From 5d1803c31d16cca532c8fac274f715727059920e Mon Sep 17 00:00:00 2001 From: Zhenting Gao <40551969+zhentg@users.noreply.github.com> Date: Wed, 24 Apr 2024 12:21:41 +0800 Subject: [PATCH] Add an entry in Debugging section (#481) ### What problem does this PR solve? _Add an entry in Debugging section._ ### Type of change - [x] Documentation Update --------- Co-authored-by: Yingfeng --- docs/faq.md | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/docs/faq.md b/docs/faq.md index 0666d0cbb..affa9fd83 100644 --- a/docs/faq.md +++ b/docs/faq.md @@ -78,7 +78,16 @@ docker build -t infiniflow/ragflow:v0.3.0 . --network host ### 2. Issues with huggingface models. -#### 2.1. `MaxRetryError: HTTPSConnectionPool(host='hf-mirror.com', port=443)` +#### 2.1 If https://huggingface.co can not be accessed + - If RAGflow is installed by docker, it will automatically download the OCR and embedding modules from Huggingface website (https://huggingface.co). + - If your computer can not access https://huggingface.co, such error will appear and PDF file parsing will fail + - FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res' + - if your computer can access https://hf-mirror.com + - cd ragflow-0.3.0/docker/; docker compose down + - replace https://huggingface.co with https://hf-mirror.com in the ragflow-0.3.0/docker/docker-compose.yml + - docker compose up -d + +#### 2.2. `MaxRetryError: HTTPSConnectionPool(host='hf-mirror.com', port=443)` This error suggests that you do not have Internet access or are unable to connect to hf-mirror.com. Try the following: @@ -88,7 +97,7 @@ This error suggests that you do not have Internet access or are unable to connec - ~/deepdoc:/ragflow/rag/res/deepdoc ``` -#### 2.2 `FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/FileNotFoundError: [Errno 2] No such file or directory: '/ragflow/rag/res/deepdoc/ocr.res'be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res'` +#### 2.3 `FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/FileNotFoundError: [Errno 2] No such file or directory: '/ragflow/rag/res/deepdoc/ocr.res'be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res'` 1. Check your network from within Docker, for example: ```bash @@ -165,7 +174,7 @@ If your RAGFlow is deployed *locally*, try the following: ```bash docker logs -f ragflow-server ``` -2. Check if the **tast_executor.py** process exist. +2. Check if the **task_executor.py** process exist. 3. Check if your RAGFlow server can access hf-mirror.com or huggingface.com. @@ -304,7 +313,6 @@ You limit what the system responds to what you specify in **Empty response** if ![](https://github.com/infiniflow/ragflow/assets/93570324/8cfb6fa4-8a97-415d-b9fa-b6f405a055f3) - ### 4. How to run RAGFlow with a locally deployed LLM? You can use Ollama to deploy local LLM. See [here](https://github.com/infiniflow/ragflow/blob/main/docs/ollama.md) for more information.