Error: BaseLLM.__call__() missing 1 required positional argument: 'prompt'

[REKKKLESS]

I'm building a custom component in langflow. Even the prompt has been passed as per the langchain documentation , it's giving the following error: BaseLLM.__call__() missing 1 required positional argument: 'prompt'. Any suggestions would be appreciated.

def build(self, OpenAI:OpenAI,qa_retriever:VectorStoreRetriever)->RetrievalQA:
        prompt_template = """Use the following pieces of context to answer the question at the end. If 
        you don't know the answer, just say that you don't know, don't try to make up an answer.

        {context}

        Question: {question}
        """
        PROMPT = PromptTemplate(
            template=prompt_template, input_variables=["context", "question"]
        )
        qa = RetrievalQA.from_chain_type(
            llm=OpenAI(),
            chain_type="stuff",
            retriever=qa_retriever,
            return_source_documents=True,
            chain_type_kwargs={"prompt": PROMPT},
        )
        return qa

[dosubot[bot]]

Hey @REKKKLESS! Great to see you diving into new challenges. How's everything going on your end?

Based on the error message you're receiving, it seems like the BaseLLM class's __call__ method is expecting a prompt argument, but it's not being provided directly in the code you've shown.

In your code, you're using the PromptTemplate class to create a PROMPT object, which you then pass as a keyword argument to the RetrievalQA.from_chain_type method. However, the error message suggests that the prompt is not being passed as a required argument to the BaseLLM's __call__ method.

The issue might be with how the chain is being executed. When you do prompt | llm, it's supposed to create a chain where the prompt is passed to llm. However, the error indicates that when chain.invoke(input=inputs) is called, the prompt is not being passed as a required argument to the llm's __call__ method.

To resolve this issue, ensure that the chaining operation (prompt | llm) correctly passes the prompt to the llm's __call__ method. This behavior depends on the implementation of the __or__ method in either PromptTemplate or BaseLLM classes, which is not shown in the provided context. If you have access to these implementations, check that the __or__ method correctly handles the chaining to pass the prompt to the llm's __call__ method.

If you cannot modify the __or__ method or if the issue persists, you might need to directly call the llm with the prompt without using the | operator, ensuring that all required arguments are explicitly passed. However, without seeing the implementation of the BaseLLM class and how it expects to receive the prompt, it's challenging to provide a precise solution.

Unfortunately, I wasn't able to find the exact implementation of the BaseLLM class and its __call__ method in the langflow codebase. If you could provide more information about the BaseLLM class and its __call__ method, it would be easier to diagnose the issue and provide a more accurate solution.

Sources

• src/backend/langflow/components/chains/PromptRunner.py

About Dosu

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.

[Cristhianzl]

Hi! 👋

We are using other channels as our official means of communication with users. We apologize for the delayed response.
For faster assistance, please direct your questions to our Discord channel or open a GitHub issue, as we are much more active on these platforms.

Langflow Discord Server

Thank you for your understanding.

Best regards,
The Langflow Team