Skip to content
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

调用agent查询本地知识库报错:APIError: Caught exception: An error occurred during streaming #4703

Closed
jersonal opened this issue Aug 9, 2024 · 5 comments
Labels
bug Something isn't working stale

Comments

@jersonal
Copy link

jersonal commented Aug 9, 2024

问题描述 / Problem Description
调用agent查询本地知识库报错:
chatchat终端报错信息:

Entering new AgentExecutor chain...
INFO: 127.0.0.1:38928 - "POST /v1/chat/completions HTTP/1.1" 200 OK
2024-08-09 09:18:30,390 httpx 22987 INFO HTTP Request: POST http://127.0.0.1:7861/v1/chat/completions "HTTP/1.1 200 OK"
2024-08-09 09:18:30,398 httpx 22987 INFO HTTP Request: POST http://127.0.0.1:9997/v1/chat/completions "HTTP/1.1 200 OK"
2024-08-09 09:18:31.734 | ERROR | chatchat.server.api_server.openai_routes:generator:105 - openai request error: An error occurred during streaming
2024-08-09 09:18:31.758 | ERROR | chatchat.server.utils:wrap_done:46 - APIError: Caught exception: An error occurred during streaming

chatchat 可视化web页面报错信息:
问:大模型在推理过程中有哪些优化显存的策略
答:这个问题涉及到大模型的优化策略,我需要调用一下大模型优化的知识库来回答这个问题。
An error occurred during streaming
image

xinference报错信息:
2024-08-09 09:18:31,730 xinference.api.restful_api 11477 ERROR Chat completion stream got an error: [address=0.0.0.0:45209, pid=12401] unhashable type: 'slice'
Traceback (most recent call last):
File "/home/envs/xinference/lib/python3.10/site-packages/xinference/model/llm/utils.py", line 587, in _to_chat_completion_chunks
for i, chunk in enumerate(chunks):
File "/home/envs/xinference/lib/python3.10/site-packages/xinference/model/llm/pytorch/chatglm.py", line 497, in _stream_generator
chunk_text = chunk_text[last_chunk_text_length:]
TypeError: [address=0.0.0.0:45209, pid=12401] unhashable type: 'slice'
image
image

复现问题的步骤 / Steps to Reproduce

  1. 执行 startup.py
  2. 页面点击启动Agent、显示Agent过程、选择工具为 本地知识库
  3. 对话框输入问题
  4. 回答:这个问题涉及到大模型的优化策略,我需要调用一下大模型优化的知识库来回答这个问题。后报错:An error occurred during streaming

环境信息 / Environment Information

  • Langchain-Chatchat 版本 / commit 号:0.3.1.3
  • 部署方式(pypi 安装 / 源码部署 / docker 部署): dev deployment
  • 使用的模型推理框架(Xinference / Ollama / OpenAI API 等):Xinference
  • 使用的 LLM 模型(GLM-4-9B / Qwen2-7B-Instruct 等):chatglm3
  • 使用的 Embedding 模型(bge-large-zh-v1.5 / m3e-base 等):bge-large-zh-v1.5
  • 使用的向量库类型 (faiss / milvus / pg_vector 等): faiss
  • 操作系统及版本 / Operating system and version: Ubuntu20.04
  • Python 版本 / Python version: 3.10.12
  • 推理使用的硬件(GPU / CPU / MPS / NPU 等) / Inference hardware (GPU / CPU / MPS / NPU, etc.): GPU
@jersonal jersonal added the bug Something isn't working label Aug 9, 2024
@zik-iiio
Copy link

zik-iiio commented Aug 9, 2024

我也是,用的chatglm3 + bge large 也是报错An error occurred during streaming
换成qwen虽然不报错 但不知道为什么卡的不行

@sy960923
Copy link

有解决办法嘛

@zik-iiio
Copy link

有解决办法嘛
不用transformers换成vllm启动试试

Copy link

这个问题已经被标记为 stale ,因为它已经超过 30 天没有任何活动。

@github-actions github-actions bot added the stale label Sep 13, 2024
Copy link

这个问题已经被自动关闭,因为它被标为 stale 后超过 14 天没有任何活动。

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

No branches or pull requests

3 participants