It was unexpected that I had to provide the accss_token when using QianfanLLMEndpoint

briup1 commented 11 months ago

System Info

Name: langchain Version: 0.0.312

Name: qianfan Version: 0.0.6

Who can help?

No response

Information

[x] The official example notebooks/scripts
[X] My own modified scripts

Related Components

[X] LLMs/Chat Models
[ ] Embedding Models
[ ] Prompts / Prompt Templates / Prompt Selectors
[ ] Output Parsers
[ ] Document Loaders
[ ] Vector Stores / Retrievers
[ ] Memory
[ ] Agents / Agent Executors
[ ] Tools / Toolkits
[ ] Chains
[ ] Callbacks/Tracing
[ ] Async

Reproduction

python
from langchain.llms import QianfanLLMEndpoint

llm = QianfanLLMEndpoint(qianfan_ak=client_id,qianfan_sk=client_secret,model="ERNIE-Bot-turbo")
res = llm("hi")
print(res)

error msg: 860 if not isinstance(prompt, str): 861 raise ValueError( 862 "Argument prompt is expected to be a string. Instead found " 863 f"{type(prompt)}. If you want to run the LLM on multiple prompts, use " 864 "generate instead." 865 ) 866 return ( --> 867 self.generate( 868 [prompt], 869 stop=stop, 870 callbacks=callbacks, 871 tags=tags, 872 metadata=metadata, 873 **kwargs, 874 ) 875 .generations[0][0] ... 166 ) 167 AuthManager().register(self._ak, self._sk, self._access_token) 168 else:

InvalidArgumentError: both ak and sk must be provided, otherwise access_token should be provided

Expected behavior

Normal operation

dosubot[bot] commented 11 months ago

🤖

Hello,

Thank you for reaching out and providing detailed information about the issue you're facing.

The QianfanLLMEndpoint class in LangChain is designed to interact with Baidu Qianfan's hosted open source or customized models. It requires the qianfan Python package to be installed and the environment variables qianfan_ak and qianfan_sk to be set with your API key and Secret Key. These keys can be obtained from https://cloud.baidu.com/product/wenxinworkshop.

From the error message you provided, it seems like the QianfanLLMEndpoint class is not receiving the qianfan_ak and qianfan_sk parameters correctly. The error message "both ak and sk must be provided, otherwise access_token should be provided" indicates that the class is not receiving either the API key and Secret Key or the access token.

Here is the correct way to use the QianfanLLMEndpoint class:

from langchain.llms import QianfanLLMEndpoint

llm = QianfanLLMEndpoint(qianfan_ak="your_ak", qianfan_sk="your_sk", model="ERNIE-Bot-turbo")
res = llm("hi")
print(res)

Please replace "your_ak" and "your_sk" with your actual API key and Secret Key.

If you're still facing the issue, could you please confirm if you're providing the correct API key and Secret Key? Also, please make sure that the qianfan Python package is installed correctly.

Regarding the changes made in the QianfanLLMEndpoint class between LangChain version 0.0.312 and the latest version 0.0.316, I'm sorry but I couldn't find any specific changes related to this class in the repository. If you're using an older version of LangChain, I would recommend updating to the latest version to ensure you have the most recent updates and bug fixes.

I hope this helps! If you have any other questions or need further clarification, please don't hesitate to ask.

Best regards.

Sources

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

danielhjz commented 11 months ago

Hi, Thanks for using Qianfan as your LLM. That is a bug in qianfan 0.0.6, Please upgrade your qianfan -> 0.0.7

# for pip 
pip install --upgrade qianfan

FYI @briup1

sqrt676 commented 8 months ago

ValueError: Argument prompt is expected to be a string. Instead found <class 'list'>. If you want to run the LLM on multiple prompts, use generate instead.

langchain-ai / langchain