Replies: 1 comment 1 reply
-
How are you resolving HTTPS? Likely an NGINX config issue: #3061 (comment) |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi Community !
Hope you are doing well!
I have deployed the librechat helm (https://github.com/bat-bs/helm-charts/tree/main/charts/librechat) to kubernates, now everything is good!
I'm used the OpenAI model and when i upload the file larger than 1 MB, i got the error
But, when test file less than 1MB , everything is good!
here is my config!
Yaml config
# For adding a custom config yaml-file you can set the contents in this var
configYamlContent: |
includedTools: []
version: 1.1.5
endpoints:
custom:
- name: 'TestAI'
# For
apiKey
andbaseURL
, you can use environment variables that you define.# recommended environment variables:
# Known issue: you should not use
OPENROUTER_API_KEY
as it will then override theopenAI
endpoint to use OpenRouter as well.apiKey: 'xx-xx!'
baseURL: 'xxx:9099'
models:
default: ['custom_rag_1', 'openai_pipeline']
fetch: true
titleConvo: true
titleModel: 'Custom RAG'
# Recommended: Drop the stop parameter from the request as Openrouter models use a variety of stop tokens.
dropParams: ['stop']
modelDisplayLabel: 'Kindred AI'
fileConfig:
serverFileSizeLimit: 20 # Global server file size limit in MB
avatarSizeLimit: 2 # Limit for user avatar image size in MB
also, tried https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/file_config
not really solve my problem !
Thank you
Beta Was this translation helpful? Give feedback.
All reactions