Exception while running node 'prompt_node' when query answer is not in document

[talhaanwarch]

Hi, I am getting this error. I want to know is there a way to handle this

Exception: Exception while running node 'prompt_node': Expected prompt parameters ['documents', 'query'] to be 
provided but got only ['query']. Make sure to provide all template parameters.
Enable debug logging to see the data that was passed when the pipeline failed.

This is how to reproduce it

retriever = EmbeddingRetriever(
    document_store=document_store, embedding_model="sentence-transformers/multi-qa-mpnet-base-dot-v1"
)
document_store.update_embeddings(retriever)

lfqa_prompt = PromptTemplate(
    name="lfqa",
    prompt_text="""Synthesize a comprehensive answer from the following text for the given question. 
                             Provide a clear and concise response that summarizes the key points and information presented in the text. 
                             Your answer should be in your own words and be no longer than 50 words.
                             If answer is not in .text. say i dont know.
                             \n\n Related text: {join(documents)} \n\n Question: {query} \n\n Answer:""",
)
prompt_node = PromptNode(model_name_or_path="google/flan-t5-large", default_prompt_template=lfqa_prompt)

pipe = Pipeline()
pipe.add_node(component=retriever, name="Retriever", inputs=["Query"])
pipe.add_node(component=prompt_node, name="prompt_node", inputs=["Retriever"])

output = pipe.run(
    query="who is obama?",
    params={
        "Retriever": {"top_k": 10},
        
    }
)
print(output["results"])

[ulan-yisaev]

I also encountered this error - after deleting some documents from the document store. It turns out that an empty list of Documents comes in the prompt_node.

[bogdankostic]

Hi @talhaanwarch and @ulan-yisaev! Thanks for reporting this, I created an issue for this (#4878).