fazhang-master

lobe-chat fails to use ollama

5

### 💻 Operating System Ubuntu ### 📦 Environment Docker ### 🌐 Browser Chrome ### 🐛 Bug Description { "error": { "headers": { "content-length": "18", "content-type": "text/plain", "date": "Mon, 18 Mar...

I don't use ollama in lobechat

14

### 💻 系统环境 Windows ### 📦 部署环境 Official Preview ### 🌐 浏览器 Chrome ### 🐛 问题描述    ### 🚦 期望结果 first, i can run 127.17.0.1:11434,but i don't use...

Gpu not use

2

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...

Traceback (most recent call last): File "/home/zf/Desktop/CMGAN/mask_generator/mask_generator.py", line 310, in image, mask, masked_image = mask_generator(image_fname, anno_seg_fname, anno_json_fname) File "/home/zf/Desktop/CMGAN/mask_generator/mask_generator.py", line 291, in __call__ image_label_, image_label_anno_ = self._load_raw_image_label(anno_seg_fname, anno_json_fname, crop_config=crop_config, panoptic=self._panoptic)...

can't install hic-straw on win11 python3.9

6

(autohic) C:\Users\Administrator>pip install hic-straw -i https://pypi.tuna.tsinghua.edu.cn/simple Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple Collecting hic-straw Using cached https://pypi.tuna.tsinghua.edu.cn/packages/8e/ec/431c76970f8973ea5937a9b5f2d1689a641b3fe6475246a32451274fa2dd/hic-straw-1.3.1.tar.gz (18 kB) Preparing metadata (setup.py) ... done Collecting pybind11>=2.4 (from hic-straw) Using cached https://pypi.tuna.tsinghua.edu.cn/packages/06/55/9f73c32dda93fa4f539fafa268f9504e83c489f460c380371d94296126cd/pybind11-2.11.1-py3-none-any.whl (227...

the check passes, but chatting still fails.

2

   Ollama is running locally, not in Docker. However, after running the lobe-chat Docker container using the following command:docker run -d -p 3210:3210 -e OLLAMA_PROXY_URL=http://127.0.0.1:11434 lobehub/lobe-chat。the check passes,...

I merged vllm with Qdrant and found that many <|im_start|>\n<|im_start|>\n appeared, the model used was Qwen-7B-Chat, and the question inquired was The progress of multimodal models in computer vision, and the vector library used was The official pre-embedded vector

1

(base) root@ubuntu20:~/storm# cd /root/storm ; /usr/bin/env /home/vipuser/anaconda3/envs/storm/bin/python /root/.vscode-server/extensions/ms-python.debugpy-2024.8.0-linux-x64/bundled/libs/debugpy/adapter/../../debugpy/launcher 57355 -- /root/storm/run_storm_wiki_gpt_with_VectorRM.py --url http://0.0.0.0 --port 8000 --output-dir /root/storm/output/ --vector-db-mode offline --offline-vector-db-dir /root/vector_store --device cuda --do-research --do-generate-outline --do-generate-article --do-polish-article topic: related_topics: annotation=NoneType...

Backend streaming api

1

I want to change run_storm_wiki_gpt_with_VectorRM.py to a backend api for streaming output, can you tell me which files/places I should change?

Fix: Prevent redundant OUT column creation and add null check

1

- Moved OUT column creation outside inner loop to avoid redundant operations - Added null check for pdb_records[r] to prevent processing undefined records - Combined performance optimization with robustness improvement...