Skip to content

[BUG] chatchat.init_database:worker:61 - 向量库 samples 加载失败 #5283

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Tara666666 opened this issue Mar 23, 2025 · 1 comment
Closed
Labels
bug Something isn't working

Comments

@Tara666666
Copy link

(mylangch) C:\Users\Jack>chatchat kb -r
recreating all vector stores
C:\Users\Jack\anaconda3\envs\mylangch\lib\site-packages\langchain_api\module_import.py:87: LangChainDeprecationWarning: Importing GuardrailsOutputParser from langchain.output_parsers is deprecated. Please replace the import with the following:
from langchain_community.output_parsers.rail_parser import GuardrailsOutputParser
warnings.warn(
2025-03-23 10:06:11.950 | INFO | chatchat.server.knowledge_base.kb_cache.faiss_cache:load_vector_store:109 - loading vector store in 'samples/vector_store/bge-large-zh-v1.5' from disk.
2025-03-23 10:06:12.339 | ERROR | chatchat.server.knowledge_base.kb_cache.faiss_cache:load_vector_store:140 - Error code: 404 - {'detail': 'Not Found'}
2025-03-23 10:06:12.340 | ERROR | chatchat.init_database:worker:61 - 向量库 samples 加载失败。

@Tara666666 Tara666666 added the bug Something isn't working label Mar 23, 2025
Copy link

dosubot bot commented Mar 23, 2025

The error you're encountering with the vector store 'samples/vector_store/bge-large-zh-v1.5' failing to load with error code 404 is likely due to the default embedding model 'bge-large-zh-v1.5' not being found. To resolve this issue, ensure that the model inference framework and corresponding embedding model are running, and complete the model integration configuration as described in the setup steps.

You can initialize Langchain-Chatchat with specific LLM and embedding models using the following command:

chatchat init -l qwen1.5-chat -e bge-m3 -r

Additionally, verify that the knowledge base path is correctly set in the knowledge_base directory under the path pointed by the DATA_PATH variable. If the vector store 'bge-large-zh-v1.5' is missing, check the directory /root/anaconda3/envs/chatchat/lib/python3.11/site-packages/chatchat/data/knowledge_base/samples/vector_store to ensure the model files are present. If necessary, specify a different text-embedding model during initialization:

cd # Return to the original directory
chatchat-kb -r --embed-model=text-embedding-3-small

For more details, you can refer to the related issue here [1].

To continue talking to Dosu, mention @dosu.


Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant