffe-4797-bd65-2957a3b9f200
PINECONE_ENV=us-west4-gcp
Motivation 🔦
No response
I'll look into this today, send me your .env file and make sure its not .env.temp
Delete your API its like a password. But I had the same problem, even when I set it up with docker redis it just kept on using local memory.
the same issue for me. also speech mode doesn't work after setting it up right
what is your command line for starting? run --gpt3only --use-memory=pinecone
Check this portion of the .env file it needs to be changed from local to pinecone.
MEMORY_BACKEND - Memory backend type
local - Default
pinecone - Pinecone (if configured)
redis - Redis (if configured)
milvus - Milvus (if configured)
MEMORY_BACKEND=pinecone
Oh, so in the new version you have to tell autoGTP in the command line which memory it should use? If so, I'll try it later if that solves my problem.
if you just downloaded it today, check that your .env file doesnt have those lines commented out. in 0.2.2 for some reason, damn near everything was commented out for me
I can confirm on 0.2.2 and even on master, settings in .env didn't take it was overwritten it appears and went back to local but does work when you use the CLI options py -m autogtp --use-memory=pinecone
Work with the groups in #tech-support in discord to get this fixed. Closing here for now
Guys, thanks for your input, I have reinstall autogpt on my laptop (windows11) strictly following the steps and run it with .\run.bat;
Here is the error:FAILED TO CONNECT TO PINECONE HTTPSConnectionPool(host='controller.%3cus-west4-gcp%3e.pinecone.io', port=443): Max retries exceeded with url: /actions/whoami (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:997)')))
DOUBLE CHECK CONFIGURATION Please ensure you have setup and configured Pinecone properly for use.You can check out https://github.com/Torantulino/Auto-GPT#-pinecone-api-key-setup to ensure you've set up everything correctly.
same issue for me won't use pinecone I will try that command , do you suppose to use the same command format when trying to use elevenlabs voice ?
