使用Streamlit+LangChain搭建在线AutoGPT应用时遇ImportError求助

我在尝试使用LangChain与Streamlit搭建在线AutoGPT应用时遇到如下错误：

终端执行的命令：

streamlit run /Users/*username*/opt/anaconda3/lib/python3.9/site-packages/ipykernel_launcher.py

返回的报错信息：

Traceback (most recent call last):
  File "/Users/*username*/.pyenv/versions/3.10.6/bin/streamlit", line 5, in <module>
    from streamlit.web.cli import main
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/streamlit/__init__.py", line 55, in <module>
    from streamlit.delta_generator import DeltaGenerator as _DeltaGenerator
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/streamlit/delta_generator.py", line 36, in <module>
    from streamlit import config, cursor, env_util, logger, runtime, type_util, util
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/streamlit/cursor.py", line 18, in <module>
    from streamlit.runtime.scriptrunner import get_script_run_ctx
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/streamlit/runtime/__init__.py", line 16, in <module>
    from streamlit.runtime.runtime import Runtime as Runtime
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/streamlit/runtime/runtime.py", line 29, in <module>
    from streamlit.proto.BackMsg_pb2 import BackMsg
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/streamlit/proto/BackMsg_pb2.py", line 5, in <module>
    from google.protobuf import descriptor as _descriptor
  File "/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/google/protobuf/descriptor.py", line 47, in <module>
    from google.protobuf.pyext import _message
ImportError: dlopen(/Users/*username*/.pyenv/versions/3.10.6/lib/python3.10/site-packages/google/protobuf/pyext/_message.cpython-310-darwin.so, 0x0002): symbol not found in flat namespace '__ZN6google8protobuf15FieldDescriptor12TypeOnceInitEPKS1_'

• 统一Python运行环境：当前命令同时调用了pyenv的Python3.10.6环境（streamlit所在）和anaconda3的Python3.9路径下的ipykernel_launcher.py，环境不匹配是核心问题。需：

  1. 选择一个固定环境（如pyenv的3.10.6或anaconda的3.9）
  2. 在该环境下重新安装所有依赖：pip install streamlit langchain protobuf
  3. 运行你自己编写的Streamlit脚本，而非ipykernel_launcher.py（这是Jupyter的启动文件，不能直接作为Streamlit入口）

• 重装protobuf依赖：报错源于protobuf的C扩展库符号缺失，执行以下命令重装：

  pip uninstall -y protobuf
  pip install protobuf==4.24.4  # 该版本与多数Streamlit版本兼容，可按需调整
  

• 清理缓存后重装所有依赖：若重装protobuf无效，清理pip缓存后重新安装全套依赖：

  pip cache purge
  pip install --no-cache-dir streamlit langchain protobuf
  

• 验证环境一致性：运行which python和which streamlit，确保输出路径属于同一个Python环境，避免跨环境调用导致的依赖混乱。

内容的提问来源于stack exchange，提问作者Lakeside52