apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-06-05 14:55:18 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixbug: last_talk

Browse source
This commit is contained in:
莘权 马 2023-09-05 01:11:21 +08:00
parent 642cdd4a5f
commit 845cc8fbfd
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
metagpt/actions/talk_action.py
View file

@ -40,7 +40,7 @@ class TalkAction(Action):
prompt += "According to the historical conversation above, "
language = CONFIG.language or DEFAULT_LANGUAGE
prompt += (
f"Answer the following questions in {language}, and the answers must follow the Markdown format.\n "
f"Answer the following questions strictly in {language}, and the answers must follow the Markdown format.\n "
f"{self._talk}"
)
return prompt
@ -89,7 +89,7 @@ Statement: Your responses should align with the role-play agreement, maintaining
[KNOWLEDGE_END]
Statement: If the information is insufficient, you can search in the historical conversation or knowledge.
Statement: Answer the following questions in {language}, and the answers must follow the Markdown format
Statement: Answer the following questions strictly in {language}, and the answers must follow the Markdown format
, excluding any tag likes "[HISTORY_BEGIN]", "[HISTORY_END]", "[KNOWLEDGE_BEGIN]", "[KNOWLEDGE_END]", "[ASK_BEGIN]"
, "[ASK_END]"
@ -117,7 +117,7 @@ Statement: Your responses should maintaining the character's persona and habits.
[KNOWLEDGE_END]
Statement: If the information is insufficient, you can search in the historical conversation or knowledge.
Statement: Answer the following questions in {language}, and the answers must follow the Markdown format
Statement: Answer the following questions strictly in {language}, and the answers must follow the Markdown format
, excluding any tag likes "[HISTORY_BEGIN]", "[HISTORY_END]", "[KNOWLEDGE_BEGIN]", "[KNOWLEDGE_END]", "[ASK_BEGIN]"
, "[ASK_END]"