提取要点：
简单说就是，每个行为都有一定模板，给gpt生成
[Conversation]
All convo utterances 全部对话话语
Write down if there is anything from the conversation that !<INPUT 1>! might have found interesting from !<INPUT 2>!'s perspective, in a full sentence.
Here is the memory that is in !<INPUT 1>!'s head:
!<INPUT 2>!
Past Context:
!<INPUT 3>!
Task: Given the above, what should !<INPUT 9>! say to !<INPUT 10>! next in the conversation? And did it end the conversation?
Here is the conversation that happened between !<INPUT 0>! and !<INPUT 1>!.
!<INPUT 2>!
Summarize what !<INPUT 3>! thought about !<INPUT 4>! in one short sentence. The sentence needs to be in third person:
!<INPUT 12>! and !<INPUT 13>! are in !<INPUT 14>!. What would they talk about now?
原文：
对话变成记忆
memo_on_convo_v1.txt
Variables:
!<INPUT 0>! -- All convo utterances
!<INPUT 1>! -- persona name
!<INPUT 2>! -- persona name
!<INPUT 3>! -- persona name
<commentblockmarker>###</commentblockmarker>
[Conversation]
!<INPUT 0>!
Write down if there is anything from the conversation that !<INPUT 1>! might have found interesting from !<INPUT 2>!'s perspective, in a full sentence.
"!<INPUT 3>!
发起对话
iterative_convo_v1.txt
Variables:
!<INPUT 0>! -- persona ISS
!<INPUT 1>! -- persona name
!<INPUT 2>! -- retrieved memory
!<INPUT 3>! -- past context
!<INPUT 4>! -- current location
!<INPUT 5>! -- current context
!<INPUT 6>! -- persona name
!<INPUT 7>! -- target persona name
!<INPUT 8>! -- curr convo
!<INPUT 9>! -- persona name
!<INPUT 10>! -- target persona name
!<INPUT 11>! -- persona name
!<INPUT 12>! -- persona name
!<INPUT 13>! -- persona name
<commentblockmarker>###</commentblockmarker>
Context for the task:
PART 1.
!<INPUT 0>!
Here is the memory that is in !<INPUT 1>!'s head:
!<INPUT 2>!
PART 2.
Past Context:
!<INPUT 3>!
Current Location: !<INPUT 4>!
Current Context:
!<INPUT 5>!
!<INPUT 6>! and !<INPUT 7>! are chatting. Here is their conversation so far:
!<INPUT 8>!
---
Task: Given the above, what should !<INPUT 9>! say to !<INPUT 10>! next in the conversation? And did it end the conversation?
Output format: Output a json of the following format:
{
"!<INPUT 11>!": "<!<INPUT 12>!'s utterance>",
"Did the conversation end with !<INPUT 13>!'s utterance?": "<json Boolean>"
}
对话变成想法
convo_to_thoughts_v1.txt
Variables:
!<INPUT 0>! -- init persona name
!<INPUT 1>! -- target persona name
!<INPUT 2>! -- convo string
!<INPUT 3>! -- init persona name
!<INPUT 4>! -- target persona name or "the conversation"
<commentblockmarker>###</commentblockmarker>
Here is the conversation that happened between !<INPUT 0>! and !<INPUT 1>!.
!<INPUT 2>!
Summarize what !<INPUT 3>! thought about !<INPUT 4>! in one short sentence. The sentence needs to be in third person:
对话中
create_conversation_v2.txt
Variables:
!<INPUT 0>! -- init_persona iss
!<INPUT 1>! -- target_persona iss
!<INPUT 2>! -- init_persona_name
!<INPUT 3>! -- target_persona_name
!<INPUT 4>! -- init_persona's thoughts
!<INPUT 5>! -- target_persona_name
!<INPUT 6>! -- init_persona_name
!<INPUT 7>! -- target_persona's thoughts
!<INPUT 8>! -- current time
!<INPUT 9>! -- init_persona curr action description
!<INPUT 10>! -- target_persona curr action description
!<INPUT 11>! -- previous convo
!<INPUT 12>! -- init_persona_name
!<INPUT 13>! -- target_persona_name
!<INPUT 14>! -- curr_location name
!<INPUT 15>! -- init_persona_name
<commentblockmarker>###</commentblockmarker>
We have two characters.
Character 1.
!<INPUT 0>!
Character 2.
!<INPUT 1>!
---
Context:
Here is what !<INPUT 2>! thinks about !<INPUT 3>!:
!<INPUT 4>!
Here is what !<INPUT 5>! thinks about !<INPUT 6>!:
!<INPUT 7>!
Currently, it is !<INPUT 8>!
-- !<INPUT 9>!
-- !<INPUT 10>!
!<INPUT 11>!
!<INPUT 12>! and !<INPUT 13>! are in !<INPUT 14>!. What would they talk about now?
!<INPUT 15>!: "