LlamaIndex RAG system with multiple agents and Recursive Retriever

Question

I am trying to build a RAG system using LlamaIndex. I try to build individual agents, summary and vector indices for each document.

# define an "object" index and retriever over these tools
from llama_index import VectorStoreIndex
from llama_index.objects import ObjectIndex, SimpleToolNodeMapping
from llama_index.retrievers import RecursiveRetriever
from llama_index.query_engine import RetrieverQueryEngine
from llama_index.response_synthesizers import get_response_synthesizer

# define top-level retriever
vector_index = VectorStoreIndex(nodes, service_context=service_context)
vector_retriever = vector_index.as_retriever(similarity_top_k=5)

tool_mapping = SimpleToolNodeMapping.from_objects(all_tools)
obj_index = ObjectIndex.from_objects(
    all_tools,
    tool_mapping,
    VectorStoreIndex,
    service_context=service_context
)
     
# note: can pass `agents` dict as `query_engine_dict` since every agent can be used as a query engine
recursive_retriever = RecursiveRetriever(
    "vector",
    retriever_dict={"vector": vector_retriever},
    query_engine_dict=agents,
    verbose=True,
)

query_engine = RetrieverQueryEngine.from_args(
    recursive_retriever,
    service_context=service_context
)

the output of query_engine.get_prompts() is:

{'response_synthesizer:text_qa_template': SelectorPromptTemplate(metadata={'prompt_type': <PromptType.QUESTION_ANSWER: 'text_qa'>}, template_vars=['context_str', 'query_str'], kwargs={}, output_parser=None, template_var_mappings={}, function_mappings={}, default_template=PromptTemplate(metadata={'prompt_type': <PromptType.QUESTION_ANSWER: 'text_qa'>}, template_vars=['context_str', 'query_str'], kwargs={}, output_parser=None, template_var_mappings=None, function_mappings=None, template='Context information is below.\n---------------------\n{context_str}\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: {query_str}\nAnswer: '), conditionals=[(<function is_chat_model at 0x79b14ff72950>, ChatPromptTemplate(metadata={'prompt_type': <PromptType.CUSTOM: 'custom'>}, template_vars=['context_str', 'query_str'], kwargs={}, output_parser=None, template_var_mappings=None, function_mappings=None, message_templates=[ChatMessage(role=<MessageRole.SYSTEM: 'system'>, content="You are an expert Q&A system that is trusted around the world.\nAlways answer the query using the provided context information, and not prior knowledge.\nSome rules to follow:\n1. Never directly reference the given context in your answer.\n2. Avoid statements like 'Based on the context, ...' or 'The context information ...' or anything along those lines.", additional_kwargs={}), ChatMessage(role=<MessageRole.USER: 'user'>, content='Context information is below.\n---------------------\n{context_str}\n---------------------\nGiven the context information and not prior knowledge, answer the query.\nQuery: {query_str}\nAnswer: ', additional_kwargs={})]))]),
 'response_synthesizer:refine_template': SelectorPromptTemplate(metadata={'prompt_type': <PromptType.REFINE: 'refine'>}, template_vars=['query_str', 'existing_answer', 'context_msg'], kwargs={}, output_parser=None, template_var_mappings={}, function_mappings={}, default_template=PromptTemplate(metadata={'prompt_type': <PromptType.REFINE: 'refine'>}, template_vars=['query_str', 'existing_answer', 'context_msg'], kwargs={}, output_parser=None, template_var_mappings=None, function_mappings=None, template="The original query is as follows: {query_str}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer (only if needed) with some more context below.\n------------\n{context_msg}\n------------\nGiven the new context, refine the original answer to better answer the query. If the context isn't useful, return the original answer.\nRefined Answer: "), conditionals=[(<function is_chat_model at 0x79b14ff72950>, ChatPromptTemplate(metadata={'prompt_type': <PromptType.CUSTOM: 'custom'>}, template_vars=['context_msg', 'query_str', 'existing_answer'], kwargs={}, output_parser=None, template_var_mappings=None, function_mappings=None, message_templates=[ChatMessage(role=<MessageRole.USER: 'user'>, content="You are an expert Q&A system that strictly operates in two modes when refining existing answers:\n1. **Rewrite** an original answer using the new context.\n2. **Repeat** the original answer if the new context isn't useful.\nNever reference the original answer or context directly in your answer.\nWhen in doubt, just repeat the original answer.New Context: {context_msg}\nQuery: {query_str}\nOriginal Answer: {existing_answer}\nNew Answer: ", additional_kwargs={})]))])} 

when I run for a query i get the following error.

response = query_engine.query(query)

TemplateError: Conversation roles must alternate user/assistant/user/assistant/...

I am using Mistral-7B-Instruct-v0.2 as the llm.

I guess I need to modify the prompts but I do not know in which way should i do it.