柠檬叔的博客

第一个坑：关于模型名称

pip升级了

pip install -U qianfan

之后，程序其实是OK的

qianfan_chat_llm =QianfanChatEndpoint(streaming=True,model="ERNIE-Bot-8k")

然后模型名是ERNIE-Bot-8k

和平台上不一样，平台上是大写的8K，好在报错比较友好，改掉了

第二个坑：升级了LangChain后发生的包名报错

这才短短几个月啊

完全broken级别的升级的感觉，也是无奈了

from langchain.chains import ConversationChain
from langchain_community.chat_models import ChatOpenAI
from langchain_community.chat_models import QianfanChatEndpoint
from log_callback_handler import NiceGuiLogElementCallbackHandler
#https://python.langchain.com/docs/integrations/toolkits/sql_database
from langchain_community.agent_toolkits import create_sql_agent
from langchain_community.agent_toolkits import SQLDatabaseToolkit
from langchain.agents.agent_types import AgentType
from langchain.sql_database import SQLDatabase

多出来一个langchain_community

第三个坑：百度qianfan那个包自身的

https://github.com/langchain-ai/langchain/pull/18445

简单的说就是，运行的时候会报错：

lemonhall@lemonhallme:~/openai$ python3 sql.py


> Entering new SQL Agent Executor chain...
[INFO] [03-03 17:23:56] openapi_requestor.py:316 [t:140066326185792]: requesting llm api endpoint: /chat/ernie_bot_8k
[INFO] [03-03 17:23:56] oauth.py:207 [t:140066326185792]: trying to refresh access_token for ak `PDj0ZL***`
[INFO] [03-03 17:23:57] oauth.py:220 [t:140066326185792]: sucessfully refresh access_token
Traceback (most recent call last):
  File "/home/lemonhall/openai/sql.py", line 46, in <module>
    agent_executor.invoke("该数据库你认为大概率是怎样的一个应用？提示：该数据库的主表是notes表")
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/chains/base.py", line 163, in invoke
    raise e
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/chains/base.py", line 153, in invoke
    self._call(inputs, run_manager=run_manager)
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/agents/agent.py", line 1391, in _call
    next_step_output = self._take_next_step(
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/agents/agent.py", line 1097, in _take_next_step
    [
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/agents/agent.py", line 1097, in <listcomp>
    [
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/agents/agent.py", line 1125, in _iter_next_step
    output = self.agent.plan(
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain/agents/agent.py", line 387, in plan
    for chunk in self.runnable.stream(inputs, config={"callbacks": callbacks}):
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 2446, in stream
    yield from self.transform(iter([input]), config, **kwargs)
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 2433, in transform
    yield from self._transform_stream_with_config(
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 1513, in _transform_stream_with_config
    chunk: Output = context.run(next, iterator)  # type: ignore
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 2397, in _transform
    for output in final_pipeline:
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 1051, in transform
    for chunk in input:
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 4173, in transform
    yield from self.bound.transform(
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/runnables/base.py", line 1061, in transform
    yield from self.stream(final, config, **kwargs)
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py", line 250, in stream
    raise e
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/language_models/chat_models.py", line 241, in stream
    generation += chunk
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/outputs/chat_generation.py", line 57, in __add__
    generation_info = merge_dicts(
  File "/home/lemonhall/.local/lib/python3.9/site-packages/langchain_core/utils/_merge.py", line 38, in merge_dicts
    raise TypeError(
TypeError: Additional kwargs key created already exists in left dict and value has unsupported type <class 'int'>.

TypeError: Additional kwargs key created already exists in left dict and value has unsupported type <class 'int'>.

核心错误就是这一句话

解决方案：

https://github.com/langchain-ai/langchain/pull/18445

以后估计就不是什么问题了，这个是qianfan这个包的一些问题，导致需要去修改langchain_core核心包的里的内容