[Bug]: Exception in calling the gpustack API interface

[Navichiong]

Is there an existing issue for the same bug?

• I have checked the existing issues.

RAGFlow workspace code commit ID

null

RAGFlow image version

v0.16.0 slim

Other environment information

Actual behavior

When I was conducting a search test in the knowledge base, RagFlow reported the following gpustack API API call exception. I have confirmed that there is no problem with the configuration because the interface can be called normally by dify

ragflow-server | 2025-03-04 08:43:55,499 ERROR 18 500 Server Error: Internal Server Error for url: http://14.116.156.241:9997/v1/rerank
ragflow-server | Traceback (most recent call last):
ragflow-server | File "/ragflow/api/apps/chunk_app.py", line 305, in retrieval_test
ragflow-server | ranks = settings.retrievaler.retrieval(question, embd_mdl, tenant_ids, kb_ids, page, size,
ragflow-server | File "<@beartype(rag.nlp.search.Dealer.retrieval) at 0x7fd32d4a5e10>", line 35, in retrieval
ragflow-server | File "/ragflow/rag/nlp/search.py", line 366, in retrieval
ragflow-server | sim, tsim, vsim = self.rerank_by_model(rerank_mdl,
ragflow-server | File "<@beartype(rag.nlp.search.Dealer.rerank_by_model) at 0x7fd32d4a5cf0>", line 35, in rerank_by_model
ragflow-server | File "/ragflow/rag/nlp/search.py", line 327, in rerank_by_model
ragflow-server | vtsim, _ = rerank_mdl.similarity(query, [rmSpace(" ".join(tks)) for tks in ins_tw])
ragflow-server | File "<@beartype(api.db.services.llm_service.LLMBundle.similarity) at 0x7fd31d413520>", line 50, in similarity
ragflow-server | File "/ragflow/api/db/services/llm_service.py", line 254, in similarity
ragflow-server | sim, used_tokens = self.mdl.similarity(query, texts)
ragflow-server | File "<@beartype(rag.llm.rerank_model.GPUStackRerank.similarity) at 0x7fd31de5a170>", line 50, in similarity
ragflow-server | File "/ragflow/rag/llm/rerank_model.py", line 505, in similarity
ragflow-server | response.raise_for_status()
ragflow-server | File "/ragflow/.venv/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status
ragflow-server | raise HTTPError(http_error_msg, response=self)
ragflow-server | requests.exceptions.HTTPError: 500 Server Error: Internal Server Error for url: http://14.116.156.241:9997/v1/rerank

Expected behavior

No response

Steps to reproduce

gpustack api error

Additional information

No response

[KevinHuSh]

Could you paste the error log of GPUStack here since error did not happend in RAGFlow?