dosubot[bot]
commented
8 months ago 🤖
Hello @rowanamgad, great to see you reaching out again! Hope you're doing well.
Thank you for providing such a detailed report. It seems like the issue you're encountering is due to the merge_dicts function in _merge.py not being able to handle merging of float values. This function is designed to merge two dictionaries, but it currently only supports merging of str, dict, and list types. If the types of the values from the 'left' and 'right' dictionaries are not one of these, and they are not equal, the function raises a TypeError.
Here is the relevant part of the code:
elif type(merged[k]) != type(v):
raise TypeError(
f'additional_kwargs["{k}"] already exists in this message,'
" but with a different type."
)
elif isinstance(merged[k], str):
merged[k] += v
elif isinstance(merged[k], dict):
merged[k] = merge_dicts(merged[k], v)
elif isinstance(merged[k], list):
merged[k] = merged[k] + v
else:
raise TypeError(
f"Additional kwargs key {k} already exists in left dict and value has "
f"unsupported type {type(merged[k])}."
)As you can see, there is no condition to handle merging of float values. This is likely the cause of the TypeError you're seeing.
Unfortunately, as a technical support rep, I don't have the ability to create pull requests or issues. However, I would recommend reporting this issue to the LangChain maintainers so they can consider adding support for merging float values in a future version of the framework. You can do this by creating a new issue in the LangChain repository and providing all the details you've shared here.
In the meantime, you might want to consider a workaround. If it's possible in your use case, you could convert the float values to strings before they are passed to the merge_dicts function, and then convert them back to floats after the merge. This would avoid the TypeError, but it might not be suitable for all use cases.
I hope this helps! If you have any further questions, please don't hesitate to ask.
leomensah
skozlovf
Checked other resources
Example Code
from langchain_google_vertexai import ChatVertexAI, VertexAI, VertexAIEmbeddings
llm_chain = LLMChain(llm=llm, prompt=prompt_template) res = llm_chain.predict(user_prompt=user_prompt)
Error Message and Stack Trace (if applicable)
Prompted _[llm/error] [1:chain:LLMChain > 2:llm:VertexAI] [4.64s] LLM run errored with error: "TypeError(\"Additional kwargs key Finance already exists in left dict and value has unsupported type <class 'float'>.\")Traceback (most recent call last):
Description
I'm trying to use text-unicorn model through vertex ai while setting the stream parameter to true. With every chunk generated by the llm, the generation_info dict contains key-value pairs where the key is the same but the value is different with every returned generation. Acoordingly a runtime error is raised and no propeper answer is returned from the llm.
System Info
System Information
Package Information
Packages not installed (Not Necessarily a Problem)
The following packages were not found: