getmetal / motorhead

🧠 Motorhead is a memory and information retrieval server for LLMs.
https://getmetal.io
Apache License 2.0
843 stars 79 forks source link

Sweep: Deployed to railway, getting internal server errors #106

Closed n0lawz closed 6 months ago

n0lawz commented 7 months ago

Details

Successfully deployed Motorhead to railway and connected it with a redis instance that connected to redis cloud. This is the context in which im using it:

Lanchain Motorhead memory integration

im using this in the context of an llm to store chat message history and i am getting cors errors in my frontend related to this somehow. when i use someone elses hosted instance of this same repository, it works. is there any reason I would need to add config to utilize this as a memory service? i have my api and motorhead deployed on railway , a frontend on vercel, and these are the errors i see in the motorhead logs on railway, slightly redacted:

[2024-01-13T21:08:14Z INFO actix_web::middleware::logger] 192.168.0.4 "GET /favicon.ico HTTP/1.1" 404 0 "[URL](DEPLOYED_URL); "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" 0.000047 [2024-01-13T21:13:31Z INFO actix_web::middleware::logger] 192.168.0.2 "GET /sessions/d11c80c5-3c77-4ff1-b2ba-4fec4d1d6b97-e68dab4e-6017-45e1-9510-3763c5d72111/memory HTTP/1.1" 500 30 "-" "python-requests/2.31.0" 0.021157

Any ideas why this is happening? im passing the url to my deployed instance of motorhead through as an env variable and when i swap it out with a different url, it works fine so im confident its not an error in the code, but rather something wrong with my hosting config.