ai-agents-langchain-input-keys-user-gets-error-missing-some-input-keys-question-w-e701d5b1

THEN Change the input key from 'query' to 'question' when calling the chain. Also configure ConversationBufferMemory with input_key='question' and output_key='answer', and ensure the prompt template includes a {question} variable.

# Correct invocation
result = qa({"question": prompt["prompt"]})

# Memory configuration
memory = ConversationBufferMemory(memory_key="chat_history", input_key="question", output_key="answer", return_messages=True)

# Prompt template must include {question}
prompt_template = """...{context}...{chat_history}...Question: {question}..."""