Is it necessary add additional_fields to AgentChainElement ?

[svjack]

In the example of https://llama-cpp-agent.readthedocs.io/en/latest/map_chain/ If I want to add a AgentChainElement to it as

summary_chain = AgentChainElement("out_0", 
system_prompt="You are an advanced AI agent for summarizing articles", 
prompt="Summarize this article into bullet points:\n{item}")

translate_chain = AgentChainElement("out_1",
system_prompt="You are an advanced AI agent for translate articles",
 prompt="translate the content into French")

combine_chain = AgentChainElement("out_2",
system_prompt="You are an advanced AI agent that summarizes text",
prompt="You are an advanced AI agent that summarizes text", prompt="Please combine the French bullet points of different summaries below, into one summary as French bullet points:\n{map_output}")

map_chain = MapChain(agent, [summary_chain, translate_chain], [combine_chain])
out = map_chain.run_map_chain(items_to_map=article_list)

the translate_chain seems not take summary_chain's output as its input. Is it necessary add additional_fields (run_map_chain) to AgentChainElement Or I should call run_map_chain In sequence manually ?

[Maximilian-Winter]

@svjack Hi, I think your code should look something like this:

summary_chain = AgentChainElement("out_0",
                                  system_prompt="You are an advanced AI agent for summarizing articles",
                                  prompt="Summarize this article into bullet points:\n{item}")

translate_chain = AgentChainElement("out_1",
                                    system_prompt="You are an advanced AI agent for translate articles",
                                    prompt="translate the content into French:\n{out_0}")

combine_chain = AgentChainElement("out_2",
                                  system_prompt="You are an advanced AI agent that summarizes text",
                                  prompt="Please combine the French bullet points of different summaries below, into one summary as French bullet points:\n{map_output}")

map_chain = MapChain(agent, [summary_chain, translate_chain], [combine_chain])

map_chain.run_map_chain(items_to_map=article_list)

You basically pipe the output from the first element in the second as out_0 and then use the outputs of the first chain in the second with map_output

[Maximilian-Winter]

The elment summary_chain will forward its output to translate_chain. The two elements build the first map chain, which will be invoked on every input element ìtems_to_mapand then the results of all these runs will be put into one prompt for the combine_chain under map_output.

[Maximilian-Winter]

@svjack I added a full example like yours here: https://github.com/Maximilian-Winter/llama-cpp-agent/blob/master/examples/08_Chains/map_chain_summary_translate.py