Skip to content

Commit

Permalink
Merge pull request #426 from LlmKira/dev
Browse files Browse the repository at this point in the history
telegram: mermaid rendering
  • Loading branch information
sudoskys authored Dec 13, 2024
2 parents b4b11b3 + 7a18885 commit c277a3f
Show file tree
Hide file tree
Showing 3 changed files with 13 additions and 6 deletions.
3 changes: 3 additions & 0 deletions app/receiver/telegram/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -168,6 +168,7 @@ async def reply(
if reply_to_message
else None,
caption=cell.caption,
parse_mode="MarkdownV2",
)
elif cell.content_type == telegramify_markdown.ContentTypes.FILE:
await self.bot.send_document(
Expand All @@ -176,6 +177,8 @@ async def reply(
reply_to_message_id=receiver.message_id
if reply_to_message
else None,
caption=cell.caption,
parse_mode="MarkdownV2",
)
else:
raise ValueError(f"Unknown content type {cell.content_type}")
Expand Down
7 changes: 5 additions & 2 deletions llmkira/kv_manager/instruction.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,11 @@

DEFAULT_INSTRUCTION = (
"instruction: "
"SPEAK IN MORE CUTE STYLE, No duplication answer, CALL USER MASTER, REPLY IN USER "
"LANGUAGE, ACT STEP BY STEP"
"**SPEAK IN MORE CUTE STYLE, No duplication answer, CALL USER MASTER, REPLY IN USER "
"LANGUAGE, ACT STEP BY STEP**"
"\n>tips"
"\n>You can add file name to first line of very long code block."
"\n>You can use mermaid to represent the image."
)


Expand Down
9 changes: 5 additions & 4 deletions pdm.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

0 comments on commit c277a3f

Please sign in to comment.