search

infiniflow / ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
https://ragflow.io
Apache License 2.0
20.94k stars 2.06k forks source link

[Question]: Do embedding models need to be re-downloaded every time changes are made to docker-compose.yml? #1369

Open NBQian opened 3 months ago

NBQian commented 3 months ago

Describe your problem

I am trying to set up a proxy for my locally run Ragflow by adding these 2 lines in docker-compose.yml under services:ragflow:environment: - http_proxy=http://host.docker.internal:8080 - https_proxy=http://host.docker.internal:8080 however, after running docker compose up -d, it seems like Ragflow is trying to re-download the embedding model and gave this error in the chat: ERROR: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/BAAI/bge-large-zh-v1.5/revision/main (Caused by ProxyError('Unable to connect to proxy', OSError('Tunnel connection failed: 502 Bad Gateway')))"), '(Request ID: 69d0b531-5024-4774-af63-84e360c4dcf7)')

May I check if it's necessary to re-download the embedding models every time when changes are made to docker-compose.yml? Thanks.

guoyuhao2330 commented 3 months ago

You can check to see if it's the same container each time you launch